Timezone: »

Long-Short Transformer: Efficient Transformers for Language and Vision
Chen Zhu · Wei Ping · Chaowei Xiao · Mohammad Shoeybi · Tom Goldstein · Anima Anandkumar · Bryan Catanzaro

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @ None #None

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%), while being more scalable on high-resolution images. The source code and models are released at https://github.com/NVIDIA/transformer-ls.

Author Information

Chen Zhu (University of Maryland, College Park)
Wei Ping (Baidu Research)
Chaowei Xiao (University of Michigan, Ann Arbor)

I am Chaowei Xiao, a third year PhD student in CSE Department, University of Michigan, Ann Arbor. My advisor is Professor Mingyan Liu . I obtained my bachelor's degree in School of Software from Tsinghua University in 2015, advised by Professor Yunhao Liu, Professor Zheng Yang and Dr. Lei Yang. I was also a visiting student at UC Berkeley in 2018, advised by Professor Dawn Song and Professor Bo Li. My research interest includes adversarial machine learning.

Mohammad Shoeybi (NVIDIA)
Tom Goldstein (Rice University)
Anima Anandkumar (NVIDIA / Caltech)
Bryan Catanzaro (NVIDIA)

More from the Same Authors