The reviewed record of science sign in
Pith

arxiv: 2111.15667 · v3 · pith:FMA7ZI5X · submitted 2021-11-30 · cs.CV

Adaptive Token Sampling For Efficient Vision Transformers

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:FMA7ZI5Xrecord.jsonopen to challenge →

classification cs.CV
keywords visionmoduletransformertransformersgflopstokensadaptiveimage
0
0 comments X
read the original abstract

While state-of-the-art vision transformer models achieve promising results in image classification, they are computationally expensive and require many GFLOPs. Although the GFLOPs of a vision transformer can be decreased by reducing the number of tokens in the network, there is no setting that is optimal for all input images. In this work, we therefore introduce a differentiable parameter-free Adaptive Token Sampler (ATS) module, which can be plugged into any existing vision transformer architecture. ATS empowers vision transformers by scoring and adaptively sampling significant tokens. As a result, the number of tokens is not constant anymore and varies for each input image. By integrating ATS as an additional layer within the current transformer blocks, we can convert them into much more efficient vision transformers with an adaptive number of tokens. Since ATS is a parameter-free module, it can be added to the off-the-shelf pre-trained vision transformers as a plug and play module, thus reducing their GFLOPs without any additional training. Moreover, due to its differentiable design, one can also train a vision transformer equipped with ATS. We evaluate the efficiency of our module in both image and video classification tasks by adding it to multiple SOTA vision transformers. Our proposed module improves the SOTA by reducing their computational costs (GFLOPs) by 2X, while preserving their accuracy on the ImageNet, Kinetics-400, and Kinetics-600 datasets.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FOCUS: Fused Observation of Channels for Unveiling Spectra

    cs.CV 2025-07 unverdicted novelty 6.0

    FOCUS enables reliable spatial-spectral interpretability for frozen ViTs in hyperspectral imaging with class-specific prompts and a [SINK] token that reduces attention collapse.