paper-with-me

홈 › Papers

OTA: Optimal Transport Assignment for Object Detection

2021-03-26 · CVPR 2021 1 · Zheng Ge, Songtao Liu, Zeming Li, Osamu Yoshie, Jian Sun

Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object. In this paper, we innovatively revisit the label assignment from a global perspective and propose to formulate the assigning procedure as an Optimal Transport (OT) problem -- a well-studied topic in Optimization Theory. Concretely, we define the unit transportation cost between each demander (anchor) and supplier (gt) pair as the weighted summation of their classification and regression losses. After formulation, finding the best assignment solution is converted to solve the optimal transport plan at minimal transportation costs, which can be solved via Sinkhorn-Knopp Iteration. On COCO, a single FCOS-ResNet-50 detector equipped with Optimal Transport Assignment (OTA) can reach 40.7% mAP under 1X scheduler, outperforming all other existing assigning methods. Extensive experiments conducted on COCO and CrowdHuman further validate the effectiveness of our proposed OTA, especially its superiority in crowd scenarios. The code is available at https://github.com/Megvii-BaseDetection/OTA.

📄 PDF Abstract BibTeX arXiv:2103.14259

Code (2)

Megvii-BaseDetection/OTA 공식 구현 pytorch
CV51GO/OTA_Megengine pytorch

Tasks

Objectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Detecting Open World Objects via Partial Attribute Assignment

2025-01-01 · CVPR 2025 1 · Muli Yang, Gabriel James Goenawan, Huaiyuan Qin, Kai Han 외

Despite being trained on massive data, today's vision foundation models still fall short in detecting open world objects. Apart from recognizing known objects from training, a successful Open World Object Detection (…

Attributeobject-detectionObject DetectionOpen World Object Detection

MT-Net Submission to the Waymo 3D Detection Leaderboard

2022-07-11 · Shaoxiang Chen, Zequn Jie, Xiaolin Wei, Lin Ma

In this technical report, we introduce our submission to the Waymo 3D Detection leaderboard. Our network is based on the Centerpoint architecture, but with significant improvements. We design a 2D backbone to utilize mul…

3D Object Detection

SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene Generation

2026-02-26 · Ling Wang, Hao-Xiang Guo, Xinzhou Wang, Fuchun Sun 외 arxiv

We introduce SceneTransporter, an end-to-end framework for structured 3D scene generation from a single image. While existing methods generate part-level 3D objects, they often fail to organize these parts into distinct …

Scene Generation

Learning Partial Graph Matching via Optimal Partial Transport

2024-10-22 · Gathika Ratnayaka, James Nichols, Qing Wang

Partial graph matching extends traditional graph matching by allowing some nodes to remain unmatched, enabling applications in more complex scenarios. However, this flexibility introduces additional complexity, as both t…

Graph Matching

HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection

2022-07-23 · Ji Liu, Dong Li, Zekun Li, Han Liu 외

Sample assignment plays a prominent part in modern object detection approaches. However, most existing methods rely on manual design to assign positive / negative samples, which do not explicitly establish the relationsh…

Objectobject-detectionObject Detection