OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning

Rizve, Mamshad Nayeem; Kardan, Navid; Khan, Salman; Khan, Fahad Shahbaz; Shah, Mubarak

doi:10.1007/978-3-031-19821-2_22

Cited by 22 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, as multiple articles were published simultaneously, different names were used and problem was presented in varying ways. Some of these names include Generalized Novel Class Discovery [41], Open Set Domain Adaptation [43] and Open-World Semi-Supervised Learning [44], however, they all ultimately aimed to solve the same task.…”

Section: New Domains Derived From Novel Class Discoverymentioning

confidence: 99%

Novel Class Discovery: an Introduction and Key Concepts

Troisemaine¹,

Lemaire²,

Gosselin³

et al. 2023

Preprint

View full text Add to dashboard Cite

Novel Class Discovery (NCD) is a growing field where we are given during training a labeled set of known classes and an unlabeled set of different classes that must be discovered. In recent years, many methods have been proposed to address this problem, and the field has begun to mature. In this paper, we provide a comprehensive survey of the state-of-the-art NCD methods. We start by formally defining the NCD problem and introducing important notions. We then give an overview of the different families of approaches, organized by the way they transfer knowledge from the labeled set to the unlabeled set. We find that they either learn in two stages, by first extracting knowledge from the labeled data only and then applying it to the unlabeled data, or in one stage by conjointly learning on both sets. For each family, we describe their general principle and detail a few representative methods. Then, we briefly introduce some new related tasks inspired by the increasing number of NCD works. We also present some common tools and techniques used in NCD, such as pseudo labeling, self-supervised learning and contrastive learning. Finally, to help readers unfamiliar with the NCD problem differentiate it from other closely related domains, we summarize some of the closest areas of research and discuss their main differences.

show abstract

Section: New Domains Derived From Novel Class Discoverymentioning

confidence: 99%

Novel Class Discovery: an Introduction and Key Concepts

Troisemaine¹,

Lemaire²,

Gosselin³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…GCD (Vaze et al, 2022;Lin et al, 2020;Zhang et al, 2021bMou et al, 2022; assume partial known classes with annotations which can also be used to infer user's requirement on clustering. As an infant research area, most previous works employ pseudo-labelling, via optimal transport (Rizve et al, 2022b;, similarity learning (Rizve et al, 2022a;Cao et al, 2022) or prototype-based learning (Sun and Li, 2022). Furthermore, new intent discovery (Zhang et al, , 2021bLin et al, 2020) Select the banking customer utterance that better corresponds with the Query in terms of intent.…”

Section: G More Related Workmentioning

confidence: 99%

ClusterLLM: Large Language Models as a Guide for Text Clustering

Zhang,

Wang,

Shang

2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We introduce CLUSTERLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupervised methods that builds upon "small" embedders, CLUSTERLLM exhibits two intriguing advantages: (1) it enjoys the emergent capability of LLM even if its embeddings are inaccessible; and (2) it understands the user's preference on clustering through textual instruction and/or a few annotated data. First, we prompt ChatGPT for insights on clustering perspective by constructing hard triplet questions , where A, B and C are similar data points that belong to different clusters according to small embedder. We empirically show that this strategy is both effective for fine-tuning small embedder and cost-efficient to query ChatGPT. Second, we prompt ChatGPT for helps on clustering granularity by carefully designed pairwise questions , and tune the granularity from cluster hierarchies that is the most consistent with the ChatGPT answers. Extensive experiments on 14 datasets show that CLUSTERLLM consistently improves clustering quality, at an average cost of ∼$0.6 1 per dataset. The code will be available at https: //github.com/zhang-yu-wei/ClusterLLM.

show abstract

“…Method Labeled Novel All DTC [9] 0.539 0.395 0.383 CGDL [58] 0.723 0.446 0.397 UNO [10] 0.916 0.693 0.805 ORCA [59] 0.882 0.904 0.897 OpenLDN UDA [60] 0.957 0.951 0.954 Ours 0.961 0.952 0.956…”

Section: Classification Accuracymentioning

confidence: 99%

Information Fusion Based on Multi-View and Multi-Feature Learning

Li¹,

Zhang²,

Zhang³

2022

Information Fusion

View full text Add to dashboard Cite

With the development of deep learning techniques, supervised learning has achieved performances surpassing those of humans. Researchers have designed numerous corresponding models for different data modalities, achieving excellent results in supervised tasks. However, with the exponential increase of data in multiple fields, the recognition and classification of unlabeled data have gradually become a hot topic. In this paper, we employed a Reinforcement Learning framework to simulate the cognitive processes of humans for effectively addressing novel class discovery in the Open-set domain. We deployed a Member-to-Leader Multi-Agent framework to extract and fuse features from multi-modal information, aiming to acquire a more comprehensive understanding of the feature space. Furthermore, this approach facilitated the incorporation of self-supervised learning to enhance model training. We employed a clustering method with varying constraint conditions, ranging from strict to loose, allowing for the generation of dependable labels for a subset of unlabeled data during the training phase. This iterative process is similar to human exploratory learning of unknown data. These mechanisms collectively update the network parameters based on rewards received from environmental feedback. This process enables effective control over the extent of exploration learning, ensuring the accuracy of learning in unknown data categories. We demonstrate the performance of our approach in both the 3D and 2D domains by employing the OS-MN40, OS-MN40-Miss, and Cifar10 datasets. Our approach achieves competitive competitive results. The source code can be found here: https://github.com/AveryFallson/RMFFN

show abstract

OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning

Cited by 22 publications

References 37 publications

Novel Class Discovery: an Introduction and Key Concepts

Novel Class Discovery: an Introduction and Key Concepts

ClusterLLM: Large Language Models as a Guide for Text Clustering

Information Fusion Based on Multi-View and Multi-Feature Learning

Contact Info

Product

Resources

About