General Incremental Learning with Domain-aware Categorical
Representations
- URL: http://arxiv.org/abs/2204.04078v1
- Date: Fri, 8 Apr 2022 13:57:33 GMT
- Title: General Incremental Learning with Domain-aware Categorical
Representations
- Authors: Jiangwei Xie, Shipeng Yan, Xuming He
- Abstract summary: We develop a novel domain-aware continual learning method based on the EM framework.
Specifically, we introduce a flexible class representation based on the von Mises-Fisher mixture model to capture the intra-class structure.
We design a bi-level balanced memory to cope with data imbalances within and across classes, which combines with a distillation loss to achieve better inter- and intra-class stability-plasticity trade-off.
- Score: 37.68376996568006
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Continual learning is an important problem for achieving human-level
intelligence in real-world applications as an agent must continuously
accumulate knowledge in response to streaming data/tasks. In this work, we
consider a general and yet under-explored incremental learning problem in which
both the class distribution and class-specific domain distribution change over
time. In addition to the typical challenges in class incremental learning, this
setting also faces the intra-class stability-plasticity dilemma and intra-class
domain imbalance problems. To address above issues, we develop a novel
domain-aware continual learning method based on the EM framework. Specifically,
we introduce a flexible class representation based on the von Mises-Fisher
mixture model to capture the intra-class structure, using an
expansion-and-reduction strategy to dynamically increase the number of
components according to the class complexity. Moreover, we design a bi-level
balanced memory to cope with data imbalances within and across classes, which
combines with a distillation loss to achieve better inter- and intra-class
stability-plasticity trade-off. We conduct exhaustive experiments on three
benchmarks: iDigits, iDomainNet and iCIFAR-20. The results show that our
approach consistently outperforms previous methods by a significant margin,
demonstrating its superiority.
Related papers
- StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization [85.18995948334592]
Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain.
State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data.
We propose emphStyDeSty, which explicitly accounts for the alignment of the source and pseudo domains in the process of data augmentation.
arXiv Detail & Related papers (2024-06-01T02:41:34Z) - Cross-Domain Continual Learning via CLAMP [10.553456651003055]
CLAMP significantly outperforms established baseline algorithms across all experiments by at least $10%$ margin.
An assessor-guided learning process is put forward to navigate the learning process of a base model.
arXiv Detail & Related papers (2024-05-12T02:41:31Z) - Transitive Vision-Language Prompt Learning for Domain Generalization [41.484858946789664]
The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains.
However, there are still some issues that an advancement still suffers from trading-off between domain invariance and class separability.
arXiv Detail & Related papers (2024-04-29T14:56:11Z) - DiffClass: Diffusion-Based Class Incremental Learning [30.514281721324853]
Class Incremental Learning (CIL) is challenging due to catastrophic forgetting.
Recent exemplar-free CIL methods attempt to mitigate catastrophic forgetting by synthesizing previous task data.
We propose a novel exemplar-free CIL method to overcome these issues.
arXiv Detail & Related papers (2024-03-08T03:34:18Z) - Enhancing cross-domain detection: adaptive class-aware contrastive
transformer [15.666766743738531]
Insufficient labels in the target domain exacerbate issues of class imbalance and model performance degradation.
We propose a class-aware cross domain detection transformer based on the adversarial learning and mean-teacher framework.
arXiv Detail & Related papers (2024-01-24T07:11:05Z) - Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization [5.124256074746721]
We argue that the generalization ability of deep convolutional neural networks can be improved by taking advantage of multi-layer and multi-scaled representations of the network.
We introduce a framework that aims at improving domain generalization of image classifiers by combining both low-level and high-level features at multiple scales.
We show that our model is able to surpass the performance of previous DG methods and consistently produce competitive and state-of-the-art results in all datasets.
arXiv Detail & Related papers (2023-08-28T08:54:27Z) - Neural Collapse Terminus: A Unified Solution for Class Incremental
Learning and Its Variants [166.916517335816]
In this paper, we offer a unified solution to the misalignment dilemma in the three tasks.
We propose neural collapse terminus that is a fixed structure with the maximal equiangular inter-class separation for the whole label space.
Our method holds the neural collapse optimality in an incremental fashion regardless of data imbalance or data scarcity.
arXiv Detail & Related papers (2023-08-03T13:09:59Z) - Learning to Augment via Implicit Differentiation for Domain
Generalization [107.9666735637355]
Domain generalization (DG) aims to overcome the problem by leveraging multiple source domains to learn a domain-generalizable model.
In this paper, we propose a novel augmentation-based DG approach, dubbed AugLearn.
AugLearn shows effectiveness on three standard DG benchmarks, PACS, Office-Home and Digits-DG.
arXiv Detail & Related papers (2022-10-25T18:51:51Z) - On Generalizing Beyond Domains in Cross-Domain Continual Learning [91.56748415975683]
Deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.
Our proposed approach learns new tasks under domain shift with accuracy boosts up to 10% on challenging datasets such as DomainNet and OfficeHome.
arXiv Detail & Related papers (2022-03-08T09:57:48Z) - Dynamic Federated Learning [57.14673504239551]
Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments.
We consider a federated learning model where at every iteration, a random subset of available agents perform local updates based on their data.
Under a non-stationary random walk model on the true minimizer for the aggregate optimization problem, we establish that the performance of the architecture is determined by three factors, namely, the data variability at each agent, the model variability across all agents, and a tracking term that is inversely proportional to the learning rate of the algorithm.
arXiv Detail & Related papers (2020-02-20T15:00:54Z)
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.