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

Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…

Previous approaches for blind image super-resolution (SR) have relied on degradation estimation to restore high-resolution (HR) images from their low-resolution (LR) counterparts. However, accurate degradation estimation poses significant…

The performance of image super-resolution relies heavily on the accuracy of degradation information, especially under blind settings. Due to the absence of true degradation models in real-world scenarios, previous methods learn distinct…

Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…

Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing…

This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step to align with…

Given the broad application of infrared technology across diverse fields, there is an increasing emphasis on investigating super-resolution techniques for infrared images within the realm of deep learning. Despite the impressive results of…

Effective representation learning from text has been an active area of research in the fields of NLP and text mining. Attention mechanisms have been at the forefront in order to learn contextual sentence representations. Current…

How to identify and segment camouflaged objects from the background is challenging. Inspired by the multi-head self-attention in Transformers, we present a simple masked separable attention (MSA) for camouflaged object detection. We first…

We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as "visual" tokens…

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Image restoration and spectral reconstruction are longstanding computer vision tasks. Currently, CNN-transformer hybrid models provide state-of-the-art performance for these tasks. The key common ingredient in the architectural designs of…

In real-world scenarios, the performance of semantic segmentation often deteriorates when processing low-quality (LQ) images, which may lack clear semantic structures and high-frequency details. Although image restoration techniques offer a…

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger…

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

Semantic segmentation is a vital problem in computer vision. Recently, a common solution to semantic segmentation is the end-to-end convolution neural network, which is much more accurate than traditional methods.Recently, the decoders…

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to…

The dot product self-attention (DPSA) is a fundamental component of transformers. However, scaling them to long sequences, like documents or high-resolution images, becomes prohibitively expensive due to quadratic time and memory…

While large multi-modal models (LMMs) demonstrate promising capabilities in segmentation and comprehension, they still struggle with two limitations: inaccurate segmentation and hallucinated comprehension. These challenges stem primarily…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various applications, but their performance on long-context tasks is often limited by the computational complexity of attention mechanisms. We introduce a novel…