Library · Machine learning & AI
What Data Augmentation got wrong, from 72 theses
Summary written by a model from the records below: The records document numerous empirical failures, baseline defeats, and design rejections across diverse data augmentation techniques in vision, speech, text, and time-series domains. Models frequently suffered when augmentations introduced unrealistic artifacts, destroyed essential task semantics, overfit through excessive perturbations, or underperformed simpler unaugmented baselines. These records come from graduate theses, 2021 to 2026, each labeled with its degree where the repository states it, and each links to its thesis. They were extracted by language models reading the full text, so treat each as a lead to read, not a verdict.
Plus 5 problems the authors left open, listed at the end.
Failure modes, by theses reporting them
Select a mode to jump to its records.
Synthetic and generative augmentation produces unrealistic samples and distributional shifts
Generative models, diffusion pipelines, and synthetic speech generators often introduced grammatical errors, visual artifacts, or domain mismatches into training sets. Consequently, the augmented data degraded downstream task performance and failed to beat models trained on clean real samples.
Tried and failed
synthetic generative data augmentation applied to atypical speech recognition. Outcome: worse than baseline. Reason: synthetic audio failed to outperform simple addition of unperturbed out-of-domain control data
On matching data and model in LF-MMI-based dysarthric speech recognition · EPFL · PhD
Tried and failed
synthetic data augmentation using repurposed conditional embeddings applied to automatic speech recognition across accents. Outcome: worse than baseline. Reason: synthetic multi-accent speech generation did not improve downstream model performance over real data training
Voice conversion and text-to-speech for privacy protection applications · Imperial · PhD
Tried and failed
generative text data augmentation applied to text quantification training datasets. Outcome: worse than baseline. Reason: generated ungrammatical, nonsensical text with misspellings, degrading training data quality
Quantification learning with deep neural networks · Iowa State · PhD
Tried and failed
standard GAN data augmentation applied to photoplethysmography time-series signals. Outcome: worse than baseline. Reason: generated synthetic samples provided limited performance gain over simple baseline augmentation techniques
Toward accurate health monitoring through large-scale Photoplethysmography signal from wearable devices · Georgia Tech · PhD
Tried and failed
heavy synthetic data augmentation during pre-training without adaptation applied to semantic segmentation pre-training. Outcome: worse than baseline. Reason: severe domain shift and distortion introduced by augmentations without calibration layers hurt downstream performance
Label-Efficient Visual Understanding with Consistency Constraints · Virginia Tech · Doctorate
Lost to a baseline
ASR models fine-tuned with multi-accent TTS augmentation (FTaug: 7.88% WER, FMaug: 6.79% WER) were beaten by models fine-tuned on real data alone (FT: 7.66% WER, FM: 6.33% WER)
Voice conversion and text-to-speech for privacy protection applications · Imperial · PhD
Considered and rejected
Considered and rejected: Rejected Seq2Seq, GAN, and generative LM models (e.g. BART, PPLM) for text augmentation because generated text contained grammatical errors, misspellings, and lacked meaning.
Quantification learning with deep neural networks · Iowa State · PhD
Considered and rejected
Considered and rejected: Rejected adding instances via generative data augmentation to balance data diversity, due to introducing confounds from machine-generated text differing from human text.
Experiment Design for Hypotheses About How NLP Models Work · University of Washington · PhD
Considered and rejected
Considered and rejected: Rejected standard GANs for data augmentation because synthetic data may not accurately represent the true data distribution
A Novel Lightweight Convolutional Neural Network for Medical Image Classification and Segmentation · Saskatchewan · Master's
Tried and failed
generative neural network for data augmentation applied to imbalanced 3D medical image segmentation. Outcome: did not generalise. Reason: generated augmentations caused heavy overfitting to validation data and failed to generalize to unseen test data
Learning strategies for improving neural networks for image segmentation under class imbalance · Imperial · PhD
Tried and failed
generative data augmentation for image classification applied to histopathology whole slide image classification. Outcome: did not generalise. Reason: boosted internal validation metrics but failed to improve or degraded performance on external cohort
Advancing Personalized Medicine Through Generative Artificial Intelligence · Georgia Tech · PhD
Tried and failed
mixup data augmentation applied to medical image segmentation across population shifts. Outcome: worse than baseline. Reason: linear interpolation created unrealistic images that degraded generalization across pathological groups
Improving the domain generalization and robustness of neural networks for medical imaging · Imperial · PhD
Tried and failed
diffusion-based synthetic data augmentation for classification applied to medical image classification. Outcome: worse than baseline. Reason: accuracy gains saturated and diminished as real training sample sizes increased
Augmenting medical image classifiers with synthetic data across populations · Harvard · PhD
Tried and failed
heuristic and back-translation data augmentation for questions applied to machine reading comprehension. Outcome: worse than baseline. Reason: generated synthetic question variations did not provide useful training signal to improve reading comprehension accuracy
Machine Reading Comprehension: Challenges and Approaches · Cornell · PhD
Tried and failed
paraphrasing and surface copy for data augmentation applied to style-constrained text dataset augmentation. Reason: generated text failed to match target domain style and stylistic conventions
Contrastive Text Generation · MIT · PhD
Lost to a baseline
SemanticGAN-augmented models achieved lower pick-and-place accuracy (0.32 AC, 0.18 AG) than the baseline trained on 100 real samples with no augmentation (0.44 AC, 0.29 AG).
Data-Efficient Learning Frameworks for Adaptive Intelligent Robots in Human-Robot Collaboration Scenarios · Politecnico di Torino · PhD
Tried and failed
pretraining with synthetic trajectory data augmentation applied to visuomotor policy learning. Outcome: worse than baseline. Reason: variable quality in synthetic trajectories degraded downstream performance compared to human-only data
Scaling robot learning with heterogeneous data from the real world, simulation, and the web · UT Austin · PhD
Geometric and temporal perturbations destroy underlying domain semantics and label integrity
Transformations such as cropping, temporal shifts, aspect-ratio scaling, and word perturbations altered the fundamental meaning or label alignment of the data. These operations degraded models in domains where spatial structure, temporal continuity, or radiometric profiles are critical.
Tried and failed
frame-independent data augmentation applied to video representation learning. Outcome: worse than baseline. Reason: disrupts temporal coherence across video frames, degrading action recognition performance
Action Recognition with Knowledge Transfer · Virginia Tech · Doctorate
Tried and failed
rule-based text data augmentation applied to intent classification. Outcome: worse than baseline. Reason: heuristic word-level perturbations alter sentence semantics and label alignment
Lifelong Machine Learning with Data Efficiency and Knowledge Retention · EPFL · PhD
Considered and rejected
Considered and rejected: Rejected standard computer vision data augmentations (random cropping, horizontal flips, rotations) as they distort frequency and temporal representations in spectrograms.
Applications of Deep Convolutional Neural Networks to Passive Acoustic Monitoring of Baleen Whales · Dalhousie · PhD
Tried and failed
standard data augmentation techniques applied to semantic change detection. Outcome: worse than baseline. Reason: random rotations and blurring degraded fine-grained semantic boundary detection
Deep learning for building and validating geometric and semantic maps · Georgia Tech · PhD
Considered and rejected
Considered and rejected: Rejected standard data augmentation (rotations, flips, color jitter) for vineyard disease detection because disease symptoms affect radiometric response without altering plant morphology.
Service robotics and machine learning for close-range remote sensing · Politecnico di Torino · PhD
Considered and rejected
Considered and rejected: Rejected standard pix2pix data augmentations because resizing/rotating narrow bacterial cells produced discontinuities and invalid ground-truth labels.
Bacterial Deepfakes: Generating Synthetic Microscopy Data to Improve Adaptability of Deep Learning-Based Segmentation Models · University of Washington · PhD
Considered and rejected
Considered and rejected: Rejected standard image rotations/flips for IMC data augmentation because pixel intensity distributions within segmented cells remain invariant
A Computational Analysis Pipeline for Imaging Mass Cytometry Data for Cancer Research · Queen's University · Master's
Tried and failed
aggressive data augmentations in contrastive learning applied to image and video quality assessment. Reason: augmentations alter or destroy distortion information that defines perceptual quality labels
Learning variable frame rate and unsupervised video quality assessment · UT Austin · PhD
Considered and rejected
Considered and rejected: Rejected Random Swap (RS) and Random Deletion (RD) data augmentation techniques because literature showed they fail to preserve dataset class labels after augmentation.
DATA MINING AND RE-IDENTIFICATION: ANALYSIS OF DATABASE QUERY PATTERNS THAT POSE A THREAT TO ANONYMISED INFORMATION · De Montfort University · PhD
Considered and rejected
Considered and rejected: Rejected shear and strain data augmentation on X-ray datasets because distortive transformations generate unrealistic synthetic fractures
Deep Learning and Augmented Reality for 3D human-machine interaction · Politecnico di Torino · PhD
Tried and failed
generic time-series data augmentation applied to intertwined multivariate time-series data. Outcome: did not generalise. Reason: altered the underlying semantic meaning of the intertwined multivariate dynamics
Exploring dispersion dynamics in agitated mixers via numerical simulations and machine learning · Imperial · Doctorate
Tried and failed
random time-translation data augmentation applied to time-series neural posterior estimation. Outcome: worse than baseline. Reason: enforcing time-invariance degraded parameter posterior estimation precision compared to fixing the feature alignment
Gravitational Waveform Modelling with Machine Learning and for Eccentric Binary Systems · Cornell · PhD
Tried and failed
Random temporal shift data augmentation applied to 1D CNN time-series regression. Outcome: worse than baseline. Reason: Random signal shifts degraded prediction accuracy instead of improving shift invariance.
Virtual metrology applied to milling process · EPFL · PhD
Tried and failed
Cutout and intensity shifting data augmentations applied to self-supervised pretraining for 3D object detection. Outcome: worse than baseline. Reason: Augmentations destroyed inherent object information critical for downstream recognition
3D deep learning threat detection for real-time computed tomography baggage screening · Imperial · PhD
Considered and rejected
Considered and rejected: Rejected random rotation and random cropping data augmentation because zero-padded image corners produced all-zero artifact patches.
A Unified Framework for Advancing Soil Erosion and Flood Assessment Through Deep Learning and Process-Based Modeling · Tübingen · PhD
Considered and rejected
Considered and rejected: Rejected translation, scaling, and shearing data augmentations because objects of interest were small or located near image edges.
Machine Vision for Patient Monitoring in the Neonatal Intensive Care Unit · Carleton University · PhD
Considered and rejected
Considered and rejected: Rejected image augmentation using compressing and stretching because altering the height/width ratio distorted air-void circular morphology and confused them with noise.
Three-dimensional Segmentation of Air-void System in Hardened Concrete using Photometric Stereo and Artificial Intelligence Methods · Texas State University · PhD
Naive duplication and unblended augmentations provide no signal or encourage shortcut learning
Simple data duplication, redundant feature addition, and unblended cut-and-paste methods offered minimal performance gains over standard training. Furthermore, models frequently learned to exploit superficial augmentation artifacts present only in training distributions rather than learning generalizable representations.
Tried and failed
asymmetric data augmentation across dataset streams applied to incremental learning with reference data. Outcome: worse than baseline. Reason: model exploited augmentation artifacts present only in the training stream, degrading representation quality
Referencing Unlabelled World Data to Prevent Catastrophic Forgetting in Class-incremental Learning · Virginia Tech · Master's
Tried and failed
data augmentation during clustering optimization applied to deep image clustering network input. Outcome: worse than baseline. Reason: feeding augmented rather than raw samples directly to the clustering head degraded cluster assignment quality
Yet another image clustering framework using deep learning · Iowa State · Master's
Tried and failed
unfiltered auxiliary training data augmentation applied to image classification model training. Outcome: did not generalise. Reason: distribution shift and bias in auxiliary data degraded downstream test performance
Probing, Improving, and Verifying Machine Learning Model Robustness · MIT · PhD
Tried and failed
data augmentation in contrastive learning applied to visual similarity representation learning. Outcome: did not generalise. Reason: augmentation corrupted fine-grained similarity signals needed for zero-shot and fine attribute discrimination
Advancements in perceptual quality assessment for interactive media : from mobile cloud gaming to human avatar videos and facial expressions · UT Austin · PhD
Considered and rejected
Considered and rejected: Decided against fixed-edge mask data augmentation during training because it overfit to mask geometry and failed to generalize as well to localized vector orientations.
Dimensionality reduction for validating engine flow simulations · Oxford · PhD
Considered and rejected
Considered and rejected: Rejected copy-pasting small object data augmentation due to high likelihood of overfitting from lack of background blending
Tracking and Measuring Objects in Obscure Image Scenarios Through the Lens of Shot Put in Track and Field · Virginia Tech · Master's
Considered and rejected
Considered and rejected: Discarded very small crops in data augmentation for UNO because cropping occludes critical image information and ruins pseudo-label quality.
Knowledge transfer and retention in deep neural networks · University of Trento · PhD
Tried and failed
data augmentation across multiple sequential training stages applied to few-shot object detection training. Reason: applying augmentation in both stages offered no compounding benefit over single-stage application
Data- and compute-efficient visual recognition and generation · UT Austin · PhD
Considered and rejected
Considered and rejected: Rejected synthetic data generation and data augmentation because small dataset size could lead to overfitting, bias amplification, and false validity.
Methods for Classifying Driver Engagement in Autonomous Vehicles Using Physiological Sensors · Carleton University · Master's
Tried and failed
combining multiple photometric data augmentations applied to low-contrast object detection. Reason: yielded no considerable performance improvement over individual augmentations alone
Object detection for low-contrast complex background applications · Iowa State · PhD
Tried and failed
explicit geometric feature augmentation in vision transformers applied to satellite surface radiation retrieval. Outcome: no signal. Reason: features were redundant and showed no impact in training and sensitivity analyses
Solar Resource Assessment And Snow-Informed Design of Alpine Photovoltaic Power Plants · EPFL · PhD
Tried and failed
synthetic detection noise for track data augmentation applied to multi-object tracking models. Outcome: no signal. Reason: random object dropout and false positive injection yielded only marginal performance gains
Autonomous Vehicle Perception Quality Assessment · Virginia Tech · Doctorate
Tried and failed
data augmentation on small training subsets applied to keypoint detection in deep pose estimation. Reason: augmentation provided minimal performance gains over non-augmented training when sample size was very small
Video analytics for lameness detection in dairy cattle: Effects of background removal and deep image matting on farm videos · Iowa State · Master's
Noise injection and contrast perturbations degrade feature representations instead of improving robustness
Adding Gaussian noise, blur, color jitter, and bias fields impaired model representations rather than enhancing generalizability. These corruptions acted as misleading signals or increased vulnerability to out-of-distribution noise.
Tried and failed
additive white Gaussian noise data augmentation applied to audio speaker diarization. Outcome: worse than baseline. Reason: models showed poor noise robustness and performance degraded across all architectures
Speaker diarization: importance of the modulation spectrum and incorporating uncertainty modelling · Imperial · PhD
Tried and failed
data augmentation with noise and reverberation applied to speaker verification x-vector models. Outcome: worse than baseline. Reason: external noise and reverberation augmentation slightly increased equal error rate
Towards Automatic Analysis of Audio Recordings from Children with Autism Spectrum Disorder · Georgia Tech · PhD
Tried and failed
synthetic noise data augmentation during pre-training applied to aerial visual object detection models. Outcome: worse than baseline. Reason: degraded detection precision across multiple evaluation categories instead of improving robustness
Translating AI to Impact: Uncertainty and Human-Agent Interactions in Multi-Agent Systems for Public Health and Conservation · Harvard · PhD
Tried and failed
Gaussian noise and blur data augmentation applied to generative image and video models. Outcome: worse than baseline. Reason: Degraded generation and reconstruction performance instead of regularizing the models
Probabilistic learning and generation in deep sequence models · Imperial · PhD
Tried and failed
Gaussian noise data augmentation applied to adversarial robustness in deep learning. Outcome: worse than baseline. Reason: training on Gaussian-augmented data degraded robustness against adversarial perturbations
Robust Efficient Edge AI: New Principles and Frameworks for Empowering Artificial Intelligence on Edge Devices · Georgia Tech · PhD
Tried and failed
random gamma correction contrast augmentation applied to multi-scanner medical image segmentation. Outcome: did not generalise. Reason: provided only minor improvements when added to geometric data augmentation pipelines
Improving the domain generalization and robustness of neural networks for medical imaging · Imperial · PhD
Tried and failed
adversarial bias field augmentation applied to medical image segmentation domain generalization. Outcome: did not generalise. Reason: increased vulnerability to out-of-distribution spike noise artifacts, degrading segmentation performance
Improving the domain generalization and robustness of neural networks for medical imaging · Imperial · PhD
Tried and failed
standard random color jitter data augmentation applied to semantic image segmentation. Outcome: did not generalise. Reason: random perturbations increased subgroup demographic bias and induced excessive false positive predictions
Color Invariant Skin Segmentation · Virginia Tech · Master's
Tried and failed
Gaussian blur data augmentation for defocus robustness applied to microscopy image segmentation. Outcome: did not generalise. Reason: Synthetic Gaussian blur fails to capture real optical defocus characteristics and provides no benefit over unaugmented data
Single-cell Methods and Spatial Analysis for Highly Multiplexed Tissue Images · Harvard · PhD
Tried and failed
noisy text augmentation for cross-validation applied to transformer language models on small datasets. Outcome: overfit. Reason: augmentations lacked sufficient diversity and heightened model sensitivity to noise, worsening overfitting on small splits
Privacy-preserving dementia processing in speech · Imperial · PhD
Tried and failed
data augmentation with poorly conditioned transformations applied to multilayer perceptron training. Outcome: did not generalise. Reason: higher condition numbers in transformed training data increased test error on clean datasets
Computational Tradeoffs and Symmetry in Polynomial Nonnegativity · MIT · PhD
Tried and failed
Random contrast data augmentation applied to low-contrast object detection. Outcome: worse than baseline. Reason: generated uninformative or misleading features that acted as negative training examples
Object detection for low-contrast complex background applications · Iowa State · PhD
Tried and failed
spectral noise data augmentation applied to hyperspectral image semantic segmentation. Outcome: worse than baseline. Reason: None
Hyperspectral Remote Sensing for UXO Detection and Damage Assessment on Airfield Pavements · MIT · PhD
Augmentation pipelines frequently underperform unaugmented baselines and simple heuristics
Across several benchmark evaluations, models trained without data augmentation or with fixed baseline expansions achieved superior accuracy and lower loss compared to augmented approaches. Evaluated models in speech verification, robotics, and image classification repeatedly lost to their unaugmented counterparts.
Lost to a baseline
Duplication and Entity Replacement data augmentation baselines produced higher test RMSE than original unaugmented training across all tensor datasets
Accurate and Trustworthy Recommender Systems: Algorithms and Findings · Georgia Tech · PhD
Lost to a baseline
x-vector fine-tuned on ADReSSo2021 with data augmentation achieved 0.6862 accuracy, performing worse than the un-augmented fine-tuned baseline (0.7163).
LEARNING UTTERANCE LEVEL REPRESENTATION FROM SPEECH · Johns Hopkins · PhD
Lost to a baseline
On ImageNet test-time augmentation (10 samples), random crop (79.60%), AutoAugment (79.20%), and FastAutoAugment (79.28%) all degraded ResNet-50 performance compared to no augmentation (80.43%)
Incorporating inductive biases into machine learning algorithms · Oxford · PhD
Lost to a baseline
Baseline StarGAN-EVC achieved higher Macro-F1 (56.64% with no augmentation vs 55.41% augmented) in SER data augmentation experiments.
Enhancing speech intelligibility through paralinguistic features · Imperial · PhD
Lost to a baseline
On RawFooT D45 texture classification, AdaAug (75.27%) and Augerino (78.97%) achieved lower test accuracy than Random Augmentation (79.99%)
Incorporating inductive biases into machine learning algorithms · Oxford · PhD
Lost to a baseline
Small rotation data augmentation (86.0% accuracy) was beaten by the no-augmentation baseline (86.7% accuracy).
IMAGE QUALITY ASSESSMENT OF ACTIVE SONAR IMAGES THROUGH BAYESIAN DEEP LEARNING · Naval Postgraduate School · Master's
Lost to a baseline
On Iris UCI dataset, fixed expansion (r=0.1) achieved lower adaptive robust loss (0.0783) than adaptive augmentation (0.0870).
Novel Examination of Interpretable Surrogates and Adversarial Robustness in Machine Learning · York University · Master's
Lost to a baseline
On VLCS, style-transfer data augmentation failed to improve upon the unstylized baseline (72.31% vs 72.49% average accuracy).
Addressing Distributional Shift challenges in Computer Vision for Real-World Applications · Politecnico di Torino · PhD
Lost to a baseline
On Heart Disease UCI dataset, original unaugmented model achieved lower adaptive robust loss (0.3465) than adaptive augmentation (0.3604).
Novel Examination of Interpretable Surrogates and Adversarial Robustness in Machine Learning · York University · Master's
Lost to a baseline
No Adaptation baseline achieved higher recall on data1 for ResNet (0.969 vs 0.918/0.928) and EfficientNet (0.962 vs 0.859) compared to geometric and DCGAN augmentations.
Learning Effectively from Medical Imaging Datasets · Saskatchewan · PhD
Lost to a baseline
On Parkinsons UCI dataset, fixed expansion (r=0.1) achieved lower adaptive robust loss (0.1542) than adaptive augmentation (0.1627).
Novel Examination of Interpretable Surrogates and Adversarial Robustness in Machine Learning · York University · Master's
Overly aggressive, cascaded, or extended augmentation causes severe overfitting
Cascading multiple augmentations, using hard transformations, or extending training schedules with augmented data caused networks to overfit. Excessive distortion and multi-sample expansions disrupted feature representations and lowered certified or generalization accuracy.
Tried and failed
heavy multi-sample data augmentation applied to certified robustness via randomized smoothing. Outcome: worse than baseline. Reason: increased class-wise accuracy disparity and degraded overall certified accuracy compared to standard single-sample augmentation
Understanding and Improving Representational Robustness of Machine Learning Models · MIT · PhD
Tried and failed
sequential cascading of multiple distinct data augmentations applied to video action recognition training. Outcome: worse than baseline. Reason: compounding intra-clip and cross-clip augmentations degraded visual representations compared to stochastic single-augmentation selection
Action Recognition with Knowledge Transfer · Virginia Tech · Doctorate
Considered and rejected
Considered and rejected: Rejected data augmentation for industrial anomaly detection due to risks of overfitting and need for complex augmentation strategies.
Neuro-Symbolic Integration in Artificial Intelligence and its Applications · Politecnico di Torino · PhD
Considered and rejected
Considered and rejected: Rejected using a neural network parameterization for data augmentation transformations because it easily overfit validation proxies.
Learning strategies for improving neural networks for image segmentation under class imbalance · Imperial · PhD
Considered and rejected
Considered and rejected: Rejected hard augmentations (RandAug) for image consistency regularization in CoPrompt, as it caused severe feature divergence and lower accuracy (79.90%) vs simple augmentations (80.48%).
Representation Learning under Limited Supervision · Queen's University · PhD
Lost to a baseline
Default Augmentation baseline B (78.8% accuracy) beat MixUp (74.6%), CutMix (76.8%), and RandAugment (76.9%) on Kvasir dataset.
Training Strategy for Limited Labeled Data by Learning from Confusion · Iowa State · Master's
Tried and failed
continuous mosaic data augmentation throughout training applied to object detection model training. Outcome: worse than baseline. Reason: applying heavy mosaic augmentation for the entire duration degraded final model performance compared to disabling it late in training
Hierarchical transfer learning for small object detection · Iowa State · Master's
Tried and failed
extending training duration with standard data augmentation applied to image classification models. Outcome: overfit. Reason: training baseline models for longer schedules caused overfitting instead of performance gains
Unified confusion-derived learning framework for image classification · Iowa State · PhD
Tried and failed
training dataset expansion via data augmentation applied to object detection model training. Outcome: overfit. Reason: tripling the dataset using data augmenters caused model overfitting, worsening error rates
Reducing measurement error in magnetic particle inspection through the optimization of process parameters and artificially intelligent solutions · Iowa State · PhD
Tried and failed
adversarial sample augmentation during iterative training applied to reward model training for alignment. Outcome: overfit. Reason: low adversarial data diversity caused the model to overfit when adding too many generated samples
Robust and Flexible Reward Modeling for LLM Alignment · Georgia Tech · PhD
Tried and failed
fine-grained rotational data augmentation applied to image classification models. Outcome: overfit. Reason: excessive rotation steps introduced data redundancy that degraded generalization performance
Development of a method to classify and analyse the composition of mixed waste materials in real-time · Cranfield · PhD
Left open by the authors
Problems the authors named and did not get to.
Left open
Develop multimodal data augmentation methods bridging text and audio by pairing text augmentations with text-to-speech models for online speech processing. Blocker: None
Privacy-preserving dementia processing in speech · Imperial · PhD
Left open
Optimize RAG retrieval strategies and data augmentation techniques to enhance fidelity and diversity for sensor-text foundation models. Blocker: Requires the private in-home monitoring sensor dataset and pipeline from the thesis
Developing a foundation model in in-home monitoring data for healthcare applications · Imperial · Master's
Left open
Implement data augmentation on cross-site pretraining datasets in TransEHR to reduce the performance gap between full-model fine-tuning and last-layer MLP tuning. Blocker: Requires multi-site electronic health record datasets (like MIMIC or eICU/private clinical data with credentialing or restrictions).
Robust Representation Learning and Real-Time Serving of Deep Models for Health Time Series · Georgia Tech · PhD
Left open
Evaluate the impact of different data augmentation levels and techniques on the informal medical entity recognition (NER) model performance. Blocker: None
Supporting laypeople in learning formal medical terminology · TU Wien · PhD
Left open
Implement audio data augmentations and active learning strategies to improve sample balance and accuracy in BirdNET-based transfer learning. Blocker: None
Avian Conservation Bioacoustics in Human-modified Landscapes: Community Responses to Forest Management and Riparian Urbanization in the Pacific Northwest · University of Washington · PhD
Who has worked on this
Authors of the public theses cited on this page, most-cited first.
- Chen Chen · Imperial · PhD · 2021
Improving the domain generalization and robustness of neural networks for medical imaging - Sadia Chowdhury · York University · Master's · 2021
Novel Examination of Interpretable Surrogates and Adversarial Robustness in Machine Learning - Dominika Woszczyk · Imperial · PhD · 2024
Privacy-preserving dementia processing in speech - Francesco Nespoli · Imperial · PhD · 2024
Voice conversion and text-to-speech for privacy protection applications - N Miao · Oxford · PhD · 2024
Incorporating inductive biases into machine learning algorithms - Harman Singh Sangha · Iowa State · PhD · 2023
Object detection for low-contrast complex background applications - Zeju Li · Imperial · PhD · 2022
Learning strategies for improving neural networks for image segmentation under class imbalance - Lei Qi · Iowa State · PhD · 2021
Quantification learning with deep neural networks - Jin-Woo Choi · Virginia Tech · Doctorate · 2021
Action Recognition with Knowledge Transfer - Hadi Shokati · Tübingen · PhD · 2026
A Unified Framework for Advancing Soil Erosion and Flood Assessment Through Deep Learning and Process-Based Modeling - Yael Frischholz · EPFL · PhD · 2026
Solar Resource Assessment And Snow-Informed Design of Alpine Photovoltaic Power Plants - Giordano Jacuzzi · University of Washington · PhD · 2026
Avian Conservation Bioacoustics in Human-modified Landscapes: Community Responses to Forest Management and Riparian Urbanization in the Pacific Northwest
Checking a claim in this area?
We can run the same search on any method or claim. If nothing turns up, we will say so, and that proves nothing on its own.