Multivariate Prototype Representation for Domain-Generalized Incremental Learning

• URL: http://arxiv.org/abs/2309.13563v1
• Date: Sun, 24 Sep 2023 06:42:04 GMT
• Title: Multivariate Prototype Representation for Domain-Generalized Incremental Learning
• Authors: Can Peng, Piotr Koniusz, Kaiyu Guo, Brian C. Lovell, Peyman Moghadam
• Abstract summary: We design a DGCIL approach that remembers old classes, adapts to new classes, and can classify reliably objects from unseen domains. Our loss formulation maintains classification boundaries and suppresses the domain-specific information of each class.
• Score: 35.83706574551515
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning models suffer from catastrophic forgetting when being fine-tuned with samples of new classes. This issue becomes even more pronounced when faced with the domain shift between training and testing data. In this paper, we study the critical and less explored Domain-Generalized Class-Incremental Learning (DGCIL). We design a DGCIL approach that remembers old classes, adapts to new classes, and can classify reliably objects from unseen domains. Specifically, our loss formulation maintains classification boundaries and suppresses the domain-specific information of each class. With no old exemplars stored, we use knowledge distillation and estimate old class prototype drift as incremental training advances. Our prototype representations are based on multivariate Normal distributions whose means and covariances are constantly adapted to changing model features to represent old classes well by adapting to the feature space drift. For old classes, we sample pseudo-features from the adapted Normal distributions with the help of Cholesky decomposition. In contrast to previous pseudo-feature sampling strategies that rely solely on average mean prototypes, our method excels at capturing varying semantic information. Experiments on several benchmarks validate our claims.

Related papers

• PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning [49.240408681098906]
  Class-incremental learning (CIL) aims to recognize new classes incrementally while maintaining the discriminability of old classes. Most existing CIL methods are exemplar-based, i.e., storing a part of old data for retraining. We present a simple and novel dual bias reduction framework that employs self-supervised transformation (SST) in input space and prototype augmentation (protoAug) in deep feature space.
  arXiv  Detail & Related papers  (2024-07-19T05:03:16Z)
• ProtoGMM: Multi-prototype Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation [0.8213829427624407]
  Domain adaptive semantic segmentation aims to generate accurate and dense predictions for an unlabeled target domain. We propose the ProtoGMM model, which incorporates the GMM into contrastive losses to perform guided contrastive learning. To achieve increased intra-class semantic similarity, decreased inter-class similarity, and domain alignment between the source and target domains, we employ multi-prototype contrastive learning.
  arXiv  Detail & Related papers  (2024-06-27T14:50:50Z)
• Activate and Reject: Towards Safe Domain Generalization under Category Shift [71.95548187205736]
  We study a practical problem of Domain Generalization under Category Shift (DGCS) It aims to simultaneously detect unknown-class samples and classify known-class samples in the target domains. Compared to prior DG works, we face two new challenges: 1) how to learn the concept of unknown'' during training with only source known-class samples, and 2) how to adapt the source-trained model to unseen environments.
  arXiv  Detail & Related papers  (2023-10-07T07:53:12Z)
• Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning [99.14132861655223]
  We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining. Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
  arXiv  Detail & Related papers  (2022-11-29T14:52:38Z)
• Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations [80.76164484820818]
  There is an inescapable long-tailed class-imbalance issue in many real-world classification problems. We study this multi-domain long-tailed learning problem and aim to produce a model that generalizes well across all classes and domains. Built upon a proposed selective balanced sampling strategy, TALLY achieves this by mixing the semantic representation of one example with the domain-associated nuisances of another.
  arXiv  Detail & Related papers  (2022-10-25T21:54:26Z)
• Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection [0.0]
  We investigate the influences of various replay strategies for semantic segmentation and evaluate them in class- and domain-incremental settings. Our findings suggest that in a class-incremental setting, it is critical to achieve a uniform distribution for the different classes in the buffer. In the domain-incremental setting, it is most effective to select buffer samples by uniformly sampling from the distribution of learned feature representations or by choosing samples with median entropy.
  arXiv  Detail & Related papers  (2022-09-20T16:32:06Z)
• 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)
• Variational Feature Disentangling for Fine-Grained Few-Shot Classification [30.350307891161865]
  Fine-grained few-shot recognition often suffers from the problem of training data scarcity for novel categories. In this paper, we focus one enlarging the intra-class variance of the unseen class to improve few-shot classification performance.
  arXiv  Detail & Related papers  (2020-10-07T08:13:42Z)
• Adaptive Risk Minimization: Learning to Adapt to Domain Shift [109.87561509436016]
  A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. In this work, we consider the problem setting of domain generalization, where the training data are structured into domains and there may be multiple test time shifts. We introduce the framework of adaptive risk minimization (ARM), in which models are directly optimized for effective adaptation to shift by learning to adapt on the training domains.
  arXiv  Detail & Related papers  (2020-07-06T17:59:30Z)
• MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation [29.43532067090422]
  We propose an easy-to-implement method dubbed MiniMax Entropy Networks (MMEN) based on adversarial learning. Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples.
  arXiv  Detail & Related papers  (2019-04-21T13:39:29Z)

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.