mlsanityData to 7 Oct 2026

Spacing Loss for Discovering Novel Categories

arXiv 2204.10595 ↗First posted 22 Apr 2022cs.CV cs.AI cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes. In this work, we first characterize existing NCD approaches into single-stage and two-stage methods based on whether they require access to labeled and unlabeled data together while discovering new classes. Next, we devise a simple yet powerful loss function that enforces separability in the latent space using cues from multi-dimensional scaling, which we refer to as Spacing Loss. Our proposed formulation can either operate as a standalone method or can be plugged into existing methods to enhance them. We validate the efficacy of Spacing Loss with thorough experimental evaluation across multiple settings on CIFAR-10 and CIFAR-100 datasets.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 31 of its 46 references that are in the map. First posted on arXiv 22 Apr 2022.

Builds on

31 of 46 references.

References · 31

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2016Learning without Forgettingcited by 2,465
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  6. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  7. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  8. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  9. 2019Large Scale Incremental Learningcited by 727
  10. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  11. 2018End-to-End Incremental Learningcited by 596
  12. 2021Towards Open World Object Detectioncited by 297
19 more
  1. 2014Towards Open World Recognitioncited by 226
  2. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  3. 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 220
  4. 2021Projected GANs Converge Fastercited by 204
  5. 2021A Unified Objective for Novel Class Discoverycited by 161
  6. 2020Adaptive Aggregation Networks for Class-Incremental Learningcited by 149
  7. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
  8. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  9. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  10. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  11. 2020Conditional Channel Gated Networks for Task-Aware Continual Learningcited by 115
  12. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  13. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  14. 2019Multi-class Classification without Multi-class Labelscited by 100
  15. 2020OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open Worldcited by 93
  16. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  17. 2020Meta-Consolidation for Continual Learningcited by 40
  18. 2020Toward fast and accurate human pose estimation via soft-gated skip connectionscited by 22
  19. 2019An Adaptive Random Path Selection Approach for Incremental Learningcited by 16

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 5; 2024: 2; 2025: 1.

10 papers.

  1. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  2. 2022Novel Class Discovery without Forgettingcited by 39
  3. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  4. 2022Modeling Inter-Class and Intra-Class Constraints in Novel Class Discoverycited by 26
  5. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  6. 2024HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shiftscited by 22
  7. 2024Effective Prompt Pool Learning for Continual Category Discoverycited by 14
  8. 2025Category Discovery: An Open-World Perspectivecited by 5
  9. 2023Novel Categories Discovery Via Constraints on Empirical Prediction Statisticscited by 3
  10. 2023NEV-NCD: Negative Learning, Entropy, and Variance regularization based novel action categories discoverycited by 2