# Novel Class Discovery for Ultra-Fine-Grained Visual Categorization

arXiv: https://arxiv.org/abs/2405.06283 · HTML: https://mlsanity.com/paper/2405.06283/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 10 May 2024.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [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)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Evaluation of Output Embeddings for Fine-Grained Image Classification](https://mlsanity.com/paper/1409.8403/) (2014)
- [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 to Navigate for Fine-grained Classification](https://mlsanity.com/paper/1809.00287/) (2018)
- [OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World](https://mlsanity.com/paper/2004.05551/) (2020)
- [Dynamic Conceptional Contrastive Learning for Generalized Category Discovery](https://mlsanity.com/paper/2303.17393/) (2023)
- [The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification](https://mlsanity.com/paper/2002.04264/) (2020)
- [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)
- [Feature Fusion Vision Transformer for Fine-Grained Visual Categorization](https://mlsanity.com/paper/2107.02341/) (2021)
- [OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2207.02261/) (2022)
- [Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies](https://mlsanity.com/paper/2010.13636/) (2020)
- [Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy](https://mlsanity.com/paper/2203.17205/) (2022)
- [Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery](https://mlsanity.com/paper/2210.03591/) (2022)
- [Class-relation Knowledge Distillation for Novel Class Discovery](https://mlsanity.com/paper/2307.09158/) (2023)

## Built on by (most cited first, 13 of 13)

- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery](https://mlsanity.com/paper/2504.03755/) (2025)
- [Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery](https://mlsanity.com/paper/2507.04051/) (2025)
- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation](https://mlsanity.com/paper/2410.23693/) (2024)
- [Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2503.16782/) (2025)
- [Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs](https://mlsanity.com/paper/2505.01064/) (2025)
- [Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts](https://mlsanity.com/paper/2509.26227/) (2025)
- [Composing Novel Classes: A Concept-Driven Approach to Generalized Category Discovery](https://mlsanity.com/paper/2410.13285/) (2024)
- [Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning](https://mlsanity.com/paper/2509.06306/) (2025)
- [The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery](https://mlsanity.com/paper/2604.14176/) (2026)
- [Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data](https://mlsanity.com/paper/2604.19345/) (2026)
- [PHOEBI: An Open-World Benchmark for Multi-Label Bacterial Identification in Phase-Contrast Microscopy](https://mlsanity.com/paper/2606.22890/) (2026)

## Abstract (arXiv)

Ultra-fine-grained visual categorization (Ultra-FGVC) aims at distinguishing highly similar sub-categories within fine-grained objects, such as different soybean cultivars. Compared to traditional fine-grained visual categorization, Ultra-FGVC encounters more hurdles due to the small inter-class and large intra-class variation. Given these challenges, relying on human annotation for Ultra-FGVC is impractical. To this end, our work introduces a novel task termed Ultra-Fine-Grained Novel Class Discovery (UFG-NCD), which leverages partially annotated data to identify new categories of unlabeled images for Ultra-FGVC. To tackle this problem, we devise a Region-Aligned Proxy Learning (RAPL) framework, which comprises a Channel-wise Region Alignment (CRA) module and a Semi-Supervised Proxy Learning (SemiPL) strategy. The CRA module is designed to extract and utilize discriminative features from local regions, facilitating knowledge transfer from labeled to unlabeled classes. Furthermore, SemiPL strengthens representation learning and knowledge transfer with proxy-guided supervised learning and proxy-guided contrastive learning. Such techniques leverage class distribution information in the embedding space, improving the mining of subtle differences between labeled and unlabeled ultra-fine-grained classes. Extensive experiments demonstrate that RAPL significantly outperforms baselines across various datasets, indicating its effectiveness in handling the challenges of UFG-NCD. Code is available at https://github.com/SSDUT-Caiyq/UFG-NCD.