On Generalizing Beyond Domains in Cross-Domain Continual Learning
- URL: http://arxiv.org/abs/2203.03970v1
- Date: Tue, 8 Mar 2022 09:57:48 GMT
- Title: On Generalizing Beyond Domains in Cross-Domain Continual Learning
- Authors: Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel
Schulter, Yumin Suh, Mehrtash Harandi, Manmohan Chandraker
- Abstract summary: 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.
- Score: 91.56748415975683
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Humans have the ability to accumulate knowledge of new tasks in varying
conditions, but deep neural networks often suffer from catastrophic forgetting
of previously learned knowledge after learning a new task. Many recent methods
focus on preventing catastrophic forgetting under the assumption of train and
test data following similar distributions. In this work, we consider a more
realistic scenario of continual learning under domain shifts where the model
must generalize its inference to an unseen domain. To this end, we encourage
learning semantically meaningful features by equipping the classifier with
class similarity metrics as learning parameters which are obtained through
Mahalanobis similarity computations. Learning of the backbone representation
along with these extra parameters is done seamlessly in an end-to-end manner.
In addition, we propose an approach based on the exponential moving average of
the parameters for better knowledge distillation. We demonstrate that, to a
great extent, existing continual learning algorithms fail to handle the
forgetting issue under multiple distributions, while our proposed approach
learns new tasks under domain shift with accuracy boosts up to 10% on
challenging datasets such as DomainNet and OfficeHome.
Related papers
- Reinforcement Learning Based Multi-modal Feature Fusion Network for
Novel Class Discovery [47.28191501836041]
In this paper, we employ a Reinforcement Learning framework to simulate the cognitive processes of humans.
We also deploy a Member-to-Leader Multi-Agent framework to extract and fuse features from multi-modal information.
We demonstrate the performance of our approach in both the 3D and 2D domains by employing the OS-MN40, OS-MN40-Miss, and Cifar10 datasets.
arXiv Detail & Related papers (2023-08-26T07:55:32Z) - Complementary Learning Subnetworks for Parameter-Efficient
Class-Incremental Learning [40.13416912075668]
We propose a rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks.
Our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order.
arXiv Detail & Related papers (2023-06-21T01:43:25Z) - Transfer Learning via Test-Time Neural Networks Aggregation [11.42582922543676]
It has been demonstrated that deep neural networks outperform traditional machine learning.
Deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution.
arXiv Detail & Related papers (2022-06-27T15:46:05Z) - Forget Less, Count Better: A Domain-Incremental Self-Distillation
Learning Benchmark for Lifelong Crowd Counting [51.44987756859706]
Off-the-shelf methods have some drawbacks to handle multiple domains.
Lifelong Crowd Counting aims at alleviating the catastrophic forgetting and improving the generalization ability.
arXiv Detail & Related papers (2022-05-06T15:37:56Z) - Learn to Adapt for Monocular Depth Estimation [17.887575611570394]
We propose an adversarial depth estimation task and train the model in the pipeline of meta-learning.
Our method adapts well to new datasets after few training steps during the test procedure.
arXiv Detail & Related papers (2022-03-26T06:49:22Z) - Uncertainty Modeling for Out-of-Distribution Generalization [56.957731893992495]
We argue that the feature statistics can be properly manipulated to improve the generalization ability of deep learning models.
Common methods often consider the feature statistics as deterministic values measured from the learned features.
We improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
arXiv Detail & Related papers (2022-02-08T16:09:12Z) - Cross-Domain Similarity Learning for Face Recognition in Unseen Domains [90.35908506994365]
We introduce a novel cross-domain metric learning loss, which we dub Cross-Domain Triplet (CDT) loss, to improve face recognition in unseen domains.
The CDT loss encourages learning semantically meaningful features by enforcing compact feature clusters of identities from one domain.
Our method does not require careful hard-pair sample mining and filtering strategy during training.
arXiv Detail & Related papers (2021-03-12T19:48:01Z) - Flexible deep transfer learning by separate feature embeddings and
manifold alignment [0.0]
Object recognition is a key enabler across industry and defense.
Unfortunately, algorithms trained on existing labeled datasets do not directly generalize to new data because the data distributions do not match.
We propose a novel deep learning framework that overcomes this limitation by learning separate feature extractions for each domain.
arXiv Detail & Related papers (2020-12-22T19:24:44Z) - Multi-task Supervised Learning via Cross-learning [102.64082402388192]
We consider a problem known as multi-task learning, consisting of fitting a set of regression functions intended for solving different tasks.
In our novel formulation, we couple the parameters of these functions, so that they learn in their task specific domains while staying close to each other.
This facilitates cross-fertilization in which data collected across different domains help improving the learning performance at each other task.
arXiv Detail & Related papers (2020-10-24T21:35:57Z) - Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network.
Our motivation is that models are expected to understand complex dynamics from different sources.
Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
arXiv Detail & Related papers (2020-09-24T15:40:55Z)
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.