Timezone: »

 
Poster
Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
Hanoona Bangalath · Muhammad Maaz · Muhammad Uzair Khattak · Salman Khan · Fahad Shahbaz Khan

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #137
in Poster Session 3 »

Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and image-level supervision. We note that both these modes of supervision are not optimally aligned for the detection task: CLIP is trained with image-text pairs and lacks precise localization of objects while the image-level supervision has been used with heuristics that do not accurately specify local object regions. In this work, we propose to address this problem by performing object-centric alignment of the language embeddings from the CLIP model. Furthermore, we visually ground the objects with only image-level supervision using a pseudo-labeling process that provides high-quality object proposals and helps expand the vocabulary during training. We establish a bridge between the above two object-alignment strategies via a novel weight transfer function that aggregates their complimentary strengths. In essence, the proposed model seeks to minimize the gap between object and image-centric representations in the OVD setting. On the COCO benchmark, our proposed approach achieves 36.6 AP50 on novel classes, an absolute 8.2 gain over the previous best performance. For LVIS, we surpass the state-of-the-art ViLD model by 5.0 mask AP for rare categories and 3.4 overall. Code: https://github.com/hanoonaR/object-centric-ovd.

Keywords: Object Detection · Vision-Language Pretraining · open vocabulary
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Hanoona Bangalath (Mohamed Bin Zayed University of Artificial Intelligence)
Muhammad Maaz (Mohamed Bin Zayed University of Artificial Intelligence)
Muhammad Maaz

Computer Vision research student with hands-on experience in design, engineering, deployment and monitoring phases of Deep Learning driven Computer Vision products. Currently working on Multi-modal understanding from vision and text to improve common-sense reasoning of machines and its applications in long-tail open vocabulary object detection.

Muhammad Uzair Khattak (Mohamed bin Zayed University of Artificial Intelligence)
Salman Khan (MBZ University of AI)
Fahad Shahbaz Khan (Inception Institute of Artificial Intelligence)

More from the Same Authors