Novel Class Discovery in Semantic Segmentation
- URL: http://arxiv.org/abs/2112.01900v1
- Date: Fri, 3 Dec 2021 13:31:59 GMT
- Title: Novel Class Discovery in Semantic Segmentation
- Authors: Yuyang Zhao, Zhun Zhong, Nicu Sebe, Gim Hee Lee
- Abstract summary: We introduce a new setting of Novel Class Discovery in Semantic (NCDSS)
It aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes.
In NCDSS, we need to distinguish the objects and background, and to handle the existence of multiple classes within an image.
We propose the Entropy-based Uncertainty Modeling and Self-training (EUMS) framework to overcome noisy pseudo-labels.
- Score: 104.30729847367104
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We introduce a new setting of Novel Class Discovery in Semantic Segmentation
(NCDSS), which aims at segmenting unlabeled images containing new classes given
prior knowledge from a labeled set of disjoint classes. In contrast to existing
approaches that look at novel class discovery in image classification, we focus
on the more challenging semantic segmentation. In NCDSS, we need to distinguish
the objects and background, and to handle the existence of multiple classes
within an image, which increases the difficulty in using the unlabeled data. To
tackle this new setting, we leverage the labeled base data and a saliency model
to coarsely cluster novel classes for model training in our basic framework.
Additionally, we propose the Entropy-based Uncertainty Modeling and
Self-training (EUMS) framework to overcome noisy pseudo-labels, further
improving the model performance on the novel classes. Our EUMS utilizes an
entropy ranking technique and a dynamic reassignment to distill clean labels,
thereby making full use of the noisy data via self-supervised learning. We
build the NCDSS benchmark on the PASCAL-5$^i$ dataset. Extensive experiments
demonstrate the feasibility of the basic framework (achieving an average mIoU
of 49.81%) and the effectiveness of EUMS framework (outperforming the basic
framework by 9.28% mIoU).
Related papers
- Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation [12.653336728447654]
We propose a class-shared memory (CSM) module consisting of a set of learnable memory vectors.
These memory vectors learn elemental object patterns from base classes during training whilst re-encoding query features during both training and inference.
We integrate CSM and UFA into representative FSS works, with experimental results on the widely-used PASCAL-5$i$ and COCO-20$i$ datasets.
arXiv Detail & Related papers (2024-06-01T19:53:25Z) - RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental
Segmentation [28.02204928717511]
We propose a weakly supervised approach to transfer objectness prior from the previously learned classes into the new ones.
We show how even a simple pairwise interaction between classes can significantly improve the segmentation mask quality of both old and new classes.
arXiv Detail & Related papers (2023-05-31T14:14:21Z) - Dynamic Conceptional Contrastive Learning for Generalized Category
Discovery [76.82327473338734]
Generalized category discovery (GCD) aims to automatically cluster partially labeled data.
Unlabeled data contain instances that are not only from known categories of the labeled data but also from novel categories.
One effective way for GCD is applying self-supervised learning to learn discriminate representation for unlabeled data.
We propose a Dynamic Conceptional Contrastive Learning framework, which can effectively improve clustering accuracy.
arXiv Detail & Related papers (2023-03-30T14:04:39Z) - Foundation Model Drives Weakly Incremental Learning for Semantic
Segmentation [12.362400851574872]
Weakly incremental learning for semantic segmentation (WILSS) is a novel and attractive task.
We propose a novel and data-efficient framework for WILSS, named FMWISS.
arXiv Detail & Related papers (2023-02-28T02:21:42Z) - Class-incremental Novel Class Discovery [76.35226130521758]
We study the new task of class-incremental Novel Class Discovery (class-iNCD)
We propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes.
Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches.
arXiv Detail & Related papers (2022-07-18T13:49:27Z) - Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks [59.12108527904171]
A model should recognize new classes and maintain discriminability over old classes.
The task of recognizing few-shot new classes without forgetting old classes is called few-shot class-incremental learning (FSCIL)
We propose a new paradigm for FSCIL based on meta-learning by LearnIng Multi-phase Incremental Tasks (LIMIT)
arXiv Detail & Related papers (2022-03-31T13:46:41Z) - Incremental Learning in Semantic Segmentation from Image Labels [18.404068463921426]
Existing semantic segmentation approaches achieve impressive results, but struggle to update their models incrementally as new categories are uncovered.
This paper proposes a novel framework for Weakly Incremental Learning for Semantics, that aims at learning to segment new classes from cheap and largely available image-level labels.
As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally.
arXiv Detail & Related papers (2021-12-03T12:47:12Z) - Open-World Semi-Supervised Learning [66.90703597468377]
We introduce a new open-world semi-supervised learning setting in which the model is required to recognize previously seen classes.
We propose ORCA, an approach that learns to simultaneously classify and cluster the data.
We demonstrate that ORCA accurately discovers novel classes and assigns samples to previously seen classes on benchmark image classification datasets.
arXiv Detail & Related papers (2021-02-06T07:11:07Z) - UniT: Unified Knowledge Transfer for Any-shot Object Detection and
Segmentation [52.487469544343305]
Methods for object detection and segmentation rely on large scale instance-level annotations for training.
We propose an intuitive and unified semi-supervised model that is applicable to a range of supervision.
arXiv Detail & Related papers (2020-06-12T22:45:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.