An official website of the United States government
Vision transformers (ViTs) have recently set off a new wave in neural architecture design thanks to their record-breaking performance in various vision tasks. In parallel, to fulfill the goal of deploying ViTs into real-world vision applications, their robustness against potential malicious attacks has gained increasing attention. In particular, recent works show that ViTs are more robust against adversarial attacks as compared with convolutional neural networks (CNNs), and conjecture that this is because ViTs focus more on capturing global interactions among different input/feature patches, leading to their improved robustness to local perturbations imposed by adversarial attacks. In this work, we ask an intriguing question: “Under what kinds of perturbations do ViTs become more vulnerable learners compared to CNNs?” Driven by this question, we first conduct a comprehensive experiment regarding the robustness of both ViTs and CNNs under various existing adversarial attacks to understand the underlying reason favoring their robustness. Based on the drawn insights, we then propose a dedicated attack framework, dubbed Patch-Fool, that fools the self-attention mechanism by attacking its basic component (i.e., a single patch) with a series of attention-aware optimization techniques. Interestingly, our Patch-Fool framework shows for the first time that ViTs are not necessarily more robust than CNNs against adversarial perturbations. In particular, we find that ViTs are more vulnerable learners compared with CNNs against our Patch-Fool attack which is consistent across extensive experiments, and the observations from Sparse/Mild Patch-Fool, two variants of Patch-Fool, indicate an intriguing insight that the perturbation density and strength on each patch seem to be the key factors that influence the robustness ranking between ViTs and CNNs. It can be expected that our Patch-Fool framework will shed light on both future architecture designs and training schemes for robustifying ViTs towards their real-world deployment. Our codes are available at https://github.com/RICE-EIC/Patch-Fool.
more »
« less
Efficient Vision Transformer for Human Pose Estimation via Patch Selection. British Machine Vision Conference
While Convolutional Neural Networks (CNNs) have been widely successful in 2D human pose estimation, Vision Transformers (ViTs) have emerged as a promising alternative to CNNs, boosting state-of-the-art performance. However, the quadratic computational complexity of ViTs has limited their applicability for processing high-resolution images. In this paper, we propose three methods for reducing ViT’s computational complexity, which are based on selecting and processing a small number of most informative patches while disregarding others. The first two methods leverage a lightweight pose estimation network to guide the patch selection process, while the third method utilizes a set of learnable joint tokens to ensure that the selected patches contain the most important information about body joints. Experiments across six benchmarks show that our proposed methods achieve a significant reduction in computational complexity, ranging from 30% to 44%, with only a minimal drop in accuracy between 0% and 3.5%.
more »
« less
- Award ID(s):
- 2124277
- PAR ID:
- 10540592
- Publisher / Repository:
- British Machine Vision Conference
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Vision Transformers (ViTs) are built on the assumption of treating image patches as “visual tokens” and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual tokenizer. The patch-to-patch attention suffers from the quadratic complexity issue, and also makes it non-trivial to explain learned ViTs. To address these issues in ViT, this paper proposes to learn Patch-to-Cluster attention (PaCa) in ViT. Queries in our PaCa-ViT starts with patches, while keys and values are directly based on clustering (with a predefined small number of clusters). The clusters are learned end-to-end, leading to better tokenizers and inducing joint clustering-for-attention and attention-for-clustering for better and interpretable models. The quadratic complexity is relaxed to linear complexity. The proposed PaCa module is used in designing efficient and interpretable ViT backbones and semantic segmentation head networks. In experiments, the proposed methods are tested on ImageNet-1k image classification, MS-COCO object detection and instance segmentation and MIT-ADE20k semantic segmentation. Compared with the prior art, it obtains better performance in all the three benchmarks than the SWin [32] and the PVTs [47], [48] by significant margins in ImageNet-1k and MIT-ADE20k. It is also significantly more efficient than PVT models in MS-COCO and MIT-ADE20k due to the linear complexity. The learned clusters are semantically meaningful. Code and model checkpoints are available at https:/github.com/iVMCL/PaCaViT.more » « less
-
Vision Transformers (ViTs) have shown impressive per-formance but still require a high computation cost as compared to convolutional neural networks (CNNs), one rea-son is that ViTs' attention measures global similarities and thus has a quadratic complexity with the number of in-put tokens. Existing efficient ViTs adopt local attention or linear attention, which sacrifice ViTs' capabilities of capturing either global or local context. In this work, we ask an important research question: Can ViTs learn both global and local context while being more efficient during inference? To this end, we propose a framework called Castling- ViT, which trains ViTs using both linear-angular attention and masked softmax-based quadratic attention, but then switches to having only linear-angular attention during inference. Our Castling- ViT leverages angular ker-nels to measure the similarities between queries and keys via spectral angles. And we further simplify it with two techniques: (1) a novel linear-angular attention mechanism: we decompose the angular kernels into linear terms and high-order residuals, and only keep the linear terms; and (2) we adopt two parameterized modules to approximate high-order residuals: a depthwise convolution and an aux-iliary masked softmax attention to help learn global and lo-cal information, where the masks for softmax attention are regularized to gradually become zeros and thus incur no overhead during inference. Extensive experiments validate the effectiveness of our Castling- ViT, e.g., achieving up to a 1.8% higher accuracy or 40% MACs reduction on classification and 1.2 higher mAP on detection under comparable FLOPs, as compared to ViTs with vanilla softmax-based at-tentions. Project page is available at here.more » « less
-
Image classification in remote sensing and geographic information system (GIS) data containing various land cover classes is essential for efficient and sustainable land use estimation and other tasks like object detection, localization, and segmentation. Deep learning (DL) techniques have shown tremendous potential in the GIS domain. While convolutional neural networks (CNNs) have dominated image analysis, transformers have proven to be a unifying solution for several AI-based processing pipelines. Vision transformers (ViTs) can have comparable and, in some cases, better accuracy than a CNN. However, they suffer from a significant drawback associated with the excessive use of training parameters. Using trainable parameters generously can have multiple advantages ranging from addressing model scalability to explainability. This can have a significant impact on model deployment in edge devices with limited resources, such as drones. In this research, we explore, without using pre-trained weights, how the inherent structure of vision transformers behaves with custom modifications. To verify our proposed approach, these architectures are trained on multiple land cover datasets. Experiments reveal that a combination of lightweight convolutional layers, including ShuffleNet, along with depthwise separable convolutions and average pooling can reduce the trainable parameters by 17.85% and yet achieve higher accuracy than the base mobile vision transformer (MViT). It is also observed that utilizing a combination of convolution layers along with multi-headed self-attention layers in MViT variants provides better performance for capturing local and global features, unlike the standalone ViT architecture, which utilizes almost 95% more parameters than the proposed MViT variant.more » « less
-
Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs’ self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency and more extensive applications to resource constrained platforms. Meanwhile, existing accelerators dedicated to NLP Transformers are not optimal for ViTs. This is because there is a large difference between ViTs and Transformers for natural language processing (NLP) tasks: ViTs have a relatively fixed number of input tokens, whose attention maps can be pruned by up to 90% even with fixed sparse patterns, without severely hurting the model accuracy (e.g., <=1.5% under 90% pruning ratio); while NLP Transformers need to handle input sequences of varying numbers of tokens and rely on on-the-fly predictions of dynamic sparse attention patterns for each input to achieve a decent sparsity (e.g., >=50%). To this end, we propose a dedicated algorithm and accelerator co-design framework dubbed ViTCoD for accelerating ViTs. Specifically, on the algorithm level, ViTCoD prunes and polarizes the attention maps to have either denser or sparser fixed patterns for regularizing two levels of workloads without hurting the accuracy, largely reducing the attention computations while leaving room for alleviating the remaining dominant data movements; on top of that, we further integrate a lightweight and learnable auto-encoder module to enable trading the dominant high-cost data movements for lower-cost computations. On the hardware level, we develop a dedicated accelerator to simultaneously coordinate the aforementioned enforced denser and sparser workloads for boosted hardware utilization, while integrating on-chip encoder and decoder engines to leverage ViTCoD’s algorithm pipeline for much reduced data movements. Extensive experiments and ablation studies validate that ViTCoD largely reduces the dominant data movement costs, achieving speedups of up to 235.3×, 142.9×, 86.0×, 10.1×, and 6.8× over general computing platforms CPUs, EdgeGPUs, GPUs, and prior-art Transformer accelerators SpAtten and Sanger under an attention sparsity of 90%, respectively. Our code implementation is available at https://github.com/GATECH-EIC/ViTCoD.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
