Open-world Semi-Supervised Learning (OSSL) is a realistic and challenging task, aiming to classify unlabeled samples from both seen and novel classes using partially labeled samples from the seen classes. Previous works typically explore the relationship of samples as priors on the pre-defined single-granularity labels to help novel class recognition. In fact, classes follow a taxonomy and samples can be classified at multiple levels of granularity, which contains more underlying relationships for supervision. We thus argue that learning with single-granularity labels results in sub-optimal representation learning and inaccurate pseudo labels, especially with unknown classes. In this paper, we take the initiative to explore and propose a uniformed framework, called Taxonomic context prIors Discovering and Aligning (TIDA), which exploits the relationship of samples under various granularity. It allows us to discover multi-granularity semantic concepts as taxonomic context priors (i.e., sub-class, target-class, and super-class), and then collaboratively leverage them to enhance representation learning and improve the quality of pseudo labels. Specifically, TIDA comprises two components: i) A taxonomic context discovery module that constructs a set of hierarchical prototypes in the latent space to discover the underlying taxonomic context priors; ii) A taxonomic context-based prediction alignment module that enforces consistency across hierarchical predictions to build the reliable relationship between classes among various granularity and provide additions supervision. We demonstrate that these two components are mutually beneficial for an effective OSSL framework, which is theoretically explained from the perspective of the EM algorithm. Extensive experiments on seven commonly used datasets show that TIDA can significantly improve the performance and achieve a new state of the art. The source codes are publicly available at https://github.com/rain305f/TIDA.

Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning / Wang, Yu; Zhong, Zhun; Qiao, Pengchong; Cheng, Xuxin; Zheng, Xiawu; Liu, Chang; Sebe, Nicu; Ji, Rongrong; Chen, Jie. - 36:(2023), pp. 1-14. (Intervento presentato al convegno NeurIPS tenutosi a New Orleans nel 10- 16 December, 2023).

Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning

Zhong, Zhun;Sebe, Nicu;Chen Jie
2023-01-01

Abstract

Open-world Semi-Supervised Learning (OSSL) is a realistic and challenging task, aiming to classify unlabeled samples from both seen and novel classes using partially labeled samples from the seen classes. Previous works typically explore the relationship of samples as priors on the pre-defined single-granularity labels to help novel class recognition. In fact, classes follow a taxonomy and samples can be classified at multiple levels of granularity, which contains more underlying relationships for supervision. We thus argue that learning with single-granularity labels results in sub-optimal representation learning and inaccurate pseudo labels, especially with unknown classes. In this paper, we take the initiative to explore and propose a uniformed framework, called Taxonomic context prIors Discovering and Aligning (TIDA), which exploits the relationship of samples under various granularity. It allows us to discover multi-granularity semantic concepts as taxonomic context priors (i.e., sub-class, target-class, and super-class), and then collaboratively leverage them to enhance representation learning and improve the quality of pseudo labels. Specifically, TIDA comprises two components: i) A taxonomic context discovery module that constructs a set of hierarchical prototypes in the latent space to discover the underlying taxonomic context priors; ii) A taxonomic context-based prediction alignment module that enforces consistency across hierarchical predictions to build the reliable relationship between classes among various granularity and provide additions supervision. We demonstrate that these two components are mutually beneficial for an effective OSSL framework, which is theoretically explained from the perspective of the EM algorithm. Extensive experiments on seven commonly used datasets show that TIDA can significantly improve the performance and achieve a new state of the art. The source codes are publicly available at https://github.com/rain305f/TIDA.
2023
37th Conference on Neural Information Processing Systems (NeurIPS 2023)
San Diego, CA
NeurIPS foundation
Wang, Yu; Zhong, Zhun; Qiao, Pengchong; Cheng, Xuxin; Zheng, Xiawu; Liu, Chang; Sebe, Nicu; Ji, Rongrong; Chen, Jie
Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning / Wang, Yu; Zhong, Zhun; Qiao, Pengchong; Cheng, Xuxin; Zheng, Xiawu; Liu, Chang; Sebe, Nicu; Ji, Rongrong; Chen, Jie. - 36:(2023), pp. 1-14. (Intervento presentato al convegno NeurIPS tenutosi a New Orleans nel 10- 16 December, 2023).
File in questo prodotto:
File Dimensione Formato  
2448_discover_and_align_taxonomic_c (1).pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.23 MB
Formato Adobe PDF
5.23 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/401002
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact