paper-with-me

홈 › Papers

SCALoss: Side and Corner Aligned Loss for Bounding Box Regression

2021-04-01 · Tu Zheng, Shuai Zhao, Yang Liu, Zili Liu, Deng Cai

Bounding box regression is an important component in object detection. Recent work achieves promising performance by optimizing the Intersection over Union~(IoU). However, IoU-based loss has the gradient vanish problem in the case of low overlapping bounding boxes, and the model could easily ignore these simple cases. In this paper, we propose Side Overlap~(SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases. Besides, to speed up the convergence, the Corner Distance~(CD) is added into the objective function. Combining the Side Overlap and Corner Distance, we get a new regression objective function, \textit{Side and Corner Align Loss~(SCALoss)}. The SCALoss is well-correlated with IoU loss, which also benefits the evaluation metric but produces more penalty for low-overlapping cases. It can serve as a comprehensive similarity measure, leading to better localization performance and faster convergence speed. Experiments on COCO, PASCAL VOC, and LVIS benchmarks show that SCALoss can bring consistent improvement and outperform $\ell_n$ loss and IoU based loss with popular object detectors such as YOLOV3, SSD, Faster-RCNN. Code is available at: \url{https://github.com/Turoad/SCALoss}.

📄 PDF Abstract BibTeX arXiv:2104.00462

Code (1)

turoad/scaloss 공식 구현 pytorch

Tasks

object-detectionObject Detectionregression

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Non Maximum Suppression Non Maximum Suppression is a computer vision method that selects a single entity out of many overlapping entities (for example bounding boxes in object detection). The…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
SSD SSD is a single-stage object detection method that discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per…

Similar Papers 제목 키워드 기반

Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds

2025-11-18 · Qinghao Meng, Junbo Yin, Jianbing Shen, Yunde Jia arxiv

Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability: object centers often fall in sparse or empty regions of the bird's-eye-view (BEV) due to the fro…

3D Object DetectionPoint Clouds

MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane

2026-03-20 · Changwoo Jeon, Rishi Upadhyay, Achuta Kadambi arxiv

Monocular 3D object understanding has largely been cast as a 2D RoI-to-3D box lifting problem. However, emerging downstream applications require image-plane geometry (e.g., projected 3D box corners) which cannot be easil…

Object Detection

Towards Better Performance and More Explainable Uncertainty for 3D Object Detection of Autonomous Vehicles

2020-06-22 · Hujie Pan, Zining Wang, Wei Zhan, Masayoshi Tomizuka

In this paper, we propose a novel form of the loss function to increase the performance of LiDAR-based 3d object detection and obtain more explainable and convincing uncertainty for the prediction. The loss function was …

3D Object DetectionAutonomous Vehiclesobject-detectionObject Detection+1

CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection

2020-03-20 · CVPR 2020 6 · Zhiwei Dong, Guoxuan Li, Yue Liao, Fei Wang 외

Keypoint-based detectors have achieved pretty-well performance. However, incorrect keypoint matching is still widespread and greatly affects the performance of the detector. In this paper, we propose CentripetalNet which…

Instance Segmentationobject-detectionObject DetectionPosition+2

Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurate Object Detection

2023-10-09 · ICCV 2023 1 · Yilong Lv, Min Li, Yujie He, Shaopeng Li 외

Anchor-based detectors have been continuously developed for object detection. However, the individual anchor box makes it difficult to predict the boundary's offset accurately. Instead of taking each bounding box as a cl…

object-detectionObject Detection