An EM Framework for Online Incremental Learning of Semantic Segmentation
- URL: http://arxiv.org/abs/2108.03613v1
- Date: Sun, 8 Aug 2021 11:30:09 GMT
- Title: An EM Framework for Online Incremental Learning of Semantic Segmentation
- Authors: Shipeng Yan, Jiale Zhou, Jiangwei Xie, Songyang Zhang, Xuming He
- Abstract summary: We propose an incremental learning strategy that can adapt deep segmentation models without catastrophic forgetting, using a streaming input data with pixel annotations on the novel classes only.
We validate our approach on the PASCAL VOC 2012 and ADE20K datasets, and the results demonstrate its superior performance over the existing incremental methods.
- Score: 37.94734474090863
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Incremental learning of semantic segmentation has emerged as a promising
strategy for visual scene interpretation in the open- world setting. However,
it remains challenging to acquire novel classes in an online fashion for the
segmentation task, mainly due to its continuously-evolving semantic label
space, partial pixelwise ground-truth annotations, and constrained data
availability. To ad- dress this, we propose an incremental learning strategy
that can fast adapt deep segmentation models without catastrophic forgetting,
using a streaming input data with pixel annotations on the novel classes only.
To this end, we develop a uni ed learning strategy based on the
Expectation-Maximization (EM) framework, which integrates an iterative
relabeling strategy that lls in the missing labels and a rehearsal-based
incremental learning step that balances the stability-plasticity of the model.
Moreover, our EM algorithm adopts an adaptive sampling method to select
informative train- ing data and a class-balancing training strategy in the
incremental model updates, both improving the e cacy of model learning. We
validate our approach on the PASCAL VOC 2012 and ADE20K datasets, and the
results demonstrate its superior performance over the existing incremental
methods.
Related papers
- CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning [17.614980614656407]
We propose Continual Generative training for Incremental prompt-Learning.
We exploit Variational Autoencoders to learn class-conditioned distributions.
We show that such a generative replay approach can adapt to new tasks while improving zero-shot capabilities.
arXiv Detail & Related papers (2024-07-22T16:51:28Z) - ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
We introduce Action-Aware Embodied Learning for Perception (ALP)
ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective.
We show that ALP outperforms existing baselines in several downstream perception tasks.
arXiv Detail & Related papers (2023-06-16T21:51:04Z) - Active Pointly-Supervised Instance Segmentation [106.38955769817747]
We present an economic active learning setting, named active pointly-supervised instance segmentation (APIS)
APIS starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object.
The model developed with these strategies yields consistent performance gain on the challenging MS-COCO dataset.
arXiv Detail & Related papers (2022-07-23T11:25:24Z) - Improving Meta-learning for Low-resource Text Classification and
Generation via Memory Imitation [87.98063273826702]
We propose a memory imitation meta-learning (MemIML) method that enhances the model's reliance on support sets for task adaptation.
A theoretical analysis is provided to prove the effectiveness of our method.
arXiv Detail & Related papers (2022-03-22T12:41:55Z) - Novel Class Discovery in Semantic Segmentation [104.30729847367104]
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.
arXiv Detail & Related papers (2021-12-03T13:31:59Z) - 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) - Adapting Segmentation Networks to New Domains by Disentangling Latent
Representations [14.050836886292869]
Domain adaptation approaches have come into play to transfer knowledge acquired on a label-abundant source domain to a related label-scarce target domain.
We propose a novel performance metric to capture the relative efficacy of an adaptation strategy compared to supervised training.
arXiv Detail & Related papers (2021-08-06T09:43:07Z) - Learning to Continuously Optimize Wireless Resource in a Dynamic
Environment: A Bilevel Optimization Perspective [52.497514255040514]
This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment.
We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes.
Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
arXiv Detail & Related papers (2021-05-03T07:23:39Z) - Model-based Meta Reinforcement Learning using Graph Structured Surrogate
Models [40.08137765886609]
We show that our model, called a graph structured surrogate model (GSSM), outperforms state-of-the-art methods in predicting environment dynamics.
Our approach is able to obtain high returns, while allowing fast execution during deployment by avoiding test time policy gradient optimization.
arXiv Detail & Related papers (2021-02-16T17:21:55Z)
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.