paper-with-me

홈 › Papers

Scene Labeling Using Beam Search Under Mutex Constraints

2014-06-01 · CVPR 2014 6 · Anirban Roy, Sinisa Todorovic

This paper addresses the problem of assigning object class labels to image pixels. Following recent holistic formulations, we cast scene labeling as inference of a conditional random field (CRF) grounded onto superpixels. The CRF inference is specified as quadratic program (QP) with mutual exclusion (mutex) constraints on class label assignments. The QP is solved using a beam search (BS), which is well-suited for scene labeling, because it explicitly accounts for spatial extents of objects; conforms to inconsistency constraints from domain knowledge; and has low computational costs. BS gradually builds a search tree whose nodes correspond to candidate scene labelings. Successor nodes are repeatedly generated from a select set of their parent nodes until convergence. We prove that our BS efficiently maximizes the QP objective of CRF inference. Effectiveness of our BS for scene labeling is evaluated on the benchmark MSRC, Stanford Backgroud, PASCAL VOC 2009 and 2010 datasets.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Scene LabelingSuperpixels

Similar Papers 제목 키워드 기반

Semantic Segmentation of RGBD Images With Mutex Constraints

2015-12-01 · ICCV 2015 12 · Zhuo Deng, Sinisa Todorovic, Longin Jan Latecki

In this paper, we address the problem of semantic scene segmentation of RGB-D images of indoor scenes. We propose a novel image region labeling method which augments CRF formulation with hard mutual exclusion (mutex) con…

Common Sense ReasoningScene LabelingScene SegmentationSemantic Segmentation

Joint Semantic Instance Segmentation on Graphs with the Semantic Mutex Watershed

2020-08-01 · ECCV 2020 8 · Steffen Wolf, Yuyan Li, Constantin Pape, Alberto Bailoni 외

Semantic instance segmentation is the task of simultaneously partitioning an image into distinct segments while associating each pixel with a class label. In commonly used pipelines, segmentation and label assignment are…

graph partitioningInstance SegmentationSegmentationSemantic Segmentation+1

The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance Segmentation

2019-12-29 · Steffen Wolf, Yuyan Li, Constantin Pape, Alberto Bailoni 외

Semantic instance segmentation is the task of simultaneously partitioning an image into distinct segments while associating each pixel with a class label. In commonly used pipelines, segmentation and label assignment are…

graph partitioningInstance SegmentationSegmentationSemantic Segmentation+1

MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization

2022-03-27 · Yue Duan, Zhen Zhao, Lei Qi, Lei Wang 외

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom ful…

Semi-Supervised Image Classification

MUTEX: Leveraging Multilingual Transformers and Conditional Random Fields for Enhanced Urdu Toxic Span Detection

2026-03-05 · Inayat Arshad, Fajar Saleem, Ijaz Hussain arxiv

Urdu toxic span detection remains limited because most existing systems rely on sentence-level classification and fail to identify the specific toxic spans within those text. It is further exacerbated by the multiple fac…