Unsupervised Landmark Discovery Using Consistency-Guided Bottleneck
Mamona Awan (MBZU), Muhammad Haris Khan (Mohamed Bin Zayed University of Artificial Intelligence),* Sanoojan Baliah (Mohamed Bin Zayed University of Artificial Intelligence), Muhammad Ahmad Waseem (Information Technology University), Salman Khan (MBZUAI), Fahad Shahbaz Khan (MBZUAI), Arif Mahmood (Information Technology University)
The 34th British Machine Vision Conference
Abstract
We study a challenging problem of unsupervised discovery of object landmarks. Many recent methods rely on bottlenecks to generate 2D Gaussian heatmaps however, these are limited in generating informed heatmaps while training, presumably due to the lack of effective structural cues. Also, it is assumed that all predicted landmarks are semantically relevant despite having no ground truth supervision. In the current work, we introduce a consistency-guided bottleneck in an image reconstruction-based pipeline that leverages landmark consistency, a measure of compatibility score with the pseudo-ground truth, to generate adaptive heatmaps. We propose obtaining pseudo-supervision via forming landmark correspondence across images. The consistency then modulates the uncertainty of the discovered landmarks in the generation of adaptive heatmaps which rank consistent landmarks above their noisy counterparts, providing effective structural information for improved robustness. Evaluations on five diverse datasets including MAFL, AFLW, LS3D, Cats, and Shoes demonstrate excellent performance of the proposed approach compared to the existing state-of-the-art methods. Our code is publicly available at https://github.com/MamonaAwan/CGB_ULD.Video
Citation
@inproceedings{Awan_2023_BMVC,
author = {Mamona Awan and Muhammad Haris Khan and Sanoojan Baliah and Muhammad Ahmad Waseem and Salman Khan and Fahad Shahbaz Khan and Arif Mahmood},
title = {Unsupervised Landmark Discovery Using Consistency-Guided Bottleneck},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0598.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by