Related papers: StructSAM: Structure- and Spectrum-Preserving Toke…
Training segmentation models for medical images continues to be challenging due to the limited availability of data annotations. Segment Anything Model (SAM) is a foundation model that is intended to segment user-defined objects of interest…
Recently, Segment Anything Model (SAM) has become a research hotspot in the fields of multimedia and computer vision, which exhibits powerful yet versatile capabilities on various (un) conditional image segmentation tasks. Although SAM can…
Image-based crack detection algorithms are increasingly in demand in infrastructure monitoring, as early detection of cracks is of paramount importance for timely maintenance planning. While deep learning has significantly advanced crack…
Segment anything models (SAMs) are gaining attention for their zero-shot generalization capability in segmenting objects of unseen classes and in unseen domains when properly prompted. Interactivity is a key strength of SAMs, allowing users…
The ability to segment objects based on open-ended language prompts remains a critical challenge, requiring models to ground textual semantics into precise spatial masks while handling diverse and unseen categories. We present OpenWorldSAM,…
Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and large amount of visual tokens, such as the penultimate layer…
In medical image segmentation, heterogeneous privacy policies across institutions often make joint training on pooled datasets infeasible, motivating continual image segmentation-learning from data streams without catastrophic forgetting.…
Large-scale foundation models have become the mainstream deep learning method, while in civil engineering, the scale of AI models is strictly limited. In this work, a vision foundation model is introduced for crack segmentation. Two…
Segment Anything Model (SAM) has demonstrated impressive zero-shot segmentation capabilities across natural image domains, but it struggles to generalize to the unique challenges of remote sensing data, such as complex terrain, multi-scale…
In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the most informative tokens, which is…
The Segment Anything Model (SAM) excels at general image segmentation but has limited ability to understand natural language, which restricts its direct application in Referring Expression Segmentation (RES). Toward this end, we propose…
Segmentation is an essential step for remote sensing image processing. This study aims to advance the application of the Segment Anything Model (SAM), an innovative image segmentation model by Meta AI, in the field of remote sensing image…
The Segment Anything Model (SAM), a foundation model pretrained on millions of images and segmentation masks, has significantly advanced semantic segmentation, a fundamental task in computer vision. Despite its strengths, SAM encounters two…
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…
In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model. In essence, VRP-SAM can…
The Segment Anything Model (SAM) is a promptable segmentation model recently introduced by Meta AI that has demonstrated its prowess across various fields beyond just image segmentation. SAM can accurately segment images across diverse…
Few-shot segmentation (FSS) aims to segment new classes using few annotated images. While recent FSS methods have shown considerable improvements by leveraging Segment Anything Model (SAM), they face two critical limitations: insufficient…
Accurate segmentation of organs and lesions in medical images is essential for clinical applications including diagnosis, prognosis, and treatment planning. While Vision Transformers (ViTs) have shown impressive segmentation performance,…
We propose a novel spectral vision transformer architecture for efficient tokenization in limited data, with an emphasis on medical imaging. We outline convenient theoretical properties arising from the choice of basis including spatial…
Tooth point cloud segmentation is a fundamental task in many orthodontic applications. Current research mainly focuses on fully supervised learning which demands expensive and tedious manual point-wise annotation. Although recent…