Pair DETR: Contrastive Learning Speeds Up DETR Training
원문 초록
The DETR object detection approach applies the transformer encoder and decoder architecture to detect objects and achieves promising performance. In this paper, we present a simple approach to address the main problem of DETR, the slow convergence, by using representation learning technique. In this approach, we detect an object bounding box as a pair of keypoints, the top-left corner and the center, using two decoders. By detecting objects as paired keypoints, the model builds up a joint classification and pair association on the output queries from two decoders. For the pair association we propose utilizing contrastive self-supervised learning algorithm without requiring specialized architecture. Experimental results on MS COCO dataset show that Pair DETR can converge at least 10x faster than original DETR and 1.5x faster than Conditional DETR during training, while having consistently higher Average Precision scores.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation
Self-Supervised Learning for Multimedia Recommendation
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
Weakly-supervised Contrastive Learning with Quantity Prompts for Moving Infrared Small Target Detection
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.