Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation

2024-10-16 · Wenbo Xu, Yanan Wu, Haoran Jiang, Yang Wang, Qiang Wu, Jian Zhang

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.

📄 PDF Abstract BibTeX arXiv:2410.13094

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Semantic Segmentation Incremental Learning Meta-Learning Semantic Segmentation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

BASE 설명 없음

Prototype-based Incremental Few-Shot Semantic Segmentation

2020-11-30 · Fabio Cermelli, Massimiliano Mancini, Yongqin Xian, Zeynep Akata 외

Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, constrained to the classes of the training s…

Few-Shot Semantic Segmentation Incremental Learning Knowledge Distillation Segmentation+1

SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning

2026-02-16 · Shishir Muralidhara, Didier Stricker, René Schuster arxiv

Continual learning remains constrained by the need for repeated retraining, high computational costs, and the persistent challenge of forgetting. These factors significantly limit the applicability of continuous learning…

Semantic Segmentation Continual Learning

Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments

2026-04-09 · Yun Zhu, Jianjun Qian, Jian Yang, Jin Xie 외 arxiv

Incremental 3D object perception is a critical step toward embodied intelligence in dynamic indoor environments. However, existing incremental 3D detection methods rely on extensive annotations of novel classes for satis…

Novel Object Detection 3D Object Detection

Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration

2023-12-08 · NeurIPS 2023 11 · Qi-Wei Wang, Da-Wei Zhou, Yi-Kai Zhang, De-Chuan Zhan 외

Real-world scenarios are usually accompanied by continuously appearing classes with scare labeled samples, which require the machine learning model to incrementally learn new classes and maintain the knowledge of base cl…

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Few-Shot Learning+3

Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks

2022-03-31 · Da-Wei Zhou, Han-Jia Ye, Liang Ma, Di Xie 외

New classes arise frequently in our ever-changing world, e.g., emerging topics in social media and new types of products in e-commerce. A model should recognize new classes and meanwhile maintain discriminability over ol…

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Incremental Learning+1