arXiv Computer Vision
CGSM: Concept-Guided Segmentation Model for Precise Pulmonary Lesion Delineation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Aug 12
MedUP: Awakening Unified Understanding and Perception in Medical Vision-Language Models
arXiv:2608. 10635v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-VLMs) excel at verbalizing visual content, yet precise visual perception, segmentation, and grounding remain challenging.
arXiv Computer Vision
Sep 22
QwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation
arXiv:2609.23139v1 Announce Type: new Abstract: Most medical vision-language models (VLMs) excel at open-ended report generation and VQA but provide limited support for structured, fine-grained clini...
arXiv AI
Aug 13
Dual-Domain Cross-Modal Decoding for Clinical Text-Guided Medical Image Segmentation
arXiv:2608. 11335v1 Announce Type: cross Abstract: Clinical text can narrow down what to segment, but recent text-guided designs emphasize spatial alignment while overlooking frequency content that governs texture and boundaries.
arXiv Machine Learning
6d ago
Multimodal Routing and Region Refinement for Language-Guided Medical Image Segmentation
Multimodal Routing and Region Refinement for Language-Guided Medical Image Segmentation (MRSeg) is a parameter‑efficient framework that uses frozen ConvNeXt‑Tiny and PubMedBERT encoders to extract multiscale visual features and clinical text tokens. A joint router predicts a sparse mixture over low‑rank adapter bases, enabling separate adaptation for two visual scales and text while keeping feature‑specific parameters distinct. Region Bridge aggregates dense visual tokens into latent regions using text‑derived queries, refines them via self‑attention and text cross‑attention, and redistributes the refined information back to the feature maps, culminating in a multiscale decoder that combines refined semantic features with shallow image evidence. MRSeg achieves state‑of‑the‑art Dice/mIoU scores on QaTa‑COV19 and MosMedData+ with only 7.11 M trainable parameters and 7.60 GFLOPs.
arXiv AI
Aug 6
EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment
arXiv:2608. 04472v1 Announce Type: cross Abstract: The development of foundation models (FMs) is crucial for advancing endoscopic image analysis.
Hugging Face Trending Papers
Sep 24
Multimodal Routing and Region Refinement for Language-Guided Medical Image Segmentation
Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided methods mainly improve where image and language fe...