conftrace_

normalized loss

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

data contribution (1) logit gradient (1) fasttext-based scorer (1) predictive data selection (1) compression efficiency (1) transferable attack (1) self-knowledge distillation (1) white-box attack (1) downstream performance (1) soft label (1)

Papers

Predictive Data Selection: The Data That Predicts Is the Data That Teaches ICML 2025 From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels ICCV 2023 Investigating Top-k White-Box and Transferable Black-Box Attack CVPR 2022