Pairwise scoring signals in Vision Transformer token reduction are inherently unstable due to high perturbation counts and degrade in deep layers, causing collapse, while unary signals with triage enable CATIS to retain 96.9% accuracy at 63% FLOPs reduction on ViT-Large ImageNet-1K.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
MDSE attack uses dynamic multi-surrogate gradient estimation to create adversarial examples that simultaneously fool SNNs, ViTs, and CNNs, with reported gains up to 91.4% on ensembles and 3x on adversarially trained SNNs versus Auto-PGD.
Compact bidirectional transformer integrates L2R and R2L flows with sentence-level ensemble and two-flow self-critical training to achieve SOTA on MSCOCO without vision-language pretraining.
citing papers explorer
-
Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals
Pairwise scoring signals in Vision Transformer token reduction are inherently unstable due to high perturbation counts and degrade in deep layers, causing collapse, while unary signals with triage enable CATIS to retain 96.9% accuracy at 63% FLOPs reduction on ViT-Large ImageNet-1K.
-
Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
MDSE attack uses dynamic multi-surrogate gradient estimation to create adversarial examples that simultaneously fool SNNs, ViTs, and CNNs, with reported gains up to 91.4% on ensembles and 3x on adversarially trained SNNs versus Auto-PGD.
-
Image Captioning via Compact Bidirectional Architecture
Compact bidirectional transformer integrates L2R and R2L flows with sentence-level ensemble and two-flow self-critical training to achieve SOTA on MSCOCO without vision-language pretraining.