# Multi-class Classification without Multi-class Labels

arXiv: https://arxiv.org/abs/1901.00544 · HTML: https://mlsanity.com/paper/1901.00544/

## Key facts

- Cited by 100 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2019.

## Built on by (most cited first, 30 of 100)

- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [Neighborhood Contrastive Learning for Novel Class Discovery](https://mlsanity.com/paper/2106.10731/) (2021)
- [AutoNovel: Automatically Discovering and Learning Novel Visual Categories](https://mlsanity.com/paper/2106.15252/) (2021)
- [Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation](https://mlsanity.com/paper/2107.03358/) (2021)
- [Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery](https://mlsanity.com/paper/2305.06144/) (2023)
- [Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data](https://mlsanity.com/paper/2104.12673/) (2021)
- [XCon: Learning with Experts for Fine-grained Category Discovery](https://mlsanity.com/paper/2208.01898/) (2022)
- [Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification](https://mlsanity.com/paper/2106.06133/) (2021)
- [Class-incremental Novel Class Discovery](https://mlsanity.com/paper/2207.08605/) (2022)
- [Novel Class Discovery without Forgetting](https://mlsanity.com/paper/2207.10659/) (2022)
- [Towards Robust Ranker for Text Retrieval](https://mlsanity.com/paper/2206.08063/) (2022)
- [OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2207.02261/) (2022)
- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [OpenCon: Open-world Contrastive Learning](https://mlsanity.com/paper/2208.02764/) (2022)
- [Meta Discovery: Learning to Discover Novel Classes given Very Limited Data](https://mlsanity.com/paper/2102.04002/) (2021)
- [New Intent Discovery with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2205.12914/) (2022)
- [Federated Generalized Category Discovery](https://mlsanity.com/paper/2305.14107/) (2023)
- [Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery](https://mlsanity.com/paper/2210.03591/) (2022)
- [CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery](https://mlsanity.com/paper/2304.06928/) (2023)
- [Incremental Generalized Category Discovery](https://mlsanity.com/paper/2304.14310/) (2023)
- [CLIP-GCD: Simple Language Guided Generalized Category Discovery](https://mlsanity.com/paper/2305.10420/) (2023)
- [TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition](https://mlsanity.com/paper/2110.15063/) (2021)
- [Novel Class Discovery: an Introduction and Key Concepts](https://mlsanity.com/paper/2302.12028/) (2023)
- [Class-relation Knowledge Distillation for Novel Class Discovery](https://mlsanity.com/paper/2307.09158/) (2023)
- [A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2311.03524/) (2023)
- [Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2104.01286/) (2021)
- [When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis](https://mlsanity.com/paper/2308.05017/) (2023)
- [Learning from Similarity-Confidence Data](https://mlsanity.com/paper/2102.06879/) (2021)

## Abstract (arXiv)

This work presents a new strategy for multi-class classification that requires no class-specific labels, but instead leverages pairwise similarity between examples, which is a weaker form of annotation. The proposed method, meta classification learning, optimizes a binary classifier for pairwise similarity prediction and through this process learns a multi-class classifier as a submodule. We formulate this approach, present a probabilistic graphical model for it, and derive a surprisingly simple loss function that can be used to learn neural network-based models. We then demonstrate that this same framework generalizes to the supervised, unsupervised cross-task, and semi-supervised settings. Our method is evaluated against state of the art in all three learning paradigms and shows a superior or comparable accuracy, providing evidence that learning multi-class classification without multi-class labels is a viable learning option.