paper-with-me

홈 › Papers

Pseudo-Label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection

2022-10-01 · Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2022 10 · Jun Yu, Liwen Zhang, Shenshen Du, Hao Chang, Keda Lu, Zhong Zhang, Ye Yu, Lei Wang, Qiang Ling

Semi-supervised learning is a highly researched problem, but existing semi-supervised object detection frameworks are based on RGB images, and existing pre-trained models cannot be used for hyperspectral images. To overcome these difficulties, this paper first select fewer but suitable data augmentation methods to improve the accuracy of the supervised model based on the labeled training set, which is suitable for the characteristics of hyperspectral images. Next, in order to make full use of the unlabeled training set, we generate pseudo-labels with the model trained in the first stage and mix the obtained pseudo-labels with the labeled training set. Then, a large number of strong data augmentation methods are added to make the final model better. We achieve the SOTA, with an AP of 26.35, on the Semi-Supervised Hyperspectral Object Detection Challenge (SSHODC) in the CVPR 2022 Perception Beyond the Visible Spectrum Workshop, and win the first place in this Challenge.

📄 PDF Abstract BibTeX

Code (1)

zlw1113/CVPR2022-SSHODC-Mindspore mindspore

Tasks

Data Augmentationobject-detectionObject DetectionPseudo LabelSemi-Supervised Object Detection

Similar Papers 제목 키워드 기반

Image to Pseudo-Episode: Boosting Few-Shot Segmentation by Unlabeled Data

2024-05-14 · Jie Zhang, Yuhan Li, Yude Wang, Stephen Lin 외

Few-shot segmentation (FSS) aims to train a model which can segment the object from novel classes with a few labeled samples. The insufficient generalization ability of models leads to unsatisfactory performance when the…

Data AugmentationPseudo Label

Target-Side Data Augmentation for Sequence Generation

2021-09-29 · ICLR 2022 4 · Shufang Xie, Ang Lv, Yingce Xia, Lijun Wu 외

Autoregressive sequence generation, a prevalent task in machine learning and natural language processing, generates every target token conditioned on both a source input and previously generated target tokens. Previous d…

Abstractive Text SummarizationData AugmentationDecoderMachine Translation+1

PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds

2022-10-24 · Zhaoqi Leng, Shuyang Cheng, Benjamin Caine, Weiyue Wang 외

Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing augmentation policies have so far been designed to only utilize labeled data, …

Data AugmentationPseudo Labelvehicle detection

Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels

2023-02-21 · NeurIPS 2023 11 · Zebin You, Yong Zhong, Fan Bao, Jiacheng Sun 외

In an effort to further advance semi-supervised generative and classification tasks, we propose a simple yet effective training strategy called dual pseudo training (DPT), built upon strong semi-supervised learners and d…

Classification

NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation

2023-11-20 · Hao Dong, Gaëtan Frusque, Yue Zhao, Eleni Chatzi 외

Anomaly detection (AD) is essential in identifying rare and often critical events in complex systems, finding applications in fields such as network intrusion detection, financial fraud detection, and fault detection in …

Anomaly DetectionData AugmentationFault DetectionFraud Detection+4