FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

• URL: http://arxiv.org/abs/2309.14062v3
• Date: Fri, 12 Jan 2024 15:35:35 GMT
• Title: FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
• Authors: Dipam Goswami, Yuyang Liu, Bart{\l}omiej Twardowski, Joost van de Weijer
• Abstract summary: Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. We explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes.
• Score: 21.088762527081883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://github.com/dipamgoswami/FeCAM.

Related papers

• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning [82.29761875805369]
  One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. We propose a novel perspective to use pre-defined class anchors serving as feature centroid to unidirectionally guide feature learning. The proposed Semantic Anchor Regularization (SAR) can be used in a plug-and-play manner in the existing models.
  arXiv  Detail & Related papers  (2023-12-19T05:52:38Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers [26.844410679685424]
  We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. We show that the few-shot error of the learned feature map on new classes is small in case of class-feature-variability collapse.
  arXiv  Detail & Related papers  (2022-12-23T18:46:05Z)
• 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)
• Exploring Category-correlated Feature for Few-shot Image Classification [27.13708881431794]
  We present a simple yet effective feature rectification method by exploring the category correlation between novel and base classes as the prior knowledge. The proposed approach consistently obtains considerable performance gains on three widely used benchmarks.
  arXiv  Detail & Related papers  (2021-12-14T08:25:24Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• Self-Supervised Learning by Estimating Twin Class Distributions [26.7828253129684]
  We present TWIST, a novel self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a softmax operation to produce twin class distributions of two augmented images. Specifically, we minimize the entropy of the distribution for each sample to make the class prediction for each sample and maximize the entropy of the mean distribution to make the predictions of different samples diverse.
  arXiv  Detail & Related papers  (2021-10-14T14:39:39Z)
• Class-incremental Learning using a Sequence of Partial Implicitly Regularized Classifiers [0.0]
  In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. Our experiments on CIFAR100 dataset show that the proposed method improves the performance over SOTA by a large margin.
  arXiv  Detail & Related papers  (2021-04-04T10:02:45Z)
• Class-incremental Learning with Pre-allocated Fixed Classifiers [20.74548175713497]
  In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. We propose a novel fixed classifier in which a number of pre-allocated output nodes are subject to the classification loss right from the beginning of the learning phase.
  arXiv  Detail & Related papers  (2020-10-16T22:40:28Z)

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.