Related papers: AHCQ-SAM: Toward Accurate and Hardware-Compatible …

Large language models (LLMs) excel at natural language tasks but face deployment challenges due to their growing size outpacing GPU memory advancements. Model quantization mitigates this issue by lowering weight and activation precision,…

Segmenting objects with complex shapes, such as wires, bicycles, or structural grids, remains a significant challenge for current segmentation models, including the Segment Anything Model (SAM) and its high-quality variant SAM-HQ. These…

The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. While click and brush interactions are both well explored in…

The advent of foundation models signals a new era in artificial intelligence. The Segment Anything Model (SAM) is the first foundation model for image segmentation. In this study, we evaluate SAM's ability to segment features from eye…

Previous Quantization-Aware Training (QAT) methods for vision transformers rely on expensive retraining to recover accuracy loss in non-linear layer quantization, limiting their use in resource-constrained environments. In contrast,…

Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-constrained devices. To reduce their computational and memory burden, various compression…

Conventional model compression techniques for LLMs address high memory consumption and slow inference challenges but typically require computationally expensive retraining to preserve accuracy. In contrast, one-shot compression methods…

Medical image segmentation is vital for clinical diagnosis and quantitative analysis, yet remains challenging due to the heterogeneity of imaging modalities and the high cost of pixel-level annotations. Although general interactive…

Local feature detection and description play an important role in many computer vision tasks, which are designed to detect and describe keypoints in "any scene" and "any downstream task". Data-driven local feature learning methods need to…

Segment Anything Models (SAMs), known for their exceptional zero-shot segmentation performance, have garnered significant attention in the research community. Nevertheless, their performance drops significantly on severely degraded,…

Vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. Despite the high accuracy, deploying it in real applications raises critical challenges including the high…

Data-free quantization aims to achieve model quantization without accessing any authentic sample. It is significant in an application-oriented context involving data privacy. Converting noise vectors into synthetic samples through a…

Sharpness-Aware Minimization (SAM) is an optimization method that improves generalization performance of machine learning models. Despite its superior generalization, SAM has not been actively used in real-world applications due to its…

The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging…

Recently, promptable segmentation models, such as the Segment Anything Model (SAM), have demonstrated robust zero-shot generalization capabilities on static images. These promptable models exhibit denoising abilities for imprecise prompt…

Image Quality Assessment (IQA) is a challenging task that requires training on massive datasets to achieve accurate predictions. However, due to the lack of IQA data, deep learning-based IQA methods typically rely on pre-trained networks…

Diffusion models have achieved remarkable success in the image and video generation tasks. Nevertheless, they often require a large amount of memory and time overhead during inference, due to the complex network architecture and…

Surgical video segmentation is a critical task in computer-assisted surgery, essential for enhancing surgical quality and patient outcomes. Recently, the Segment Anything Model 2 (SAM2) framework has demonstrated remarkable advancements in…

Segment Anything Model (SAM) demonstrates powerful zero-shot capabilities; however, its accuracy and robustness significantly decrease when applied to medical image segmentation. Existing methods address this issue through modality fusion,…

Large language models (LLMs) achieve impressive performance across domains but face significant challenges when deployed on consumer-grade GPUs or personal devices such as laptops, due to high memory consumption and inference costs.…