Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 7096-7104
DOI: 10.1609/aaai.v38i7.28537 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Hongquan Zhang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).
Abstract (Originalsprache)
Class-incremental object detection (CIOD) is a real-world desired capability, requiring an object detector to continuously adapt to new tasks without forgetting learned ones, with the main challenge being catastrophic forgetting. Many methods based on distillation and replay have been proposed to alleviate this problem. However, they typically learn on a pure visual backbone, neglecting the powerful representation capabilities of textual cues, which to some extent limits their performance. In this paper, we propose task-aware language-image representation to mitigate catastrophic forgetting, introducing a new paradigm for language-image-based CIOD. First of all, we demonstrate the significant advantage of language-image detectors in mitigating catastrophic forgetting. Secondly, we propose a learning task-aware language-image representation method that overcomes the existing drawback of directly utilizing the language-image detector for CIOD. More specifically, we learn the language-image representation of different tasks through an insulating approach in the training stage, while using the alignment scores produced by task-specific language-image representation in the inference stage. Through our proposed method, language-image detectors can be more practical for CIOD. We conduct extensive experiments on COCO 2017 and Pascal VOC 2007 and demonstrate that the proposed method achieves state-of-the-art results under the various CIOD settings.
Zitieren
APA
Zhang, H., Gao, B., Zeng, Y., Tian, X., Tan, X., Zhang, Z., Qu, Y., Liu, J., & Xie, Y. (2024). Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7096-7104. https://doi.org/10.1609/aaai.v38i7.28537
Vancouver
Zhang H, Gao B, Zeng Y, Tian X, Tan X, Zhang Z, et al. Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):7096-7104. doi:10.1609/aaai.v38i7.28537
BibTeX
@article{Zhang2024,
author = {Zhang, Hongquan and Gao, Bin-Bin and Zeng, Yi and Tian, Xudong and Tan, Xin and Zhang, Zhizhong and Qu, Yanyun and Liu, Jun and Xie, Yuan},
title = {Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {7},
pages = {7096--7104},
doi = {10.1609/aaai.v38i7.28537}
}
EUVIMED