8 papers
Coordination on a Budget: Federated Active Learning with Few Labels
Liam Mohr, Daphna Weinshall
Federated Active Learning (FAL) addresses the dual challenges of data privacy and label scarcity, where the absence of a global data view introduces additional hurdles for coordina…
VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation
Eli Corn, Daphna Weinshall
Deep learning models may converge to suboptimal solutions despite strong validation accuracy, masking an optimization failure we term Trajectory Deviation. This is because as train…
Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers
Danit Yanowsky, Daphna Weinshall
Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selectio…
DCoM: Active Learning for All Learners
Inbal Mishal, Daphna Weinshall
Deep Active Learning (AL) techniques can be effective in reducing annotation costs for training deep models. However, their effectiveness in low- and high-budget scenarios seems to…
Forget Me Not: Fighting Local Overfitting with Knowledge Fusion and Distillation
Uri Stern, Eli Corn, Daphna Weinshall
Overfitting in deep neural networks occurs less frequently than expected. This is a puzzling observation, as theory predicts that greater model capacity should eventually lead to o…
Active Learning with a Noisy Annotator
Netta Shafir, Guy Hacohen, Daphna Weinshall
Active Learning (AL) aims to reduce annotation costs by strategically selecting the most informative samples for labeling. However, most active learning methods struggle in the low…