Rank-DETR for High Quality Object Detection

Authors: Yifan Pu, Weicong Liang, Yiduo Hao, YUHUI YUAN, Yukang Yang, Chao Zhang, Han Hu, Gao Huang

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct comprehensive experiments, showcasing consistent performance improvements across recent strong DETR-based methods such as H-DETR and DINO-DETR.
Researcher Affiliation Collaboration 1Tsinghua University 2Peking University 3University of Cambridge 4Microsoft Research Asia
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks. It describes the methods using text and mathematical formulations.
Open Source Code Yes Code is available at https://github.com/Leap Lab THU/Rank-DETR.
Open Datasets Yes We perform object detection experiments using the COCO object detection benchmark [42]
Dataset Splits Yes Our model is trained on the train set and evaluated on the val set.
Hardware Specification Yes These assessments were conducted on RTX 3090 GPUs
Software Dependencies No The paper mentions using the "detrex [54] toolbox" but does not specify its version number or any other software dependencies with version details.
Experiment Setup Yes We adhere to the same experimental setup as the original papers for H-DETR [30] and DINO-DETR [75].