Related papers: Dilated Neighborhood Attention Transformer
Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…
Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…
Attention-based models such as transformers have shown outstanding performance on dense prediction tasks, such as semantic segmentation, owing to their capability of capturing long-range dependency in an image. However, the benefit of…
Humans can effectively find salient regions in complex scenes. Self-attention mechanisms were introduced into Computer Vision (CV) to achieve this. Attention Augmented Convolutional Network (AANet) is a mixture of convolution and…
Recently, Transformers have shown promising performance in various vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute, especially for the high-resolution vision tasks. Local…
In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational…
Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information.…
Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the quadratic cost of global attention. In this work, we observe…
Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging.…
Automatic medical image segmentation has made great progress benefit from the development of deep learning. However, most existing methods are based on convolutional neural networks (CNNs), which fail to build long-range dependencies and…
By incorporating the graph structural information into Transformers, graph Transformers have exhibited promising performance for graph representation learning in recent years. Existing graph Transformers leverage specific strategies, such…
To manage the complexity of transformers in video compression, local attention mechanisms are a practical necessity. The common approach of partitioning frames into patches, however, creates architectural flaws like irregular receptive…
Diffusion transformers (DiTs) have emerged as a powerful architecture for high-fidelity image generation, yet the quadratic cost of self-attention poses a major scalability bottleneck. To address this, linear attention mechanisms have been…
Medical image segmentation plays a pivotal role in automated diagnostic and treatment planning systems. In this work, we present DAUNet, a novel lightweight UNet variant that integrates Deformable V2 Convolutions and Parameter-Free…
Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g., content query and positional query) are still…
While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…
Single-frame infrared small target (SIRST) detection aims at separating small targets from clutter backgrounds. With the advances of deep learning, CNN-based methods have yielded promising results in generic object detection due to their…
Transformers have achieved promising results on a variety of tasks. However, the quadratic complexity in self-attention computation has limited the applications, especially in low-resource settings and mobile or edge devices. Existing works…
Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs. Yet, they generally require much more data for model pre-training. Most of recent works thus are dedicated to designing more…
Attention within windows has been widely explored in vision transformers to balance the performance, computation complexity, and memory footprint. However, current models adopt a hand-crafted fixed-size window design, which restricts their…