相关论文: Task-Aware Low-Rank Adaptation of Segment Anything…

Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high cost of retraining. While parameter-efficient tuning methods…

Large language models (LLMs) demonstrate strong task-specific capabilities through fine-tuning, but merging multiple fine-tuned models often leads to degraded performance due to overlapping instruction-following components. Task Arithmetic…

We propose SAM2LoRA, a parameter-efficient fine-tuning strategy that adapts the Segment Anything Model 2 (SAM2) for fundus image segmentation. SAM2 employs a masked autoencoder-pretrained Hierarchical Vision Transformer for multi-scale…

Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our…

Temporal Action Localization (TAL) methods typically operate on top of feature sequences from a frozen snippet encoder that is pretrained with the Trimmed Action Classification (TAC) tasks, resulting in a task discrepancy problem. While…

Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods. Nevertheless, while LoRA improves efficiency,…

This paper introduces a new Segment Anything Model (SAM) that leverages reverse parameter configuration and test-time training to enhance its performance on Camouflaged Object Detection (COD), named SAM-TTT. While most existing SAM-based…

Recently, the first foundation model developed specifically for image segmentation tasks was developed, termed the "Segment Anything Model" (SAM). SAM can segment objects in input imagery based on cheap input prompts, such as one (or more)…

In the research field of few-shot learning, the main difference between image-based and video-based is the additional temporal dimension. In recent years, some works have used the Transformer to deal with frames, then get the attention…

Medical image segmentation is crucial for clinical diagnosis and treatment planning, especially when dealing with complex anatomical structures such as vessels. However, accurately segmenting vessels remains challenging due to their small…

Tongue segmentation serves as the primary step in automated TCM tongue diagnosis, which plays a significant role in the diagnostic results. Currently, numerous deep learning based methods have achieved promising results. However, when…

Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challenging due to data scarcity and efficiency constraints.…

The performance of image segmentation models has historically been constrained by the high cost of collecting large-scale annotated data. The Segment Anything Model (SAM) alleviates this original problem through a promptable,…

Recently, foundation models trained on massive datasets to adapt to a wide range of tasks have attracted considerable attention and are actively being explored within the computer vision community. Among these, the Segment Anything Model…

LoRA has become one of the most widely used parameter-efficient fine-tuning methods due to its simplicity and effectiveness. However, numerous studies have shown that LoRA often introduces substantial parameter redundancy, which not only…

Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system. Nonetheless, its performance is challenged by images…

Processing visual data often involves small adjustments or sequences of changes, e.g., image filtering, surface smoothing, and animation. While established graphics techniques like normal mapping and video compression exploit redundancy to…

Foundation models such as the recently introduced Segment Anything Model (SAM) have achieved remarkable results in image segmentation tasks. However, these models typically require user interaction through handcrafted prompts such as…

Low-Rank Adaptation (LoRA) has proven effective in reducing computational costs while maintaining performance comparable to fully fine-tuned foundation models across various tasks. However, its fixed low-rank structure restricts its…

Vision Foundation Models (VFMs) such as the Segment Anything Model (SAM) allow zero-shot or interactive segmentation of visual contents, thus they are quickly applied in a variety of visual scenes. However, their direct use in many Remote…