A test-time adaptation system that triggers model updates only on detected domain shifts, plus a decoupled batch-normalization update, achieves high accuracy with low energy on edge devices.
Pytorch image models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
BlackVIP adapts foundation models via a Coordinator for input-dependent visual prompts and SPSA-GC for gradient estimation, enabling robust transfer on 19 datasets with low memory use and a link to randomized smoothing robustness.
LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.
citing papers explorer
-
EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems
A test-time adaptation system that triggers model updates only on detected domain shifts, plus a decoupled batch-normalization update, achieves high accuracy with low energy on edge devices.
-
Robust Adaptation of Foundation Models with Black-Box Visual Prompting
BlackVIP adapts foundation models via a Coordinator for input-dependent visual prompts and SPSA-GC for gradient estimation, enabling robust transfer on 19 datasets with low memory use and a link to randomized smoothing robustness.
-
Breaking Global Self-Attention Bottlenecks in Transformer-based Spiking Neural Networks with Local Structure-Aware Self-Attention
LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.