paper-with-me

홈 › Papers

A viable framework for semi-supervised learning on realistic dataset

2022-07-21 · Machine Learning 2022 7 · Hao Chang, Guochen Xie, Jun Yu, Qiang Ling, Fang Gao, Ye Yu

Semi-supervised Fine-Grained Recognition is a challenging task due to the difficulty of data imbalance, high inter-class similarity and domain mismatch. Recently, this field has witnessed giant leap and many methods have gained great performance. We discover that these existing Semi-supervised Learning (SSL) methods achieve satisfactory performance owe to the exploration of unlabeled data. However, on the realistic large-scale datasets, due to the abovementioned challenges, the improvement of the quality of pseudo-labels requires further research. In this work, we propose Bilateral-Branch Self-Training Framework (BiSTF), a simple yet effective framework to improve existing semi-supervised learning methods on class-imbalanced and domain-shifted fine-grained data. By adjusting stochastic epoch update frequency, BiSTF iteratively retrains a baseline SSL model with a labeled set expanded by selectively adding pseudo-labeled samples from an unlabeled set, where the distribution of pseudo-labeled samples is the same as the labeled data. We show that BiSTF outperforms the existing state-of-the-art SSL algorithm on Semi-iNat dataset. Our code is available at https://github.com/HowieChangchn/BiSTF.

📄 PDF Abstract BibTeX

Code (2)

2023-MindSpore-1/ms-code-136 mindspore
HowieChangchn/A-viable-framework-for-semi-supervised-learning-on-realistic-dataset mindspore

Similar Papers 제목 키워드 기반

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

Semi-Supervised Adaptation of Vision-Language Models for Image Classification

2026-08-26 · Mohamed L. Mekhalfi, Mohamad M. Al Rahhal, Yakoub Bazi, Salah E. Khenfer 외 arxiv

Vision-language models like CLIP have shown sig- nificant potential in handling natural images, yet their perfor- mance is often limited by the distinct characteristics of satellite imagery. While parameter-efficient ada…

Scene ClassificationImage Classification

OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data

2021-06-29 · Jongjin Park, Sukmin Yun, Jongheon Jeong, Jinwoo Shin

Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations. In this paper, we focus on a practical scenario that one aims to apply SSL when unlabeled data may…

Contrastive LearningRepresentation Learning

A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification

2021-04-01 · CVPR 2021 1 · Jong-Chyi Su, Zezhou Cheng, Subhransu Maji

We evaluate the effectiveness of semi-supervised learning (SSL) on a realistic benchmark where data exhibits considerable class imbalance and contains images from novel classes. Our benchmark consists of two fine-grained…

General ClassificationTransfer Learning

Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling

2026-01-08 · Xingyuan Li, Mengyue Wu arxiv

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recordi…