Related papers: Dilated Neighborhood Attention Transformer

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…

We propose Differentiable Window, a new neural module and general purpose component for dynamic window selection. While universally applicable, we demonstrate a compelling use case of utilizing Differentiable Window to improve standard…

Convolutional denoising autoencoders (DAEs) are powerful tools for image restoration. However, they inherit a key limitation of convolutional neural networks (CNNs): they tend to recover low-frequency features, such as smooth regions, more…

Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resolution transformers have…

Current state-of-the-art Neural Architecture Search (NAS) methods neither efficiently scale to multiple hardware platforms, nor handle diverse architectural search-spaces. To remedy this, we present DONNA (Distilling Optimal Neural Network…

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational…

We propose a novel perspective of the attention mechanism by reinventing it as a memory architecture for neural networks, namely Neural Attention Memory (NAM). NAM is a memory structure that is both readable and writable via differentiable…

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

In this paper, we present a comparative analysis of various self-supervised Vision Transformers (ViTs), focusing on their local representative power. Inspired by large language models, we examine the abilities of ViTs to perform various…

In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and…

Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when…

Automated segmentation of structural defects from visual inspection imagery remains challenging due to the diversity of damage types, extreme class imbalance, and the need for precise boundary delineation. This paper presents DeltaSeg, a…

We introduce Iwin Transformer, a novel position-embedding-free hierarchical vision transformer, which can be fine-tuned directly from low to high resolution, through the collaboration of innovative interleaved window attention and depthwise…

In the field of medical CT image processing, convolutional neural networks (CNNs) have been the dominant technique.Encoder-decoder CNNs utilise locality for efficiency, but they cannot simulate distant pixel interactions properly.Recent…

Accurate medical image segmentation requires effective modeling of both long-range dependencies and fine-grained boundary details. While transformers mitigate the issue of insufficient semantic information arising from the limited receptive…

The vanilla self-attention mechanism inherently relies on pre-defined and steadfast computational dimensions. Such inflexibility restricts it from possessing context-oriented generalization that can bring more contextual cues and global…

Transformer-based models are popularly used in natural language processing (NLP). Its core component, self-attention, has aroused widespread interest. To understand the self-attention mechanism, a direct method is to visualize the attention…

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…