Paper Info
Title
Towards Partial Supervision for Generic Object Counting in Natural Scenes
Abstract
Generic object counting in natural scenes is a challenging computer vision problem. Existing approaches either rely on instance-level supervision or absolute count information to train a generic object counter. We introduce a partially supervised setting that significantly reduces the supervision level required for generic object counting. We propose two novel frameworks, named lower-count (LC) and reduced lower-count (RLC), to enable object counting under this setting. Our frameworks are built on a novel dual-branch architecture that has an image classification and a density branch. Our LC framework reduces the annotation cost due to multiple instances in an image by using only lower-count supervision for all object categories. Our RLC framework further reduces the annotation cost arising from large numbers of object categories in a dataset by only using lower-count supervision for a subset of categories and class-labels for the remaining ones. The RLC framework extends our dual-branch LC framework with a novel weight modulation layer and a category-independent density map prediction. Experiments are performed on COCO, Visual Genome and PASCAL 2007 datasets. Our frameworks perform on par with state-of-the-art approaches using higher levels of supervision. Additionally, we demonstrate the applicability of our LC supervised density map for image-level supervised instance segmentation.
Year
DOI
Venue
2022
10.1109/TPAMI.2020.3021025
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords
DocType
Volume
Generic object counting,reduced supervision,object localization,weakly supervised instance segmentation
Journal
44
Issue
ISSN
Citations 
3
0162-8828
0
PageRank 
References 
Authors
0.34
33
6
Name
Order
Citations
PageRank
Hisham Cholakkal1488.40
Guolei Sun2184.56
Salman Khan338741.05
Fahad Shahbaz Khan4162269.24
Ling Shao55424249.92
Luc Van Gool6275661819.51