Related papers: ViM-Q: Scalable Algorithm-Hardware Co-Design for V…
State Space Models (SSMs) are emerging as a compelling alternative to Transformers because of their consistent memory usage and high performance. Despite this, scaling up SSMs on cloud services or limited-resource devices is challenging due…
Extracting actionable knowledge from industrial visual data is fundamentally bottlenecked by extreme class imbalance and the prohibitive computational complexity of modern foundation models. In semi-conductor manufacturing, identifying…
Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issues not only limit visibility but also degrade automatic tasks like detection.…
Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited resources. As an efficient model compression technique, vector quantization (VQ) excels in…
Hyperspectral image (HSI) classification remains challenging due to high spectral dimensionality, redundancy, and limited labeled data. Although convolutional neural networks (CNNs) and Vision Transformers (ViTs) achieve strong performance…
Recent progress in remote sensing image (RSI) super-resolution (SR) has exhibited remarkable performance using deep neural networks, e.g., Convolutional Neural Networks and Transformers. However, existing SR methods often suffer from either…
Image restoration is a key task in low-level computer vision that aims to reconstruct high-quality images from degraded inputs. The emergence of Vision Mamba, which draws inspiration from the advanced state space model Mamba, marks a…
Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems. However, most existing methods based on CNNs and transformers still suffer from substantial computational burdens and have…
Recent Vision Mamba (Vim) models exhibit nearly linear complexity in sequence length, making them highly attractive for processing visual data. However, the training methodologies and their potential are still not sufficiently explored. In…
Capturing long-range dependencies (LRD) efficiently is a core challenge in visual recognition, and state-space models (SSMs) have recently emerged as a promising alternative to self-attention for addressing it. However, adapting SSMs into…
Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…
Mamba has recently garnered attention as an effective backbone for vision tasks. However, its underlying mechanism in visual domains remains poorly understood. In this work, we systematically investigate Mamba's representational properties…
Mamba is an effective state space model with linear computation complexity. It has recently shown impressive efficiency in dealing with high-resolution inputs across various vision tasks. In this paper, we reveal that the powerful Mamba…
Semantic segmentation of remote sensing imagery is a fundamental task in computer vision, supporting a wide range of applications such as land use classification, urban planning, and environmental monitoring. However, this task is often…
Recently, State Space Models (SSMs), with Mamba as a prime example, have shown great promise for long-range dependency modeling with linear complexity. Then, Vision Mamba and the subsequent architectures are presented successively, and they…
Classifying 3D MRI images for early detection of Alzheimer's disease is a critical task in medical imaging. Traditional approaches using Convolutional Neural Networks (CNNs) and Transformers face significant challenges in this domain. CNNs,…
Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…
With the advancement of RNN models with linear complexity, the quadratic complexity challenge of transformers has the potential to be overcome. Notably, the emerging Mamba-2 has demonstrated competitive performance, bridging the gap between…
While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary…
Recent State Space Models (SSM), especially Mamba, have demonstrated impressive performance in visual modeling and possess superior model efficiency. However, the application of Mamba to visual tasks suffers inferior performance due to…