paper-with-me

홈 › Papers

Adversarial Feature Distribution Alignment for Semi-Supervised Learning

2019-12-22 · Christoph Mayer, Matthieu Paul, Radu Timofte

Training deep neural networks with only a few labeled samples can lead to overfitting. This is problematic in semi-supervised learning where only a few labeled samples are available. In this paper, we show that a consequence of overfitting in SSL is feature distribution misalignment between labeled and unlabeled samples. Hence, we propose a new feature distribution alignment method. Our method is particularly effective when using only a small amount of labeled samples. We test our method on CIFAR10 and SVHN. On SVHN we achieve a test error of 3.88% (250 labeled samples) and 3.39% (1000 labeled samples) which is close to the fully supervised model 2.89% (73k labeled samples). In comparison, the current SOTA achieves only 4.29% and 3.74%. Finally, we provide a theoretical insight why feature distribution alignment occurs and show that our method reduces it.

📄 PDF Abstract BibTeX arXiv:1912.10428

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

2020-07-12 · ECCV 2020 8 · Chenyang Si, Xuecheng Nie, Wei Wang, Liang Wang 외

We consider the problem of semi-supervised 3D action recognition which has been rarely explored before. Its major challenge lies in how to effectively learn motion representations from unlabeled data. Self-supervised lea…

3D Action RecognitionAction RecognitionSelf-Supervised Learning

SemiGDA: Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentation

2026-04-25 · Kaiwen Huang, Yi Zhou, Yizhe Zhang, Jingxiong Li 외 arxiv

Semi-supervised learning addresses label scarcity and high annotation costs in medical image segmentation by exploiting the latent information in unlabeled data to enhance model performance. Traditional discriminative se…

Semi-supervised Medical Image SegmentationRepresentation Learning

Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound

2022-03-13 · Feiyu Wang, Qin Wang, Wen Li, Dong Xu 외

In this work, we revisit the semi-supervised learning (SSL) problem from a new perspective of explicitly reducing empirical distribution mismatch between labeled and unlabeled samples. Benefited from this new perspective…

Data AugmentationDomain Adaptation

FireMatch: A Semi-Supervised Video Fire Detection Network Based on Consistency and Distribution Alignment

2023-11-09 · Qinghua Lin, Zuoyong Li, Kun Zeng, Haoyi Fan 외

Deep learning techniques have greatly enhanced the performance of fire detection in videos. However, video-based fire detection models heavily rely on labeled data, and the process of data labeling is particularly costly…

Data AugmentationFairnessFire DetectionPseudo Label

Semi-Supervised Learning by Augmented Distribution Alignment

2019-05-20 · ICCV 2019 10 · Qin Wang, Wen Li, Luc van Gool

In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited n…

Domain AdaptationSemi-Supervised Image Classification