相关论文: How Universal Are SAM2 Features?

Sharpness-Aware Minimization (SAM) has attracted considerable attention for its effectiveness in improving generalization in deep neural network training by explicitly minimizing sharpness in the loss landscape. Its success, however, relies…

Domain generalization (DG) aims to adapt a model using one or multiple source domains to ensure robust performance in unseen target domains. Recently, Parameter-Efficient Fine-Tuning (PEFT) of foundation models has shown promising results…

The Segment Anything Model (SAM), introduced to the computer vision community by Meta in April 2023, is a groundbreaking tool that allows automated segmentation of objects in images based on prompts such as text, clicks, or bounding boxes.…

Humans effortlessly interpret images by parsing them into part-whole hierarchies; deep learning excels in learning multi-level feature spaces, but they often lack explicit coding of part-whole relations, a prominent property of medical…

Fundamental models, trained on large-scale datasets and adapted to new data using innovative learning methods, have revolutionized various fields. In materials science, microstructure image segmentation plays a pivotal role in understanding…

Medical image segmentation is crucial for computer-aided diagnosis, yet privacy constraints hinder data sharing across institutions. Federated learning addresses this limitation, but existing approaches often rely on lightweight…

This study investigates the application and performance of the Segment Anything Model 2 (SAM2) in the challenging task of video camouflaged object segmentation (VCOS). VCOS involves detecting objects that blend seamlessly in the…

The Segment Anything Model (SAM) represents a state-of-the-art research advancement in natural image segmentation, achieving impressive results with input prompts such as points and bounding boxes. However, our evaluation and recent…

The significant morphological and distributional variability among subcellular components poses a long-standing challenge for learning-based organelle segmentation models, significantly increasing the risk of biased feature learning.…

Large-scale delineation of individual trees from remote sensing imagery is crucial to the advancement of ecological research, particularly as climate change and other environmental factors rapidly transform forest landscapes across the…

Recently, many foundation models for medical image analysis such as MedSAM, SwinUNETR have been released and proven to be useful in multiple tasks. However, considering the inherent heterogeneity and inhomogeneity of real-world medical…

The Segment Anything Model (SAM) serves as a fundamental model for semantic segmentation and demonstrates remarkable generalization capabilities across a wide range of downstream scenarios. In this empirical study, we examine SAM's…

Foundation models for image segmentation have shown strong generalization in natural images, yet their applicability to 3D medical imaging remains limited. In this work, we study the zero-shot use of Segment Anything Model 2 (SAM2) for…

Recent advancements in foundation models have transformed computer vision, driving significant performance improvements across diverse domains, including digital histopathology. However, the advantages of domain-specific histopathology…

The Segment Anything Model (SAM) family has become a widely adopted vision foundation model, but its ability to control segmentation granularity remains limited. Users often need to refine results manually - by adding more prompts or…

General vision encoders like DINOv2 and SAM have recently transformed computer vision. Even though they are trained on natural images, such encoder models have excelled in medical imaging, e.g., in classification, segmentation, and…

Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs…

Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything…

Models trained in federated settings often suffer from degraded performances and fail at generalizing, especially when facing heterogeneous scenarios. In this work, we investigate such behavior through the lens of geometry of the loss and…

Recent "segment anything" efforts show promise by learning from large-scale data, but adapting such models directly to medical images remains challenging due to the complexity of medical data, noisy annotations, and continual learning…