Zero-shot Learning (ZSL) enables classifiers to recognize classes unseen during training, commonly via generative two stage methods: (1) learn visual semantic correlations from seen classes; (2) synthesize unseen class features from semantics to train classifiers. In this paper, we identify spurious visual semantic cor...
Zihan Ye, S. Gowda, Kaile Du et al.· IEEE Transactions on Pattern...· 0 citations
Test-time adaptation (TTA) has become a practical way to adapt deployed models to unlabeled target data, a setting that is especially relevant in computational pathology where staining, scanner, and cohort shifts are routine. While most TTA methods are evaluated by their effect on accuracy, clinical use also depends on...
R. G. Bahumanya, M. HarshithV., S. N. Gowda et al.· 0 citations
CARE is introduced, a closed-form concept erasure operator that replaces the raw target direction with a kept-subspace-aware direction computed from a small bank of retained concept anchors, and preserves non-target concepts more faithfully while maintaining competitive erasure across instance, style, and celebrity con...
Parth Upman, Nishita Jain, S. Gowda· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
