Image Segmentation

New method for moving object segmentation by combining long-range motion cues, semantic features, and SAM2, achieving state-of-the-art performance in challenging scenarios.

FDConv: Adaptable convolution via frequency domain learning, enhancing performance without heavy parameter cost.

SALT: Fine-tuning SAM for medical images using Singular Value Adaptation with Low-Rank Transformation for efficient, robust segmentation.

Seg-Zero: Cognitive Reinforcement for Reasoning-Chain Guided Segmentation!

DICEPTION: A generalist diffusion model for visual perceptual tasks.

JL1-CD: New all-inclusive dataset & multi-teacher knowledge distillation framework for robust remote sensing change detection, achieving state-of-the-art results!

CAPI: a novel masked image modeling framework boosts self-supervised visual representation learning by predicting latent clusterings, achieving state-of-the-art ImageNet accuracy and mIoU.

3CAD: A new large-scale, real-world dataset with diverse 3C product anomalies boosts unsupervised anomaly detection, enabling superior algorithm development via a novel Coarse-to-Fine framework.

ViLU-Net, a novel U-Net modification using Vision-xLSTM, achieves superior retroperitoneal tumor segmentation accuracy and efficiency, exceeding existing state-of-the-art methods.

MRGen, a novel diffusion-based data engine, controllably synthesizes MRI data for unannotated modalities, boosting segmentation model performance.

EfficientTAMs achieve comparable video object segmentation accuracy to SAM 2 with ~2x speedup using lightweight ViTs and efficient cross-attention.

MedNeXt, a novel model ensemble, optimizes brain tumor segmentation in diverse populations, achieving state-of-the-art results on the BraTS 2024 SSA and pediatric datasets.

SegBook: a large-scale benchmark, reveals that fine-tuning full-body CT pre-trained models significantly improves performance on various downstream medical image segmentation tasks, particularly for s…

ITACLIP boosts training-free semantic segmentation by architecturally enhancing CLIP, integrating LLM-generated class descriptions, and employing image engineering; achieving state-of-the-art results.