Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference

by   Haoran You, et al.

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), due to the global similarity measurements and thus a quadratic complexity with the input tokens. Existing efficient ViTs adopt local attention (e.g., Swin) or linear attention (e.g., Performer), which sacrifice ViTs' capabilities of capturing either global or local context. In this work, we ask an important research question: Can ViTs learn both global and local context while being more efficient during inference? To this end, we propose a framework called Castling-ViT, which trains ViTs using both linear-angular attention and masked softmax-based quadratic attention, but then switches to having only linear angular attention during ViT inference. Our Castling-ViT leverages angular kernels to measure the similarities between queries and keys via spectral angles. And we further simplify it with two techniques: (1) a novel linear-angular attention mechanism: we decompose the angular kernels into linear terms and high-order residuals, and only keep the linear terms; and (2) we adopt two parameterized modules to approximate high-order residuals: a depthwise convolution and an auxiliary masked softmax attention to help learn both global and local information, where the masks for softmax attention are regularized to gradually become zeros and thus incur no overhead during ViT inference. Extensive experiments and ablation studies on three tasks consistently validate the effectiveness of the proposed Castling-ViT, e.g., achieving up to a 1.8 classification and 1.2 higher mAP on COCO detection under comparable FLOPs, as compared to ViTs with vanilla softmax-based attentions.


page 1

page 2

page 3

page 4


EfficientViT: Enhanced Linear Attention for High-Resolution Low-Computation Visual Recognition

Vision Transformer (ViT) has achieved remarkable performance in many vis...

Linear Video Transformer with Feature Fixation

Vision Transformers have achieved impressive performance in video classi...

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer

Vision Transformers (ViTs) have shown impressive performance and have be...

FLatten Transformer: Vision Transformer using Focused Linear Attention

The quadratic computation complexity of self-attention has been a persis...

X-ViT: High Performance Linear Vision Transformer without Softmax

Vision transformers have become one of the most important models for com...

LFACon: Introducing Anglewise Attention to No-Reference Quality Assessment in Light Field Space

Light field imaging can capture both the intensity information and the d...

EcoFormer: Energy-Saving Attention with Linear Complexity

Transformer is a transformative framework that models sequential data an...

Please sign up or login with your details

Forgot password? Click here to reset