mlsanityData to 7 Oct 2026

Are Labels Needed for Incremental Instance Learning?

arXiv 2301.11417 ↗First posted 26 Jan 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

In this paper, we learn to classify visual object instances, incrementally and via self-supervision (self-incremental). Our learner observes a single instance at a time, which is then discarded from the dataset. Incremental instance learning is challenging, since longer learning sessions exacerbate forgetfulness, and labeling instances is cumbersome. We overcome these challenges via three contributions: i. We propose VINIL, a self-incremental learner that can learn object instances sequentially, ii. We equip VINIL with self-supervision to by-pass the need for instance labelling, iii. We compare VINIL to label-supervised variants on two large-scale benchmarks, and show that VINIL significantly improves accuracy while reducing forgetfulness.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 46 of its 61 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

46 of 61 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  7. 2016Learning without Forgettingcited by 2,465
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  9. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  11. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  12. 2017Continual Learning with Deep Generative Replaycited by 1,152
34 more
  1. 2018Experience Replay for Continual Learningcited by 1,074
  2. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  3. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  4. 2019Large Scale Incremental Learningcited by 727
  5. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  6. 2018End-to-End Incremental Learningcited by 596
  7. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  8. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
  9. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  10. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  11. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  12. 2021Co2L: Contrastive Continual Learningcited by 243
  13. 2020VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrievalcited by 188
  14. 2022TransGeo: Transformer Is All You Need for Cross-view Image Geo-localizationcited by 166
  15. 2021Self-Supervised Models are Continual Learnerscited by 149
  16. 2019H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactionscited by 139
  17. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
  18. 2017Deep Metric Learning with Angular Losscited by 107
  19. 2021Representational Continuity for Unsupervised Continual Learningcited by 95
  20. 2022Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Imagecited by 88
  21. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  22. 2016Siamese Instance Search for Trackingcited by 60
  23. 2021Essentials for Class Incremental Learningcited by 57
  24. 2021Self-Supervised Training Enhances Online Continual Learningcited by 53
  25. 2021Continually Learning Self-Supervised Representations with Projected Functional Regularizationcited by 38
  26. 2022The Challenges of Continuous Self-Supervised Learningcited by 36
  27. 2021How Well Does Self-Supervised Pre-Training Perform with Streaming Data?cited by 29
  28. 2020The Effectiveness of Memory Replay in Large Scale Continual Learningcited by 26
  29. 2022GAMa: Cross-view Video Geo-localizationcited by 23
  30. 2021Visual and Object Geo-localization: A Comprehensive Surveycited by 13
  31. 2021SPeCiaL: Self-Supervised Pretraining for Continual Learningcited by 12
  32. 2022Hand-Object Interaction Reasoningcited by 7
  33. 2022Evaluating Continual Test-Time Adaptation for Contextual and Semantic Domain Shiftscited by 5
  34. 2020Continual Learning of Object Instancescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Continual Hyperbolic Learning of Instances and Classescited by 4
  2. 2026Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Modelscited by 0