MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation
원문 초록
Pretrained vision-language models (VLMs), \eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation. As VLMs are generally pretrained with low-resolution images (e.g. $224\times224$), most previous methods operate only on downscaled images. We question this design as low resolution features often fail to preserve fine details. A typical solution is to employ additional image backbones for high-resolution inputs, but it also introduce significant computation overhead. Therefore, we propose MROVSeg, a multi-resolution training framework for open-vocabulary image segmentation with a single pretrained CLIP backbone, that uses sliding windows to slice the high-resolution input into uniform patches, each matching the input size of the well-trained image encoder. Its key components include a Multi-Res Adapter, which restores the spatial geometry and grasps local-global correspondences across patches by interacting with multi-resolution features. To achieve accurate segmentation, we introduce Multi-grained Masked Attention scheme to aggregate multi-grained semantics from multi-resolution CLIP features to object queries. Through comprehensive experiments, we demonstrate the superiority of MROVSeg on well-established open-vocabulary image segmentation benchmarks, establishing new standards for open-vocabulary image segmentation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
A New Dataset and Performance Benchmark for Real-time Spacecraft Segmentation in Onboard Flight Computers
RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models
No time to train! Training-Free Reference-Based Instance Segmentation
Autoadaptive Medical Segment Anything Model
Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
토론
이 논문과 연결된 포럼 글이 아직 없습니다.