Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

Hao Zhang · Feng Li · Shilong Liu · Lei Zhang · Hang Su · Jun Zhu · Lionel Ni · Heung-Yeung Shum

MH1-2-3-4 #24

Keywords: [ object detection ] [ Detection Transformer ] [ End-to-End Detector ] [ Deep Learning and representational learning ]


Abstract:

We present DINO (DETR with Improved deNoising anchOr boxes), a strong end-to-end object detector. DINO improves over previous DETR-like models in performance and efficiency by using a contrastive way for denoising training, a look forward twice scheme for box prediction, and a mixed query selection method for anchor initialization. DINO achieves 49.4AP in 12 epochs and 51.3AP in 24 epochs on COCO with a ResNet-50 backbone and multi-scale features, yielding a significant improvement of +6.0AP and +2.7AP, respectively, compared to DN-DETR, the previous best DETR-like model. DINO scales well in both model size and data size. Without bells and whistles, after pre-training on the Objects365 dataset with a SwinL backbone, DINO obtains the best results on both COCO val2017 (63.2AP) and test-dev (63.3AP) with model size under 1 billion parameters. Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results. The code will be available.

Chat is not available.