PartCo: Part-Level Correspondence Priors Enhance Category Discovery
Not on the map. Why?
Abstract (arXiv)
Generalized Category Discovery (GCD) aims to identify both known and novel categories within unlabeled data by leveraging a set of labeled examples from known categories. Existing GCD methods primarily depend on semantic labels and global image representations, often overlooking the detailed part-level cues that are crucial for distinguishing closely related categories. In this paper, we introduce PartCo, short for Part-Level Correspondence Prior, a novel framework that enhances category discovery by incorporating part-level visual feature correspondences. By leveraging part-level relationships, PartCo captures finer-grained semantic structures, enabling a more nuanced understanding of category relationships. Importantly, PartCo seamlessly integrates with existing GCD methods without requiring significant modifications. Our extensive experiments on multiple benchmark datasets demonstrate that PartCo significantly improves the performance of current GCD approaches, outperforming most existing methods by bridging the gap between semantic labels and part-level visual compositions, thereby setting new benchmarks for GCD.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 61 of its 78 references that are in the map. First posted on arXiv 26 Sep 2025.
Builds on
61 of 78 references.
References · 61
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
- 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
- 2025DINOv3cited by 1,414
- 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
- 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
- 2020Object-Centric Learning with Slot Attentioncited by 876
- 2021Deep ViT Features as Dense Visual Descriptorscited by 330
- 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
38 more
- 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 301
- 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 225
- 2022Generalized Category Discoverycited by 211
- 2021Open-World Semi-Supervised Learningcited by 165
- 2021A Unified Objective for Novel Class Discoverycited by 162
- 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 143
- 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 121
- 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
- 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 116
- 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
- 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
- 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
- 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 92
- 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
- 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
- 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
- 2023No Representation Rules Them All in Category Discoverycited by 61
- 2019The Herbarium Challenge 2019 Datasetcited by 60
- 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57
- 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
- 2023Going Denser with Open-Vocabulary Part Segmentationcited by 51
- 2024SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuningcited by 51
- 2014Bird Species Categorization Using Pose Normalized Deep Convolutional Netscited by 50
- 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
- 2021Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learningcited by 40
- 2022Novel Class Discovery without Forgettingcited by 39
- 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
- 2022Grow and Merge: A Unified Framework for Continuous Categories Discoverycited by 33
- 2024Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discoverycited by 31
- 2018Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspectioncited by 27
- 2023Federated Generalized Category Discoverycited by 27
- 2024GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discoverycited by 27
- 2023CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discoverycited by 26
- 2023CLIP-GCD: Simple Language Guided Generalized Category Discoverycited by 25
- 2024HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shiftscited by 23
- 2025Hyperbolic Category Discoverycited by 20
- 2025ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discoverycited by 19
- 2025DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discoverycited by 15
50 most cited of 61 All 61 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.