English
Related papers

Related papers: Training-based Model Refinement and Representation…

200 papers

Deep learning-based solutions for semantic segmentation suffer from significant performance degradation when tested on data with different characteristics than what was used during the training. Adapting the models using annotated data from…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Xingchen Zhao , Niluthpol Chowdhury Mithun , Abhinav Rajvanshi , Han-Pang Chiu , Supun Samarasekera

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed approach uses a teacher model which is updated as the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-28 Vimal Manohar , Tatiana Likhomanenko , Qiantong Xu , Wei-Ning Hsu , Ronan Collobert , Yatharth Saraf , Geoffrey Zweig , Abdelrahman Mohamed

Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that…

Machine Learning · Computer Science 2023-01-19 Aswathnarayan Radhakrishnan , Jim Davis , Zachary Rabin , Benjamin Lewis , Matthew Scherreik , Roman Ilin

Semi-supervised learning (SSL) has been proposed to leverage unlabeled data for training powerful models when only limited labeled data is available. While existing SSL methods assume that samples in the labeled and unlabeled data share the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-23 Qing Yu , Daiki Ikami , Go Irie , Kiyoharu Aizawa

Surface defect detection plays an increasingly important role in manufacturing industry to guarantee the product quality. Many deep learning methods have been widely used in surface defect detection tasks, and have been proven to perform…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Jiahui Cheng , Bin Guo , Jiaqi Liu , Sicong Liu , Guangzhi Wu , Yueqi Sun , Zhiwen Yu

Semi-supervised learning (SSL) has demonstrated high performance in image classification tasks by effectively utilizing both labeled and unlabeled data. However, existing SSL methods often suffer from poor calibration, with models yielding…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Mehrab Mustafy Rahman , Jayanth Mohan , Tiberiu Sosea , Cornelia Caragea

Person re-identification (re-ID) aims at identifying the same persons' images across different cameras. However, domain diversities between different datasets pose an evident challenge for adapting the re-ID model trained on one dataset to…

Computer Vision and Pattern Recognition · Computer Science 2020-01-31 Yixiao Ge , Dapeng Chen , Hongsheng Li

Multi-view learning methods often focus on improving decision accuracy while neglecting the decision uncertainty, which significantly restricts their applications in safety-critical scenarios. To address this, trusted multi-view learning…

Machine Learning · Computer Science 2025-07-24 Yilin Zhang , Cai Xu , Han Jiang , Ziyu Guan , Wei Zhao , Xiaofei He , Murat Sensoy

Lesion detection serves a critical role in early diagnosis and has been well explored in recent years due to methodological advancesand increased data availability. However, the high costs of annotations hinder the collection of large and…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Bolin Lai , Yuhsuan Wu , Xiao-Yun Zhou , Peng Wang , Le Lu , Lingyun Huang , Mei Han , Jing Xiao , Heping Hu , Adam P. Harrison

Supervised deep learning for semantic segmentation has achieved excellent results in accurately identifying anatomical and pathological structures in medical images. However, it often requires large annotated training datasets, which limits…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Luca Ciampi , Gabriele Lagani , Giuseppe Amato , Fabrizio Falchi

The current state-of-the-art methods in domain adaptive object detection (DAOD) use Mean Teacher self-labelling, where a teacher model, directly derived as an exponential moving average of the student model, is used to generate labels on…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Marc-Antoine Lavoie , Anas Mahmoud , Steven L. Waslander

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Shuaijun Chen , Xu Jia , Jianzhong He , Yongjie Shi , Jianzhuang Liu

In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus…

Neural and Evolutionary Computing · Computer Science 2017-03-16 Samuli Laine , Timo Aila

The teacher-student framework, prevalent in semi-supervised semantic segmentation, mainly employs the exponential moving average (EMA) to update a single teacher's weights based on the student's. However, EMA updates raise a problem in that…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Jaemin Na , Jung-Woo Ha , Hyung Jin Chang , Dongyoon Han , Wonjun Hwang

Consistency training, which exploits both supervised and unsupervised learning with different augmentations on image, is an effective method of utilizing unlabeled data in semi-supervised learning (SSL) manner. Here, we present another…

Computer Vision and Pattern Recognition · Computer Science 2021-09-01 Juyong Lee , Seunghyuk Cho

Despite significant success of deep learning in object detection tasks, the standard training of deep neural networks requires access to a substantial quantity of annotated images across all classes. Data annotation is an arduous and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Zeyu Shangguan , Mohammad Rostami

In Automatic Speech Recognition (ASR), teacher-student (T/S) training has shown to perform well for domain adaptation with small amount of training data. However, adaption without ground-truth labels is still challenging. A previous study…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-08 Rehan Ahmad , Muhammad Umar Farooq , Thomas Hain

In this work, we focus on semi-supervised learning for video action detection. Video action detection requires spatiotemporal localization in addition to classification, and a limited amount of labels makes the model prone to unreliable…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Akash Kumar , Sirshapan Mitra , Yogesh Singh Rawat

In this technical report, we present our submission to the VisDA Challenge in ECCV 2020 and we achieved one of the top-performing results on the leaderboard. Our solution is based on Structured Domain Adaptation (SDA) and Mutual…

Computer Vision and Pattern Recognition · Computer Science 2020-08-25 Yixiao Ge , Shijie Yu , Dapeng Chen

Unsupervised multi-object discovery (MOD) aims to detect and localize distinct object instances in visual scenes without any form of human supervision. Recent approaches leverage object-centric learning (OCL) and motion cues from video to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Xinrui Gong , Oliver Hahn , Christoph Reich , Krishnakant Singh , Simone Schaub-Meyer , Daniel Cremers , Stefan Roth