ConSel: Concept-Aware Self-supervised Learning for Regression Beyond Ordinal Tasks

Tariq, Abdullah and Saleem, Bisma and Azad, R. Muhammad Atif and Masek, Martin and Gilani, Zulqarnain (2026) ConSel: Concept-Aware Self-supervised Learning for Regression Beyond Ordinal Tasks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026, 3rd-7th June 2026, Denver, Colorado, US.

Preview

Text 33094_ConSel_Concept_Aware_Sel_1_.pdf - Accepted Version Download (22MB)

Abstract

Regression is a fundamental problem in computer vision, underpinning tasks such as gaze estimation, head pose prediction, age assessment, aesthetic quality evaluation, crowd counting and historical image dating. We introduce ConSel
(Concept-Aware Self-Supervised Regression), a unified framework that learns to predict continuous values by progressing from coarse semantic concepts to fine-grained numeric precision. ConSel follows a two-stage curriculum: (1) concept-aware self-supervised pretraining, which aligns visual embeddings with conceptual guidance through variance–covariance regularization without access to ground-truth labels, and (2) fine-tuning for precise continuous prediction. Unlike prior approaches that are optimized only for 1D ordinal regression, ConSel generalizes to both ordinal and multi-dimensional continuous tasks. Evaluated on 15 benchmark datasets spanning 6 domains, ConSel surpasses both domain-specialized and ordinal methods by 15-35% while using only 25% of labeled data (4× less than prior methods)}.

Item Type:	Conference or Workshop Item (Paper)
Dates:	Date Event 12 March 2026 Accepted 1 June 2026 Published Online
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions:	Architecture, Built Environment, Computing and Engineering > Computer Science
Depositing User:	Gemma Tonks
Date Deposited:	02 Jun 2026 12:04
Last Modified:	02 Jun 2026 12:04
URI:	https://www.open-access.bcu.ac.uk/id/eprint/17068

Actions (login required)

View Item