mlsanityData to 14 Oct 2026

Incremental Few-Shot Instance Segmentation

arXiv 2105.05312 ↗First posted 11 May 2021cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

Few-shot instance segmentation methods are promising when labeled training data for novel classes is scarce. However, current approaches do not facilitate flexible addition of novel classes. They also require that examples of each class are provided at train and test time, which is memory intensive. In this paper, we address these limitations by presenting the first incremental approach to few-shot instance segmentation: iMTFA. We learn discriminative embeddings for object instances that are merged into class representatives. Storing embedding vectors rather than images effectively solves the memory overhead problem. We match these class embeddings at the RoI-level using cosine similarity. This allows us to add new classes without the need for further training or access to previous training data. In a series of experiments, we consistently outperform the current state-of-the-art. Moreover, the reduced memory requirements allow us to evaluate, for the first time, few-shot instance segmentation performance on all classes in COCO jointly.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 11 May 2021.

Builds on

29 of 39 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2017Mask R-CNNcited by 7,277
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  12. 2019Objects as Pointscited by 1,175
17 more
  1. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  2. 2019A Closer Look at Few-shot Classificationcited by 684
  3. 2016Learning to learn by gradient descent by gradient descentcited by 620
  4. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  5. 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
  6. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  7. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  8. 2017Semantic Instance Segmentation with a Discriminative Loss Functioncited by 118
  9. 2020Incremental Few-Shot Object Detectioncited by 102
  10. 2015Learning to Segment Object Candidatescited by 79
  11. 2016Deep Watershed Transform for Instance Segmentationcited by 78
  12. 2018Deep Cosine Metric Learning for Person Re-Identificationcited by 73
  13. 2017Recurrent Pixel Embedding for Instance Groupingcited by 58
  14. 2017MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Featurescited by 54
  15. 2020FGN: Fully Guided Network for Few-Shot Instance Segmentationcited by 46
  16. 2018One-Shot Instance Segmentationcited by 43
  17. 2019ShapeMask: Learning to Segment Novel Objects by Refining Shape Priorscited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 12; 2023: 20; 2024: 7; 2025: 5; 2026: 3.

49 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2023Class-Incremental Learning: A Surveycited by 209
  3. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  4. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  5. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  6. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  7. 2022From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instrumentscited by 32
  8. 2022RBC: Rectifying the Biased Context in Continual Semantic Segmentationcited by 27
  9. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  10. 2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
  11. 2022iFS-RCNN: An Incremental Few-shot Instance Segmentercited by 19
  12. 2024A Simple Image Segmentation Framework via In-Context Examplescited by 19
37 more
  1. 2023MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentationcited by 18
  2. 2022Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representationcited by 16
  3. 2023New Insights for the Stability-Plasticity Dilemma in Online Continual Learningcited by 16
  4. 2024Zero-shot Generalizable Incremental Learning for Vision-Language Object Detectioncited by 15
  5. 2025DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistencycited by 15
  6. 2022Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learningcited by 14
  7. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  8. 2023Continual Learning for Image Segmentation with Dynamic Querycited by 12
  9. 2025No time to train! Training-Free Reference-Based Instance Segmentationcited by 9
  10. 2021Towards Generalized and Incremental Few-Shot Object Detectioncited by 7
  11. 2023Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentationcited by 6
  12. 2023The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentationcited by 5
  13. 2023Instance-level Few-shot Learning with Class Hierarchy Miningcited by 5
  14. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
  15. 2024Few-shot Online Anomaly Detection and Segmentationcited by 5
  16. 2024Zero-Shot Automatic Annotation and Instance Segmentation using LLM-Generated Datasets: Eliminating Field Imaging and Manual Annotation for Deep Learning Model Developmentcited by 5
  17. 2022SupeRGB-D: Zero-shot Instance Segmentation in Cluttered Indoor Environmentscited by 4
  18. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  19. 2022Incremental Few-Shot Learning via Implanting and Compressingcited by 2
  20. 2022A New Knowledge Distillation Network for Incremental Few-Shot Surface Defect Detectioncited by 2
  21. 2023ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentationcited by 2
  22. 2023Incremental Few-Shot Object Detection via Simple Fine-Tuning Approachcited by 2
  23. 2023Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillationcited by 2
  24. 2024UniFS: Universal Few-shot Instance Perception with Point Representationscited by 2
  25. 2024Learning from Exemplars for Interactive Image Segmentationcited by 2
  26. 2022A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Imagescited by 1
  27. 2025Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentationcited by 1
  28. 2026SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentationcited by 1
  29. 2022Expanding continual few-shot learning benchmarks to include recognition of specific instancescited by 0
  30. 2023A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognitioncited by 0
  31. 2023Transport-Hub-Aware Spatial-Temporal Adaptive Graph Transformer for Traffic Flow Predictioncited by 0
  32. 2023SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Storecited by 0
  33. 2024Integrated Image-Text Based on Semi-supervised Learning for Small Sample Instance Segmentationcited by 0
  34. 2025Learning to Upscale 3D Segmentations in Neuroimagingcited by 0
  35. 2025Task-oriented Learnable Diffusion Timesteps for Universal Few-shot Learning of Dense Taskscited by 0
  36. 2026Reference-based Category Discovery: Unsupervised Object Detection with Category Awarenesscited by 0
  37. 2026Boundary-by-Mask: Few-Shot Instance Segmentation with Mask-Conditioned Boundary Learning for Texture-Poor Industrial Partscited by 0