Image Segmentation

Unlocking personalized image retrieval and segmentation, a novel approach uses pre-trained text-to-image diffusion models to surpass supervised methods, addressing limitations of existing self-supervi…

Boosting 3D medical image segmentation, a novel U-shaped Connection (uC) integrates 2D U-Net skip connections into 3D CNNs, improving axial-slice plane feature extraction, surpassing state-of-the-art …

Modality Adaptation with Diffusion Models (MADM) achieves state-of-the-art semantic segmentation by using pre-trained text-to-image diffusion models to enhance cross-modality capabilities and generate…

This study introduces a novel unsupervised hierarchy-agnostic image segmentation method achieving detailed and unbiased parsing of semantic image structures across various datasets.

UnSeg: One universal unlearnable example generator protects images from image segmentation model training.

DiffewS: a novel framework leverages diffusion models for few-shot semantic segmentation, significantly outperforming existing methods in multiple settings.

New MVUAV dataset and SemiMV semi-supervised learning model significantly improve multispectral video semantic segmentation!

PartCLIPSeg, a novel framework, leverages generalized parts and object-level contexts to achieve significant improvements in open-vocabulary part segmentation, outperforming state-of-the-art methods.

UMI-GRAT: A universal meta-initialized and gradient robust adversarial attack effectively exploits vulnerabilities in the Segment Anything Model (SAM) and its fine-tuned downstream models, even withou…

PixelCLIP: Open-vocabulary semantic segmentation without pixel-level labels! Leveraging unlabeled image masks from Vision Foundation Models and an online clustering algorithm, PixelCLIP achieves imp…

Partial2Global: A novel VICL framework achieving globally optimal prompt selection, significantly improving visual in-context learning across various tasks.

FleVRS: One unified model masters standard, promptable, and open-vocabulary visual relationship segmentation, outperforming existing methods.

SGNet cultivates general segmentation models for ultra images by integrating surrounding context, achieving significant performance improvements across various datasets.

TARSS-Net: A novel temporal-aware radar semantic segmentation network uses a data-driven approach to aggregate temporal information, enhancing accuracy and performance.

SSA-Seg improves semantic segmentation by adapting pixel-level classifiers to the test image’s semantic and spatial features, achieving state-of-the-art performance with minimal extra computational co…

Soft Superpixel Neighborhood Attention (SNA) optimally denoises images by incorporating superpixel probabilities into an attention module, outperforming traditional methods.

SlimSAM achieves near original SAM performance using 0.1% of its training data by employing a novel alternate slimming framework and disturbed Taylor pruning, significantly advancing data-efficient mo…

SegVol: A universal, interactive 3D medical image segmentation model achieving state-of-the-art performance across diverse anatomical categories.

Unsupervised SAM (UnSAM) achieves competitive image segmentation results without human annotation, surpassing previous unsupervised methods and even improving supervised SAM’s accuracy.

AnyChange achieves zero-shot image change detection by adapting the Segment Anything Model (SAM) via a training-free bitemporal latent matching method, significantly outperforming previous state-of-th…