相关论文: Continual Learning for Segment Anything Model Adap…

Object extraction and segmentation from remote sensing (RS) images is a critical yet challenging task in urban environment monitoring. Urban morphology is inherently complex, with irregular objects of diverse shapes and varying scales.…

Inspired by Segment Anything 2, which generalizes segmentation from images to videos, we propose SAM2MOT--a novel segmentation-driven paradigm for multi-object tracking that breaks away from the conventional detection-association framework.…

Recently segment anything model (SAM) has attracted widespread concerns, and it is often treated as a vision foundation model for universal segmentation. Some researchers have attempted to directly apply the foundation model to the RGB-D…

Domain adaptive segmentation (DAS) of numerous organelle instances from large-scale electron microscopy (EM) is a promising way to enable annotation-efficient learning. Inspired by SAM, we propose a promptable multitask framework, namely…

Training a modern machine learning architecture on a new task requires extensive learning-rate tuning, which comes at a high computational cost. Here we develop new Polyak-type adaptive learning rates that can be used on top of any momentum…

Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains. In this…

The Segment Anything Model (SAM) has garnered significant attention for its versatile segmentation abilities and intuitive prompt-based interface. However, its application in medical imaging presents challenges, requiring either substantial…

In always-on HAR deployments, model accuracy erodes silently as domain shift accumulates over time. Addressing this challenge requires moving beyond one-off updates toward instance-driven adaptation from streaming data. However, continuous…

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain…

Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks. Recently, approaches leveraging pre-trained models have gained…

Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic Unsupervised domain…

End-to-end medical image segmentation is of great value for computer-aided diagnosis dominated by task-specific models, usually suffering from poor generalization. With recent breakthroughs brought by the segment anything model (SAM) for…

SAM is a segmentation model recently released by Meta AI Research and has been gaining attention quickly due to its impressive performance in generic object segmentation. However, its ability to generalize to specific scenes such as…

The Segment Anything Model (SAM) has gained significant attention for its impressive performance in image segmentation. However, it lacks proficiency in referring video object segmentation (RVOS) due to the need for precise user-interactive…

The recent Segment Anything Model 2 (SAM2) has demonstrated exceptional capabilities in interactive object segmentation for both images and videos. However, as a foundational model on interactive segmentation, SAM2 performs segmentation…

The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being trained with 1.1 billion masks, SAM's mask prediction…

Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation,…

Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability. Interestingly, prior continual learning strategies in online settings inadvertently anchor their updated parameters to a local parameter…

Recent segmentation methods, which adopt large-scale data training and transformer architecture, aim to create one foundation model that can perform multiple tasks. However, most of these methods rely on heavy encoder and decoder…