SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult. Pruning, a traditional model compression paradigm for hardware efficiency, has been widely applied in various DNN structures. Nevertheless, it stays ambiguous on how to perform exclusive pruning on the ViT structure. Considering three key points: the structural characteristics, the internal data pattern of ViTs, and the related edge device deployment, we leverage the input token sparsity and propose a computation-aware soft pruning framework, which can be set up on vanilla Transformers of both flatten and CNN-type structures, such as Pooling-based ViT (PiT). More concretely, we design a dynamic attention-based multi-head token selector, which is a lightweight module for adaptive instance-wise token selection. We further introduce a soft pruning technique, which integrates the less informative tokens generated by the selector module into a package token that will participate in subsequent calculations rather than being completely discarded. Our framework is bound to the trade-off between accuracy and computation constraints of specific edge devices through our proposed computation-aware training strategy. Experimental results show that our framework significantly reduces the computation cost of ViTs while maintaining comparable performance on image classification. Moreover, our framework can guarantee the identified model to meet resource specifications of mobile devices and FPGA, and even achieve the real-time execution of DeiT-T on mobile platforms. For example, our method reduces the latency of DeiT-T to 26 ms (26%$\sim $41% superior to existing works) on the mobile device with 0.25%$\sim $4% higher top-1 accuracy on ImageNet.
Code (1)
Tasks
Efficient ViTsimage-classificationImage ClassificationModel CompressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Pruning Self-attentions into Convolutional Layers in Single Path
Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues:…
Efficient ViTsInductive BiasNeural Architecture SearchCross-Axis Transformer with 3D Rotary Positional Embeddings
Despite lagging behind their modal cousins in many respects, Vision Transformers have provided an interesting opportunity to bridge the gap between sequence modeling and image modeling. Up until now however, vision trans…
Interpret Vision Transformers as ConvNets with Dynamic Convolutions
There has been a debate about the superiority between vision Transformers and ConvNets, serving as the backbone of computer vision models. Although they are usually considered as two completely different architectures, i…
Integrated electro-optic attention nonlinearities for transformers
Transformers have emerged as the dominant neural-network architecture, achieving state-of-the-art performance in language processing and computer vision. At the core of these models lies the attention mechanism, which re…
Replacing softmax with ReLU in Vision Transformers
Previous research observed accuracy degradation when replacing the attention softmax with a point-wise activation such as ReLU. In the context of vision transformers, we find that this degradation is mitigated when divid…