# XCon: Learning with Experts for Fine-grained Category Discovery

arXiv: https://arxiv.org/abs/2208.01898 · HTML: https://mlsanity.com/paper/2208.01898/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 3 Aug 2022.

## Builds on (most cited first, 24 of 24)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [Automatically Discovering and Learning New Visual Categories with Ranking Statistics](https://mlsanity.com/paper/2002.05714/) (2020)
- [Learning to cluster in order to transfer across domains and tasks](https://mlsanity.com/paper/1711.10125/) (2017)
- [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)
- [Multi-class Classification without Multi-class Labels](https://mlsanity.com/paper/1901.00544/) (2019)
- [OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World](https://mlsanity.com/paper/2004.05551/) (2020)
- [Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2003.05438/) (2020)
- [Improving Contrastive Learning by Visualizing Feature Transformation](https://mlsanity.com/paper/2108.02982/) (2021)
- [Meta Discovery: Learning to Discover Novel Classes given Very Limited Data](https://mlsanity.com/paper/2102.04002/) (2021)

## Built on by (most cited first, 30 of 50)

- [Parametric Classification for Generalized Category Discovery: A Baseline Study](https://mlsanity.com/paper/2211.11727/) (2022)
- [Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery](https://mlsanity.com/paper/2305.06144/) (2023)
- [No Representation Rules Them All in Category Discovery](https://mlsanity.com/paper/2311.17055/) (2023)
- [Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery](https://mlsanity.com/paper/2310.19776/) (2023)
- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [Active Generalized Category Discovery](https://mlsanity.com/paper/2403.04272/) (2024)
- [Federated Generalized Category Discovery](https://mlsanity.com/paper/2305.14107/) (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)
- [Novel Class Discovery: an Introduction and Key Concepts](https://mlsanity.com/paper/2302.12028/) (2023)
- [Hyperbolic Category Discovery](https://mlsanity.com/paper/2504.06120/) (2025)
- [ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery](https://mlsanity.com/paper/2504.03755/) (2025)
- [Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery](https://mlsanity.com/paper/2307.10943/) (2023)
- [DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery](https://mlsanity.com/paper/2504.04804/) (2025)
- [Effective Prompt Pool Learning for Continual Category Discovery](https://mlsanity.com/paper/2407.19001/) (2024)
- [Novel Class Discovery for Ultra-Fine-Grained Visual Categorization](https://mlsanity.com/paper/2405.06283/) (2024)
- [Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction](https://mlsanity.com/paper/2508.10731/) (2025)
- [Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery](https://mlsanity.com/paper/2303.15975/) (2023)
- [MOS: Modeling Object-Scene Associations in Generalized Category Discovery](https://mlsanity.com/paper/2503.12035/) (2025)
- [Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery](https://mlsanity.com/paper/2409.19659/) (2024)
- [SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation](https://mlsanity.com/paper/2304.10113/) (2023)
- [Joint Out-of-Distribution Filtering and Data Discovery Active Learning](https://mlsanity.com/paper/2503.02491/) (2025)
- [SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery](https://mlsanity.com/paper/2510.18740/) (2025)
- [Contextuality Helps Representation Learning for Generalized Category Discovery](https://mlsanity.com/paper/2407.19752/) (2024)
- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [Generalized Category Discovery with Clustering Assignment Consistency](https://mlsanity.com/paper/2310.19210/) (2023)
- [Labeled Data Selection for Category Discovery](https://mlsanity.com/paper/2406.04898/) (2024)
- [Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2503.16782/) (2025)
- [DIG-FACE: De-biased Learning for Generalized Facial Expression Category Discovery](https://mlsanity.com/paper/2409.20098/) (2024)
- [Open Ad-hoc Categorization with Contextualized Feature Learning](https://mlsanity.com/paper/2512.16202/) (2025)

## Abstract (arXiv)

We address the problem of generalized category discovery (GCD) in this paper, i.e. clustering the unlabeled images leveraging the information from a set of seen classes, where the unlabeled images could contain both seen classes and unseen classes. The seen classes can be seen as an implicit criterion of classes, which makes this setting different from unsupervised clustering where the cluster criteria may be ambiguous. We mainly concern the problem of discovering categories within a fine-grained dataset since it is one of the most direct applications of category discovery, i.e. helping experts discover novel concepts within an unlabeled dataset using the implicit criterion set forth by the seen classes. State-of-the-art methods for generalized category discovery leverage contrastive learning to learn the representations, but the large inter-class similarity and intra-class variance pose a challenge for the methods because the negative examples may contain irrelevant cues for recognizing a category so the algorithms may converge to a local-minima. We present a novel method called Expert-Contrastive Learning (XCon) to help the model to mine useful information from the images by first partitioning the dataset into sub-datasets using k-means clustering and then performing contrastive learning on each of the sub-datasets to learn fine-grained discriminative features. Experiments on fine-grained datasets show a clear improved performance over the previous best methods, indicating the effectiveness of our method.