اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدEvo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
128
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadratic with respect to the input sequence length, a mainstream paradigm for computation reduction is to reduce the number of tokens. Existing designs include structured spatial compression that uses a progressive shrinking pyramid to reduce the computations of large feature maps, and unstructured token pruning that dynamically drops redundant tokens. However, the limitation of existing token pruning lies in two folds: 1) the incomplete spatial structure caused by pruning is not compatible with structured spatial compression that is commonly used in modern deep-narrow transformers; 2) it usually requires a time-consuming pre-training procedure. To tackle the limitations and expand the applicable scenario of token pruning, we present Evo-ViT, a self-motivated slow-fast token evolution approach for vision transformers. Specifically, we conduct unstructured instance-wise token selection by taking advantage of the simple and effective global class attention that is native to vision transformers. Then, we propose to update the selected informative tokens and uninformative tokens with different computation paths, namely, slow-fast updating. Since slow-fast updating mechanism maintains the spatial structure and information flow, Evo-ViT can accelerate vanilla transformers of both flat and deep-narrow structures from the very beginning of the training process. Experimental results demonstrate that our method significantly reduces the computational cost of vision transformers while maintaining comparable performance on image classification.
قيم البحث
اقرأ أيضاً
Recently the vision transformer (ViT) architecture, where the backbone purely consists of self-attention mechanism, has achieved very promising performance in visual classification. However, the high performance of the original ViT heavily depends on
pretraining using ultra large-scale datasets, and it significantly underperforms on ImageNet-1K if trained from scratch. This paper makes the efforts toward addressing this problem, by carefully considering the role of visual tokens. First, for classification head, existing ViT only exploits class token while entirely neglecting rich semantic information inherent in high-level visual tokens. Therefore, we propose a new classification paradigm, where the second-order, cross-covariance pooling of visual tokens is combined with class token for final classification. Meanwhile, a fast singular value power normalization is proposed for improving the second-order pooling. Second, the original ViT employs the naive embedding of fixed-size image patches, lacking the ability to model translation equivariance and locality. To alleviate this problem, we develop a light-weight, hierarchical module based on off-the-shelf convolutions for visual token embedding. The proposed architecture, which we call So-ViT, is thoroughly evaluated on ImageNet-1K. The results show our models, when trained from scratch, outperform the competing ViT variants, while being on par with or better than state-of-the-art CNN models. Code is available at https://github.com/jiangtaoxie/So-ViT
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, eg, the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and th
en applies multiple Transformer layers to model their global relation for classification. However, ViT achieves inferior performance to CNNs when trained from scratch on a midsize dataset like ImageNet. We find it is because: 1) the simple tokenization of input images fails to model the important local structure such as edges and lines among neighboring pixels, leading to low training sample efficiency; 2) the redundant attention backbone design of ViT leads to limited feature richness for fixed computation budgets and limited training samples. To overcome such limitations, we propose a new Tokens-To-Token Vision Transformer (T2T-ViT), which incorporates 1) a layer-wise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study. Notably, T2T-ViT reduces the parameter count and MACs of vanilla ViT by half, while achieving more than 3.0% improvement when trained from scratch on ImageNet. It also outperforms ResNets and achieves comparable performance with MobileNets by directly training on ImageNet. For example, T2T-ViT with comparable size to ResNet50 (21.5M parameters) can achieve 83.3% top1 accuracy in image resolution 384$times$384 on ImageNet. (Code: https://github.com/yitu-opensource/T2T-ViT)
Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we propose a dynam
ic token sparsification framework to prune redundant tokens progressively and dynamically based on the input. Specifically, we devise a lightweight prediction module to estimate the importance score of each token given the current features. The module is added to different layers to prune redundant tokens hierarchically. To optimize the prediction module in an end-to-end manner, we propose an attention masking strategy to differentiably prune a token by blocking its interactions with other tokens. Benefiting from the nature of self-attention, the unstructured sparse tokens are still hardware friendly, which makes our framework easy to achieve actual speed-up. By hierarchically pruning 66% of the input tokens, our method greatly reduces 31%~37% FLOPs and improves the throughput by over 40% while the drop of accuracy is within 0.5% for various vision transformers. Equipped with the dynamic token sparsification framework, DynamicViT models can achieve very competitive complexity/accuracy trade-offs compared to state-of-the-art CNNs and vision transformers on ImageNet. Code is available at https://github.com/raoyongming/DynamicViT
Deep neural networks can be converted to multi-exit architectures by inserting early exit branches after some of their intermediate layers. This allows their inference process to become dynamic, which is useful for time critical IoT applications with
stringent latency requirements, but with time-variant communication and computation resources. In particular, in edge computing systems and IoT networks where the exact computation time budget is variable and not known beforehand. Vision Transformer is a recently proposed architecture which has since found many applications across various domains of computer vision. In this work, we propose seven different architectures for early exit branches that can be used for dynamic inference in Vision Transformer backbones. Through extensive experiments involving both classification and regression problems, we show that each one of our proposed architectures could prove useful in the trade-off between accuracy and speed.
In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the attention m
aps among different transformer layers are redundant. Based on the observations above, we propose a PSViT: a ViT with token Pooling and attention Sharing to reduce the redundancy, effectively enhancing the feature representation ability, and achieving a better speed-accuracy trade-off. Specifically, in our PSViT, token pooling can be defined as the operation that decreases the number of tokens at the spatial level. Besides, attention sharing will be built between the neighboring transformer layers for reusing the attention maps having a strong correlation among adjacent layers. Then, a compact set of the possible combinations for different token pooling and attention sharing mechanisms are constructed. Based on the proposed compact set, the number of tokens in each layer and the choices of layers sharing attention can be treated as hyper-parameters that are learned from data automatically. Experimental results show that the proposed scheme can achieve up to 6.6% accuracy improvement in ImageNet classification compared with the DeiT.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
