Long-Short Transformer: Efficient Transformers for Language and Vision

by   Chen Zhu, et al.

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic time and memory complexities with respect to the input sequence length. In this paper, we propose Long-Short Transformer (Transformer-LS), an efficient self-attention mechanism for modeling long sequences with linear complexity for both language and vision tasks. It aggregates a novel long-range attention with dynamic projection to model distant correlations and a short-term attention to capture fine-grained local correlations. We propose a dual normalization strategy to account for the scale mismatch between the two attention mechanisms. Transformer-LS can be applied to both autoregressive and bidirectional models without additional complexity. Our method outperforms the state-of-the-art models on multiple tasks in language and vision domains, including the Long Range Arena benchmark, autoregressive language modeling, and ImageNet classification. For instance, Transformer-LS achieves 0.97 test BPC on enwik8 using half the number of parameters than previous method, while being faster and is able to handle 3x as long sequences compared to its full-attention version on the same hardware. On ImageNet, it can obtain the state-of-the-art results (e.g., a moderate size of 55.8M model solely trained on 224x224 ImageNet-1K can obtain Top-1 accuracy 84.1 scalable on high-resolution images. The source code and models are released at https://github.com/NVIDIA/transformer-ls .


Focal Self-attention for Local-Global Interactions in Vision Transformers

Recently, Vision Transformer and its variants have shown great promise o...

Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding

Transformer has become ubiquitous in the deep learning field. One of the...

Learned Queries for Efficient Local Attention

Vision Transformers (ViT) serve as powerful vision models. Unlike convol...

Recasting Self-Attention with Holographic Reduced Representations

In recent years, self-attention has become the dominant paradigm for seq...

Multiscale Attention via Wavelet Neural Operators for Vision Transformers

Transformers have achieved widespread success in computer vision. At the...

FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention

We propose FMMformers, a class of efficient and flexible transformers in...

Axial Attention in Multidimensional Transformers

We propose Axial Transformers, a self-attention-based autoregressive mod...

Please sign up or login with your details

Forgot password? Click here to reset