paper-with-me

Papers

Multi-Grained Cross-modal Alignment for Learning Open-vocabulary Semantic Segmentation from Text Supervision

2024-03-06 · Yajie Liu, Pu Ge, Qingjie Liu, Di Huang

Recently, learning open-vocabulary semantic segmentation from text supervision has achieved promising downstream performance. Nevertheless, current approaches encounter an alignment granularity gap owing to the absence of dense annotations, wherein they learn coarse image/region-text alignment during training yet perform group/pixel-level predictions at inference. Such discrepancy leads to suboptimal learning efficiency and inferior zero-shot segmentation results. In this paper, we introduce a Multi-Grained Cross-modal Alignment (MGCA) framework, which explicitly learns pixel-level alignment along with object- and region-level alignment to bridge the granularity gap without any dense annotations. Specifically, MGCA ingeniously constructs pseudo multi-granular semantic correspondences upon image-text pairs and collaborates with hard sampling strategies to facilitate fine-grained cross-modal contrastive learning. Further, we point out the defects of existing group and pixel prediction units in downstream segmentation and develop an adaptive semantic unit which effectively mitigates their dilemmas including under- and over-segmentation. Training solely on CC3M, our method achieves significant advancements over state-of-the-art methods, demonstrating its effectiveness and efficiency.

📄 PDF Abstract BibTeX arXiv:2403.03707

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learningcross-modal alignmentOpen Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic SegmentationZero Shot Segmentation

Similar Papers 제목 키워드 기반

CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering

2025-11-03 · Qiangguo Jin, Xianyao Zheng, Hui Cui, Changming Sun 외 arxiv

Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent self-attention based methods struggle to effectively handle cross-modal semantic alignments b…

Visual Question AnsweringMulti-Task Learning

Multi-modal Attribute Prompting for Vision-Language Models

2024-03-01 · Xin Liu, Jiamin Wu, and Wenfei Yang, Xu Zhou 외

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image r…

Attributecross-modal alignment

Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation

2026-05-15 · Chenhao Wang, Yingrui Ji, Yu Meng, Yao Zhu arxiv

Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained descriptions are typically encoded as holistic sentences that entangle mul…

Learning Relative Representations for Fine-Grained Multimodal Alignment with Limited Data

2026-05-16 · Shiwon Kim, Yu Rang Park arxiv

Multimodal pre-training demonstrates strong generalization performance, but this paradigm is often impractical in domains where paired data are scarce. A promising alternative is post-hoc multimodal alignment, which alig…

Cross-Modal Retrieval

Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment

2024-01-01 · CVPR 2024 1 · Zheren Fu, Lei Zhang, Hou Xia, Zhendong Mao

Cross-modal alignment aims to build a bridge connecting vision and language. It is an important multi-modal task that efficiently learns the semantic similarities between images and texts. Traditional fine-grained al…

cross-modal alignmentCross-Modal RetrievalImage RetrievalImage-to-Text Retrieval+4