Linear Video Transformer with Feature Fixation

Abstract

Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some studies alleviate the computational costs by reducing the number of tokens in attention calculation, but the complexity is still quadratic. Another promising way is to replace Softmax attention with linear attention, which owns linear complexity but presents a clear performance drop. We find that such a drop in linear attention results from the lack of attention concentration on critical features. Therefore, we propose a feature fixation module to reweight feature importance of the query and key before computing linear attention. Specifically, we regard the query, key, and value as various latent representations of the input token, and learn the feature fixation ratio by aggregating Query-Key-Value information. This is beneficial for measuring the feature importance comprehensively. Furthermore, we enhance the feature fixation by neighborhood association, which leverages additional guidance from spatial and temporal neighbouring tokens. The proposed method significantly improves the linear attention baseline and achieves state-of-the-art performance among linear video Transformers on three popular video classification benchmarks. With fewer parameters and higher efficiency, our performance is even comparable to some Softmax-based quadratic Transformers.

Exploring Transformer Extrapolation

“…Transformer (Vaswani et al 2017) is advancing steadily in the areas of natural language processing (Qin et al 2023b;Devlin et al 2019;Liu et al 2019;Qin et al 2022b,a;Liu et al 2022;Zhong 2023), computer vision (Dosovitskiy et al 2020;Sun et al 2022b;Lu et al 2022;Hao et al 2024), and audio processing (Gong, Chung, and Glass 2021; Akbari et al 2021;Gulati et al 2020;Sun et al 2022a). Although it outperforms other architectures such as RNNs (Cho et al 2014;Qin, Yang, and Zhong 2023) and CNNs (Kim 2014;Hershey et al 2016;Gehring et al 2017) in many sequence modeling tasks, its lack of length extrapolation capability limits its ability to handle a wide range of sequence lengths, i.e., inference sequences need to be equal to or shorter than training sequences.…”

Search task oriented path planning method of airborne radar network

“…Transformer [32] is advancing steadily in the areas of natural language processing [4,8,18,27,26,19], computer vision [9,2,31,21], and audio processing [12,1,13,30]. Although it outperforms other architectures such as RNNs [7] and CNNs [16,14,11] in many sequence modeling tasks, its lack of length extrapolation capability limits its ability to handle a wide range of sequence lengths, i.e., inference sequences need to be equal to or shorter than training sequences.…”