pith. sign in

In: Proceedings of the IEEE/CVF International Conference on Computer Vision

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

background 1

representative citing papers

Variational Feature Compression for Model-Specific Representations

cs.CV · 2026-04-08 · unverdicted · novelty 6.0

A variational latent bottleneck with KL regularization and a dynamic binary mask based on saliency produces model-specific features that keep high accuracy for one classifier but drop others below 2% on CIFAR-100 with over 45x suppression.

citing papers explorer

Showing 1 of 1 citing paper.

  • Variational Feature Compression for Model-Specific Representations cs.CV · 2026-04-08 · unverdicted · none · ref 13

    A variational latent bottleneck with KL regularization and a dynamic binary mask based on saliency produces model-specific features that keep high accuracy for one classifier but drop others below 2% on CIFAR-100 with over 45x suppression.