mlsanityData to 14 Oct 2026

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation

arXiv 2410.13094 ↗First posted 16 Oct 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 16 Oct 2024.

Builds on

29 of 35 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  8. 2016Pyramid Scene Parsing Networkcited by 2,479
  9. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  10. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  11. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  12. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
17 more
  1. 2019Large Scale Incremental Learningcited by 732
  2. 2019Panoptic Feature Pyramid Networkscited by 645
  3. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  4. 2020Few-Shot Class-Incremental Learningcited by 251
  5. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  6. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  7. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 190
  8. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
  9. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 96
  10. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  11. 2020Generalized Few-shot Semantic Segmentationcited by 59
  12. 2023MetaGCD: Learning to Continually Learn in Generalized Category Discoverycited by 42
  13. 2020Prototype-based Incremental Few-Shot Semantic Segmentationcited by 25
  14. 2022Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representationcited by 16
  15. 2023Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptationcited by 6
  16. 2023Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentationcited by 6
  17. 2023Masked Cross-image Encoding for Few-shot Segmentationcited by 3

Built on by

Not cited yet.