Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

All-higher-stages-in adaptive context aggregation for semantic edge detection

Bo, Qihan, Ma, Wei, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680 and Zha, Hongbin 2022. All-higher-stages-in adaptive context aggregation for semantic edge detection. IEEE Transactions on Circuits and Systems for Video Technology 32 (10) , pp. 6778-6791. 10.1109/TCSVT.2022.3170048

[thumbnail of AdaptiveSemanticEdgeDetection_TCSVT2022.pdf]
Preview
PDF - Accepted Post-Print Version
Download (5MB) | Preview

Abstract

Convolutional Neural Networks (CNNs) can reveal local variation details and multi-scale spatial context in images via low-to-high stages of feature expression; effective fusion of these raw features is key to Semantic Edge Detection (SED). The methods available in the field generally fuse features across stages in a position-aligned mode, which cannot satisfy the requirements of diverse semantic context in categorizing different pixels. In this paper, we propose a deep framework for SED, the core of which is a new multi-stage feature fusion structure, called All-HiS-In ACA (All-Higher-Stages-In Adaptive Context Aggregation). All-HiS-In ACA can adaptively select semantic context from all higher-stages for detailed features via a cross-stage self-attention paradigm, and thus can obtain fused features with high-resolution details for edge localization and rich semantics for edge categorization. In addition, we develop a non-parametric Inter-layer Complementary Enhancement (ICE) module to supplement clues at each stage with their counterparts in adjacent stages. The ICE-enhanced multi-stage features are then fed into the All-HiS-In ACA module. We also construct an Object-level Semantic Integration (OSI) module to further refine the fused features by enforcing the consistency of the features within the same object. Extensive experiments demonstrate the superior performance of the proposed method over state-of-the-art works.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers
ISSN: 1051-8215
Date of First Compliant Deposit: 1 May 2022
Date of Acceptance: 18 April 2022
Last Modified: 06 Nov 2023 19:22
URI: https://orca.cardiff.ac.uk/id/eprint/149470

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics