paper-with-me

Papers

CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection

2019-05-30 · Ye Guo, Ya-Li Li, Shengjin Wang

Generic object detection is one of the most fundamental problems in computer vision, yet it is difficult to provide all the bounding-box-level annotations aiming at large-scale object detection for thousands of categories. In this paper, we present a novel cross-supervised learning pipeline for large-scale object detection, denoted as CS-R-FCN. First, we propose to utilize the data flow of image-level annotated images in the fully-supervised two-stage object detection framework, leading to cross-supervised learning combining bounding-box-level annotated data and image-level annotated data. Second, we introduce a semantic aggregation strategy utilizing the relationships among the cross-supervised categories to reduce the unreasonable mutual inhibition effects during the feature learning. Experimental results show that the proposed CS-R-FCN improves the mAP by a large margin compared to previous related works.

📄 PDF Abstract BibTeX arXiv:1905.12863

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection

2023-03-16 · CVPR 2023 1 · Liang Liu, Boshen Zhang, Jiangning Zhang, Wuhao Zhang 외

Scale variation across object instances remains a key challenge in object detection task. Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised cas…

Objectobject-detectionObject DetectionPseudo Label+1

CrossMatch: Improving Semi-Supervised Object Detection via Multi-Scale Consistency

2021-09-29 · Zhuoran Yu, Yen-Cheng Liu, Chih-Yao Ma, Zsolt Kira

We present a novel method, CrossMatch, for semi-supervised object detection. Inspired by the fact that teacher/student pseudo-labeling approaches result in a weak and sparse gradient signal due to the difficulty of conf…

Objectobject-detectionObject DetectionSemi-Supervised Object Detection

Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes

2019-08-14 · ICCV 2019 10 · Hao Yang, Hao Wu, Hao Chen

Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, thes…

Objectobject-detectionObject DetectionRe-Ranking

Scaling Novel Object Detection with Weakly Supervised Detection Transformers

2022-07-11 · Tyler LaBonte, Yale Song, Xin Wang, Vibhav Vineet 외

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect. Weakly supervised o…

Multiple Instance LearningNovel Object DetectionObjectobject-detection+3

VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection

2023-03-16 · Arushi Rai, Adriana Kovashka

The use of large-scale vision-language datasets is limited for object detection due to the negative impact of label noise on localization. Prior methods have shown how such large-scale datasets can be used for pretrainin…

object-detectionObject DetectionWeakly Supervised Object Detection