Shallow layers are most robust to corruptions early in training; freezing them (EPS) or rewinding them (AWR) reduces corruption error on several benchmarks, with caveats.
In: Proceedings of the IEEE/CVF international conference on computer vision workshops
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Robustness Emerges Early in Training Dynamics, but Is Not Preserved
Shallow layers are most robust to corruptions early in training; freezing them (EPS) or rewinding them (AWR) reduces corruption error on several benchmarks, with caveats.