Learning object-language alignments for open-vocabulary object detection

Chuang Lin, Peize Sun, Yi Jiang, Ping Luo, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan, Jianfei Cai

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an attractive alternative for its annotation-free attributes and broader object concepts. However, learning open-vocabulary object detection from language is challenging since image-text pairs do not contain fine-grained object-language alignments. Previous solutions rely on either expensive grounding annotations or distilling classification-oriented vision models. In this paper, we propose a novel open-vocabulary object detection framework directly learning from image-text pair data. We formulate object-language alignment as a set matching problem between a set of image region features and a set of word embeddings. It enables us to train an open-vocabulary object detector on image-text pairs in a much simple and effective way. Extensive experiments on two benchmark datasets, COCO and LVIS, demonstrate our superior performance over the competing approaches on novel categories, e.g. achieving 32.0% mAP on COCO and 21.7% mask mAP on LVIS. Code will be released.
Original languageEnglish
Title of host publicationThe Eleventh International Conference on Learning Representations
EditorsMaximilian Nickel, Mengdi Wang, Nancy F Chen, Vukosi Marivate
Place of PublicationPortland OR USA
PublisherOpenReview
Number of pages13
Publication statusPublished - 2023
EventInternational Conference on Learning Representations 2023 - Kigali, Rwanda
Duration: 1 May 20235 May 2023
Conference number: 11th
https://iclr.cc/Conferences/2023
https://openreview.net/group?id=ICLR.cc (Proceedings)

Conference

ConferenceInternational Conference on Learning Representations 2023
Abbreviated titleICLR 2023
Country/TerritoryRwanda
CityKigali
Period1/05/235/05/23
Internet address

Cite this