mlsanityData to 14 Oct 2026

iFS-RCNN: An Incremental Few-shot Instance Segmenter

arXiv 2205.15562 ↗First posted 31 May 2022cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

This paper addresses incremental few-shot instance segmentation, where a few examples of new object classes arrive when access to training examples of old classes is not available anymore, and the goal is to perform well on both old and new classes. We make two contributions by extending the common Mask-RCNN framework in its second stage -- namely, we specify a new object class classifier based on the probit function and a new uncertainty-guided bounding-box predictor. The former leverages Bayesian learning to address a paucity of training examples of new classes. The latter learns not only to predict object bounding boxes but also to estimate the uncertainty of the prediction as guidance for bounding box refinement. We also specify two new loss functions in terms of the estimated object-class distribution and bounding-box uncertainty. Our contributions produce significant performance gains on the COCO dataset over the state of the art -- specifically, the gain of +6 on the new classes and +16 on the old classes in the AP instance segmentation metric. Furthermore, we are the first to evaluate the incremental few-shot setting on the more challenging LVIS dataset.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 31 May 2022.

Builds on

32 of 39 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2017Mask R-CNNcited by 7,277
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2018YOLOv3: An Incremental Improvementcited by 2,659
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  9. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  10. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  11. 2019Objects as Pointscited by 1,175
  12. 2017Focal Loss for Dense Object Detectioncited by 752
20 more
  1. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 429
  2. 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
  3. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  4. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  5. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  6. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  7. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  8. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  9. 2020Incremental Few-Shot Object Detectioncited by 102
  10. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  11. 2018RepMet: Representative-based metric learning for classification and one-shot object detectioncited by 85
  12. 2018LSTD: A Low-Shot Transfer Detector for Object Detectioncited by 77
  13. 2021Incremental Few-Shot Instance Segmentationcited by 49
  14. 2020FGN: Fully Guided Network for Few-Shot Instance Segmentationcited by 46
  15. 2021Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitationcited by 44
  16. 2018One-Shot Instance Segmentationcited by 43
  17. 2020Localization Uncertainty Estimation for Anchor-Free Object Detectioncited by 19
  18. 2021FAPIS: A Few-shot Anchor-free Part-based Instance Segmentercited by 15
  19. 2021Class-Incremental Few-Shot Object Detectioncited by 13
  20. 2021Towards Generalized and Incremental Few-Shot Object Detectioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 13; 2024: 2; 2025: 2; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  2. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  3. 2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
  4. 2023MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentationcited by 18
  5. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  6. 2023Continual Learning for Image Segmentation with Dynamic Querycited by 12
  7. 2025No time to train! Training-Free Reference-Based Instance Segmentationcited by 9
  8. 2023Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentationcited by 6
  9. 2023The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentationcited by 5
  10. 2023Instance-level Few-shot Learning with Class Hierarchy Miningcited by 5
  11. 2024Zero-Shot Automatic Annotation and Instance Segmentation using LLM-Generated Datasets: Eliminating Field Imaging and Manual Annotation for Deep Learning Model Developmentcited by 5
  12. 2022Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmentercited by 3
7 more
  1. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  2. 2023ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentationcited by 2
  3. 2023Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillationcited by 2
  4. 2023CMFDFormer: Transformer-based Copy-Move Forgery Detection with Continual Learningcited by 1
  5. 2025Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentationcited by 1
  6. 2024Integrated Image-Text Based on Semi-supervised Learning for Small Sample Instance Segmentationcited by 0
  7. 2026Reference-based Category Discovery: Unsupervised Object Detection with Category Awarenesscited by 0