Papers › Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular...

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

18 Nov 2022CVPR 2023 1arXiv:2211.10526archive 2025-07-28

Haoran You, Yunyang Xiong, Xiaoliang Dai, Bichen Wu, Peizhao Zhang, Haoqi Fan, Peter Vajda, Yingyan Celine Lin

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a quadratic complexity with the number of 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% higher accuracy or 40% MACs reduction on ImageNet classification and 1.2 higher mAP on COCO detection under comparable FLOPs, as compared to ViTs with vanilla softmax-based attentions.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

gatech-eic/castling-vit officialmentioned on GitHubpytorchApache-2.0Syntology: not harvested report
MindCode-4/code-11 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Entropy Law: The Story Behind Data Compression and LLM Performance (arXiv:2407.06645; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-6 mindsporeSyntology: not harvested report
MindSpore-scientific/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Coneheads: Hierarchy Aware Attention (arXiv:2306.00392; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Efficient ViTs

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionDepthwise ConvolutionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections