paper-with-me

홈 › Papers

Context Driven Scene Parsing with Attention to Rare Classes

2014-06-01 · CVPR 2014 6 · Jimei Yang, Brian Price, Scott Cohen, Ming-Hsuan Yang

This paper presents a scalable scene parsing algorithm based on image retrieval and superpixel matching. We focus on rare object classes, which play an important role in achieving richer semantic understanding of visual scenes, compared to common background classes. Towards this end, we make two novel contributions: rare class expansion and semantic context description. First, considering the long-tailed nature of the label distribution, we expand the retrieval set by rare class exemplars and thus achieve more balanced superpixel classification results. Second, we incorporate both global and local semantic context information through a feedback based mechanism to refine image retrieval and superpixel matching. Results on the SIFTflow and LMSun datasets show the superior performance of our algorithm, especially on the rare classes, without sacrificing overall labeling accuracy.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationImage RetrievalRetrievalScene Parsing

Similar Papers 제목 키워드 기반

Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score

2020-09-28 · He Huang, Shunta Saito, Yuta Kikuchi, Eiichi Matsumoto 외

Scene graph parsing aims to detect objects in an image scene and recognize their relations. Recent approaches have achieved high average scores on some popular benchmarks, but fail in detecting rare relations, as the hig…

Feature boosting with efficient attention for scene parsing

2024-02-29 · Vivek Singh, Shailza Sharma, Fabio Cuzzolin

The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeedi…

Scene Parsing

GEBNet: Graph-Enhancement Branch Network for RGB-T Scene Parsing

2022-10-31 · journal 2022 10 · Shaohua Dong, WuJie Zhou, Xiaohong Qian, Lu Yu

RGB-T (red–green–blue and thermal) scene parsing has recently drawn considerable research attention. Although existing methods efficiently conduct RGB-T scene parsing, their performance remains limited by a small recepti…

DecoderScene ParsingThermal Image Segmentation

Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired

2021-03-06 · Yingzhi Zhang, Haoye Chen, Kailun Yang, Jiaming Zhang 외

As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks…

Real-Time Semantic SegmentationScene ParsingScene RecognitionSemantic Segmentation

ORDNet: Capturing Omni-Range Dependencies for Scene Parsing

2021-01-11 · Shaofei Huang, Si Liu, Tianrui Hui, Jizhong Han 외

Learning to capture dependencies between spatial positions is essential to many visual tasks, especially the dense labeling problems like scene parsing. Existing methods can effectively capture long-range dependencies wi…

Scene Parsing