paper-with-me

홈 › Papers

Autoencoder Based Sample Selection for Self-Taught Learning

2018-08-05 · Siwei Feng, Han Yu, Marco F. Duarte

Self-taught learning is a technique that uses a large number of unlabeled data as source samples to improve the task performance on target samples. Compared with other transfer learning techniques, self-taught learning can be applied to a broader set of scenarios due to the loose restrictions on the source data. However, knowledge transferred from source samples that are not sufficiently related to the target domain may negatively influence the target learner, which is referred to as negative transfer. In this paper, we propose a metric for the relevance between a source sample and the target samples. To be more specific, both source and target samples are reconstructed through a single-layer autoencoder with a linear relationship between source samples and reconstructed target samples being simultaneously enforced. An $\ell_{2,1}$-norm sparsity constraint is imposed on the transformation matrix to identify source samples relevant to the target domain. Source domain samples that are deemed relevant are assigned pseudo-labels reflecting their relevance to target domain samples, and are combined with target samples in order to provide an expanded training set for classifier training. Local data structures are also preserved during source sample selection through spectral graph analysis. Promising results in extensive experiments show the advantages of the proposed approach.

📄 PDF Abstract BibTeX arXiv:1808.01574

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

On the benefits of self-taught learning for brain decoding

2022-09-19 · Elodie Germani, Elisa Fromont, Camille Maumet

Context. We study the benefits of using a large public neuroimaging database composed of fMRI statistic maps, in a self-taught learning framework, for improving brain decoding on new tasks. First, we leverage the NeuroVa…

Brain Decoding

Evaluation of Self-taught Learning-based Representations for Facial Emotion Recognition

2022-04-26 · Bruna Delazeri, Leonardo L. Veras, Alceu de S. Britto Jr., Jean Paul Barddal 외

This work describes different strategies to generate unsupervised representations obtained through the concept of self-taught learning for facial emotion recognition (FER). The idea is to create complementary representat…

DiversityEmotion RecognitionFacial Emotion Recognition

Deep Self-Taught Learning for Weakly Supervised Object Localization

2017-04-18 · CVPR 2017 7 · Zequn Jie, Yunchao Wei, Xiaojie Jin, Jiashi Feng 외

Most existing weakly supervised localization (WSL) approaches learn detectors by finding positive bounding boxes based on features learned with image-level supervision. However, those features do not contain spatial loca…

ObjectObject LocalizationWeakly Supervised Object DetectionWeakly-Supervised Object Localization

Latent-Insensitive autoencoders for Anomaly Detection

2021-10-25 · Muhammad S. Battikh, Artem A. Lenskiy

Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in tra…

Anomaly DetectionClass Incremental LearningIncremental LearningTransfer Learning

HS-STAR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation

2025-05-26 · Feng Xiong, Hongling Xu, Yifei Wang, Runxi Cheng 외

Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging self-generated responses for self-training. Recent studies have incorporated reward models to guide…

Mathematical Reasoning