相关论文: Vision Transformers with Patch Diversification

Vision Transformer (ViT) is known to be highly nonlinear like other classical neural networks and could be easily fooled by both natural and adversarial patch perturbations. This limitation could pose a threat to the deployment of ViT in…

Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks. One of the simplest solutions is to directly search the optimal one via the widely used…

Transformers have become the standard in state-of-the-art vision architectures, achieving impressive performance on both image-level and dense pixelwise tasks. However, training vision transformers for high-resolution pixelwise tasks has a…

Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…

Vision transformers have shown remarkable performance in vision tasks, but enabling them for accessible and real-time use is still challenging. Quantization reduces memory and inference costs at the risk of performance loss. Strides have…

Vision transformers have shown excellent performance in computer vision tasks. As the computation cost of their self-attention mechanism is expensive, recent works tried to replace the self-attention mechanism in vision transformers with…

The key idea of current deep learning methods for dense prediction is to apply a model on a regular patch centered on each pixel to make pixel-wise predictions. These methods are limited in the sense that the patches are determined by…

Previous work has proposed many new loss functions and regularizers that improve test accuracy on image classification tasks. However, it is not clear whether these loss functions learn better representations for downstream tasks. This…

Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition. Although their performance has been greatly enhanced through…

Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability…

Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…

There has recently been great progress in automatic segmentation of medical images with deep learning algorithms. In most works observer variation is acknowledged to be a problem as it makes training data heterogeneous but so far no…

Vision transformers have gained significant attention and achieved state-of-the-art performance in various computer vision tasks, including image classification, instance segmentation, and object detection. However, challenges remain in…

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in…

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…

The aim of this paper is to study the influence of locality mechanisms in vision transformers. Transformers originated from machine translation and are particularly good at modelling long-range dependencies within a long sequence. Although…

The vision transformer (ViT) has advanced to the cutting edge in the visual recognition task. Transformers are more robust than CNN, according to the latest research. ViT's self-attention mechanism, according to the claim, makes it more…

Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…

Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger misclassifications. Most existing defenses assume a single patch…

High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without…