Anticipating Future Object Compositions without Forgetting
conference paper
Despite the significant advancements in computer vision models, their ability to generalize to novel object-attribute compositions remains limited. Existing methods for Compositional Zero-Shot Learning (CZSL) mainly focus on image classification. This paper aims to enhance CZSL in object detection without forgetting prior learned knowledge. We use Grounding DINO and incorporate Compositional Soft Prompting (CSP) into it and extend it with Compositional Anticipation. We achieve a 70.5% improvement over CSP on the harmonic mean (HM) between seen and unseen compositions on the CLEVR dataset. Furthermore, we introduce Contrastive Prompt Tuning to incrementally address model confusion between similar compositions. We demonstrate the effectiveness of this method and achieve an increase of 14.5% in HM across the pretrain, increment, and unseen sets. Collectively, these methods provide a framework for learning various compositions with limited data, as well as improving the performance of underperforming compositions when additional data becomes available. © 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
TNO Identifier
1008698
Publisher
Springer
Source title
Pattern Recognition: 27th International Conference, ICPR 2024 Kolkata, India, December 1–5, 2024
Proceedings, Part XXIX
Proceedings, Part XXIX
Editor(s)
Antonacopoulos, A.
Chaudhuri, S.
Chellappa, R.
Liu, C.L.
Bhattacharya, S.
Pal, U.
Chaudhuri, S.
Chellappa, R.
Liu, C.L.
Bhattacharya, S.
Pal, U.
Place of publication
Cham
Pages
291-306