Related papers: Low-Resolution Self-Attention for Semantic Segment…

Balancing accuracy and latency on high-resolution images is a critical challenge for lightweight models, particularly for Transformer-based architectures that often suffer from excessive latency. To address this issue, we introduce…

In remote sensing applications, such as disaster detection and response, real-time efficiency and model lightweighting are of critical importance. Consequently, existing remote sensing image super-resolution methods often face a trade-off…

Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent…

High-quality semantic segmentation relies on three key capabilities: global context modeling, local detail encoding, and multi-scale feature extraction. However, recent methods struggle to possess all these capabilities simultaneously.…

Self-attention has become a defacto choice for capturing global context in various vision applications. However, its quadratic computational complexity with respect to image resolution limits its use in real-time applications, especially…

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades…

Transformer architectures have exhibited remarkable performance in image super-resolution (SR). Since the quadratic computational complexity of the self-attention (SA) in Transformer, existing methods tend to adopt SA in a local region to…

Few-shot Semantic Segmentation (FSS) was proposed to segment unseen classes in a query image, referring to only a few annotated examples named support images. One of the characteristics of FSS is spatial inconsistency between query and…

Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objects before executing visual recognition tasks. Such systems…

Vision problems ranging from image clustering to motion segmentation to semi-supervised learning can naturally be framed as subspace segmentation problems, in which one aims to recover multiple low-dimensional subspaces from noisy and…

Vision-based Semantic Scene Completion (SSC) has gained much attention due to its widespread applications in various 3D perception tasks. Existing sparse-to-dense approaches typically employ shared context-independent queries across various…

Query-based methods have garnered significant attention in object detection since the advent of DETR, the pioneering query-based detector. However, these methods face challenges like slow convergence and suboptimal performance. Notably,…

The DETR-like segmentors have underpinned the most recent breakthroughs in semantic segmentation, which end-to-end train a set of queries representing the class prototypes or target segments. Recently, masked attention is proposed to…

Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity, yet state-of-the-art text-to-image diffusion models such as FLUX and SD3 remain confined…

Self-Attention has become prevalent in computer vision models. Inspired by fully connected Conditional Random Fields (CRFs), we decompose self-attention into local and context terms. They correspond to the unary and binary terms in CRF and…

Soft attention in Transformer-based Large Language Models (LLMs) is susceptible to incorporating irrelevant information from the context into its latent representations, which adversely affects next token generations. To help rectify these…

Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However,…

Although large language models (LLMs) have achieved significant success in natural language processing, they still struggle with long-context comprehension. Traditional approaches to mitigating this issue typically rely on fine-tuning or…

As a de facto solution, the vanilla Vision Transformers (ViTs) are encouraged to model long-range dependencies between arbitrary image patches while the global attended receptive field leads to quadratic computational cost. Another branch…

Few-shot semantic segmentation (FSS) aims to segment novel classes in query images using only a small annotated support set. While prior research has mainly focused on improving decoders, the encoder's limited ability to extract meaningful…