Judy Hoffman

33

Papers

348

Total Citations

Papers (33)

Label Efficient Learning of Transferable Representations acrosss Domains and Tasks

Model merging with SVD to tie the Knots

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders

Improving Personalized Search with Regularized Low-Rank Parameter Updates

Learning With Side Information Through Modality Hallucination

Cross Modal Distillation for Supervision Transfer

Adversarial Discriminative Domain Adaptation

VisCUIT: Visual Auditor for Bias in CNN Image Classifier

Spatial Semantic Regularisation for Large Scale Object Detection

Simultaneous Deep Transfer Across Domains and Tasks

Fine-Grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach

Inferring and Executing Programs for Visual Reasoning

SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation

Active Domain Adaptation via Clustering Uncertainty-Weighted Embeddings

RobustNav: Towards Benchmarking Robustness in Embodied Navigation

SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

FACTS: First Amplify Correlations and Then Slice to Discover Bias

PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization

Benchmarking Low-Shot Robustness to Natural Distribution Shifts

TIDE: A General Toolbox for Identifying Object Detection Errors

Learning to Balance Specificity and Invariance for In and Out of Domain Generalization

Temporal Action Detection With Multi-Level Supervision

Contrastive Flow Matching

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning

Algorithms and Theory for Multiple-Source Adaptation

Auxiliary Task Reweighting for Minimum-data Learning

Scalable Diverse Model Selection for Accessible Transfer Learning

Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency

ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings

LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

CyCADA: Cycle-Consistent Adversarial Domain Adaptation