Adapting CLIP for DETR-based Object Detection
Keywords: Object detection, contrastive learning, open-vocabulary object detection
Abstract: Object detection involves class identification and spatial positioning. While DETR-based architectures have shown promising detection capabilities by framing the task as set prediction, prior approaches have limited refinement for object features, leading to inferior inherent understanding of objects, particularly when generalizing to unseen categories. To this end, we propose CLIP-DETR, a novel detection framework that harnesses the pretrained visual-linguistic capabilities of CLIP to enhance both the encoding and decoding processes in DETR models. Our method focuses on two key principles: 1) feature map sensitivity to objects, and 2) query adaptability. Extensive experiments demonstrate that CLIP-DETR significantly outperforms state-of-the-art models in object detection and open-vocabulary detection tasks, illustrating its superior generalization and recognition abilities.
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 538
Loading