paper-with-me

홈 › Papers

Confidence Propagation Cluster: Unleash Full Potential of Object Detectors

2021-12-01 · CVPR 2022 1 · Yichun Shen, Wanli Jiang, Zhen Xu, Rundong Li, Junghyun Kwon, Siyi Li

It has been a long history that most object detection methods obtain objects by using the non-maximum suppression (NMS) and its improved versions like Soft-NMS to remove redundant bounding boxes. We challenge those NMS-based methods from three aspects: 1) The bounding box with highest confidence value may not be the true positive having the biggest overlap with the ground-truth box. 2) Not only suppression is required for redundant boxes, but also confidence enhancement is needed for those true positives. 3) Sorting candidate boxes by confidence values is not necessary so that full parallelism is achievable. In this paper, inspired by belief propagation (BP), we propose the Confidence Propagation Cluster (CP-Cluster) to replace NMS-based methods, which is fully parallelizable as well as better in accuracy. In CP-Cluster, we borrow the message passing mechanism from BP to penalize redundant boxes and enhance true positives simultaneously in an iterative way until convergence. We verified the effectiveness of CP-Cluster by applying it to various mainstream detectors such as FasterRCNN, SSD, FCOS, YOLOv3, YOLOv5, Centernet etc. Experiments on MS COCO show that our plug and play method, without retraining detectors, is able to steadily improve average mAP of all those state-of-the-art models with a clear margin from 0.3 to 1.9 respectively when compared with NMS-based methods.

📄 PDF Abstract BibTeX arXiv:2112.00342

Code (1)

shenyi0220/cp-cluster 공식 구현 pytorch

Tasks

Objectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

BNB Customer Service Number +1-833-534-1729 설명 없음
FPN 설명 없음
k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…
Average Pooling 설명 없음
Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…
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…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

3C: Confidence-Guided Clustering and Contrastive Learning for Unsupervised Person Re-Identification

2024-08-18 · Mingxiao Zheng, Yanpeng Qu, Changjing Shang, Longzhi Yang 외

Unsupervised person re-identification (Re-ID) aims to learn a feature network with cross-camera retrieval capability in unlabelled datasets. Although the pseudo-label based methods have achieved great progress in Re-ID, …

ClusteringContrastive LearningPerson Re-IdentificationPseudo Label+1

Extended Affinity Propagation: Global Discovery and Local Insights

2018-03-12 · Rayyan Ahmad Khan, Rana Ali Amjad, Martin Kleinsteuber

We propose a new clustering algorithm, Extended Affinity Propagation, based on pairwise similarities. Extended Affinity Propagation is developed by modifying Affinity Propagation such that the desirable features of Affin…

Clustering

BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation

2022-03-04 · CVPR 2022 1 · Wenqiao Zhang, Lei Zhu, James Hallinan, Andrew Makmur 외

In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1)…

Active Learning

Unleash the Potential of Adaptation Models via Dynamic Domain Labels

2021-09-29 · Xin Jin, Tianyu He, Xu Shen, Songhua Wu 외

In this paper, we propose an embarrassing simple yet highly effective adversarial domain adaptation (ADA) method for effectively training models for alignment. We view ADA problem primarily from a neural network memoriza…

Domain AdaptationMemorization

Are LLM-based Recommenders Already the Best? Simple Scaled Cross-entropy Unleashes the Potential of Traditional Sequential Recommenders

2024-08-26 · Cong Xu, Zhangchi Zhu, Mo Yu, Jun Wang 외

Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achie…

Sequential Recommendation