paper-with-me

Papers

Linguistic Query-Guided Mask Generation for Referring Image Segmentation

2023-01-16 · Zhichao Wei, Xiaohao Chen, Mingqiang Chen, Siyu Zhu

Referring image segmentation aims to segment the image region of interest according to the given language expression, which is a typical multi-modal task. Existing methods either adopt the pixel classification-based or the learnable query-based framework for mask generation, both of which are insufficient to deal with various text-image pairs with a fix number of parametric prototypes. In this work, we propose an end-to-end framework built on transformer to perform Linguistic query-Guided mask generation, dubbed LGFormer. It views the linguistic features as query to generate a specialized prototype for arbitrary input image-text pair, thus generating more consistent segmentation results. Moreover, we design several cross-modal interaction modules (\eg, vision-language bidirectional attention module, VLBA) in both encoder and decoder to achieve better cross-modal alignment.

📄 PDF Abstract BibTeX arXiv:2301.06429

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learningcross-modal alignmentDecoderImage SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

RISAM: Referring Image Segmentation via Mutual-Aware Attention Features

2023-11-27 · Mengxi Zhang, Yiming Liu, Xiangjun Yin, Huanjing Yue 외

Referring image segmentation (RIS) aims to segment a particular region based on a language expression prompt. Existing methods incorporate linguistic features into visual features and obtain multi-modal features for mask…

DecoderImage SegmentationSegmentationSemantic Segmentation

LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation

2024-01-01 · CVPR 2024 1 · Nisarg A. Shah, Vibashan VS, Vishal M. Patel

Referring Image Segmentation (RIS) aims to segment objects from an image based on a language description. Recent advancements have introduced transformer-based methods that leverage cross-modal dependencies significa…

Image SegmentationSemantic SegmentationVisual Grounding

Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation

2024-10-17 · Changcheng Xiao, Qiong Cao, Yujie Zhong, Xiang Zhang 외

Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to locate an arbitrary number of target objects and maintain their identities referred by a language expression in a video. This intricate …

Multi-Object TrackingMulti-Object Tracking and SegmentationObject TrackingReferring Multi-Object Tracking+3

RefMask3D: Language-Guided Transformer for 3D Referring Segmentation

2024-07-25 · Shuting He, Henghui Ding

3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The key challenge behind this task is visio…

3D visual groundingImage SegmentationSegmentationSemantic Segmentation+1

Contrastive Grouping with Transformer for Referring Image Segmentation

2023-09-02 · CVPR 2023 1 · Jiajin Tang, Ge Zheng, Cheng Shi, Sibei Yang

Referring image segmentation aims to segment the target referent in an image conditioning on a natural language expression. Existing one-stage methods employ per-pixel classification frameworks, which attempt straightfor…

Contrastive LearningImage SegmentationObjectSegmentation+1