SimA: Simple Softmax-free Attention For Vision Transformers

Soroush Abbasi Koohpayegani, Hamed Pirsiavash

Keywords: Computer Vision, Vision Transformer, Efficient Vision Transformer, Image Recognition

TL;DR: SimA is a simple softmax-free and hardware friendly attention that has on-par accuracy with SOTA vision transformers.

Abstract: Recently, vision transformers have become very popular. However, deploying them in many applications is computationally expensive partly due to the Softmax layer in the attention block. We introduce a simple yet effective, Softmax-free attention block, SimA, which normalizes query and key matrices with simple $\ell_1$-norm instead of using Softmax layer. Then, the attention block in SimA is a simple multiplication of three matrices, so SimA can dynamically change the ordering of the computation at the test time to achieve linear computation on the number of tokens or the number of channels. We empirically show that SimA applied to three SOTA variations of transformers, DeiT, XCiT, and CvT, results in on-par accuracy compared to the SOTA models, without any need for Softmax layer. Interestingly, changing SimA from multi-head to single-head has only a small effect on the accuracy, which further simplifies the attention block.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/sima-simple-softmax-free-attention-for-vision/code)