Online Prototype Learning for Online Continual Learning
- URL: http://arxiv.org/abs/2308.00301v1
- Date: Tue, 1 Aug 2023 05:46:40 GMT
- Title: Online Prototype Learning for Online Continual Learning
- Authors: Yujie Wei, Jiaxin Ye, Zhizhong Huang, Junping Zhang, Hongming Shan
- Abstract summary: We study the problem of learning continuously from a single-pass data stream.
By storing a small subset of old data, replay-based methods have shown promising performance.
This paper aims to understand why the online learning models fail to generalize well from a new perspective of shortcut learning.
- Score: 36.91213307667659
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Online continual learning (CL) studies the problem of learning continuously
from a single-pass data stream while adapting to new data and mitigating
catastrophic forgetting. Recently, by storing a small subset of old data,
replay-based methods have shown promising performance. Unlike previous methods
that focus on sample storage or knowledge distillation against catastrophic
forgetting, this paper aims to understand why the online learning models fail
to generalize well from a new perspective of shortcut learning. We identify
shortcut learning as the key limiting factor for online CL, where the learned
features may be biased, not generalizable to new tasks, and may have an adverse
impact on knowledge distillation. To tackle this issue, we present the online
prototype learning (OnPro) framework for online CL. First, we propose online
prototype equilibrium to learn representative features against shortcut
learning and discriminative features to avoid class confusion, ultimately
achieving an equilibrium status that separates all seen classes well while
learning new classes. Second, with the feedback of online prototypes, we devise
a novel adaptive prototypical feedback mechanism to sense the classes that are
easily misclassified and then enhance their boundaries. Extensive experimental
results on widely-used benchmark datasets demonstrate the superior performance
of OnPro over the state-of-the-art baseline methods. Source code is available
at https://github.com/weilllllls/OnPro.
Related papers
- Towards Non-Exemplar Semi-Supervised Class-Incremental Learning [33.560003528712414]
Class-incremental learning aims to gradually recognize new classes while maintaining the discriminability of old ones.
We propose a non-exemplar semi-supervised CIL framework with contrastive learning and semi-supervised incremental prototype classifier (Semi-IPC)
Semi-IPC learns a prototype for each class with unsupervised regularization, enabling the model to incrementally learn from partially labeled new data.
arXiv Detail & Related papers (2024-03-27T06:28:19Z) - RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning [68.42776779425978]
We show that existing online continually trained deep networks produce inferior representations compared to a simple pre-defined random transforms.
We then train a simple linear classifier on top without storing any exemplars, processing one sample at a time in an online continual learning setting.
Our study reveals the significant limitations of representation learning, particularly in low-exemplar and online continual learning scenarios.
arXiv Detail & Related papers (2024-02-13T22:07:29Z) - Few-Shot Class-Incremental Learning via Training-Free Prototype
Calibration [67.69532794049445]
We find a tendency for existing methods to misclassify the samples of new classes into base classes, which leads to the poor performance of new classes.
We propose a simple yet effective Training-frEE calibratioN (TEEN) strategy to enhance the discriminability of new classes.
arXiv Detail & Related papers (2023-12-08T18:24:08Z) - Online Continual Learning with Contrastive Vision Transformer [67.72251876181497]
This paper proposes a framework Contrastive Vision Transformer (CVT) to achieve a better stability-plasticity trade-off for online CL.
Specifically, we design a new external attention mechanism for online CL that implicitly captures previous tasks' information.
Based on the learnable focuses, we design a focal contrastive loss to rebalance contrastive learning between new and past classes and consolidate previously learned representations.
arXiv Detail & Related papers (2022-07-24T08:51:02Z) - Bypassing Logits Bias in Online Class-Incremental Learning with a
Generative Framework [15.345043222622158]
We focus on online class-incremental learning setting in which new classes emerge over time.
Almost all existing methods are replay-based with a softmax classifier.
We propose a novel generative framework based on the feature space.
arXiv Detail & Related papers (2022-05-19T06:54:20Z) - Tackling Online One-Class Incremental Learning by Removing Negative
Contrasts [12.048166025000976]
Distinct from other continual learning settings the learner is presented new samples only once.
ER-AML achieved strong performance in this setting by applying an asymmetric loss based on contrastive learning to the incoming data and replayed data.
We adapt a recently proposed approach from self-supervised learning to the supervised learning setting, unlocking the constraint on contrasts.
arXiv Detail & Related papers (2022-03-24T19:17:29Z) - New Insights on Reducing Abrupt Representation Change in Online
Continual Learning [69.05515249097208]
We focus on the change in representations of observed data that arises when previously unobserved classes appear in the incoming data stream.
We show that applying Experience Replay causes the newly added classes' representations to overlap significantly with the previous classes.
We propose a new method which mitigates this issue by shielding the learned representations from drastic adaptation to accommodate new classes.
arXiv Detail & Related papers (2022-03-08T01:37:00Z) - Online Continual Learning with Natural Distribution Shifts: An Empirical
Study with Visual Data [101.6195176510611]
"Online" continual learning enables evaluating both information retention and online learning efficacy.
In online continual learning, each incoming small batch of data is first used for testing and then added to the training set, making the problem truly online.
We introduce a new benchmark for online continual visual learning that exhibits large scale and natural distribution shifts.
arXiv Detail & Related papers (2021-08-20T06:17:20Z) - Continual Prototype Evolution: Learning Online from Non-Stationary Data
Streams [42.525141660788]
We introduce a system to enable learning and prediction at any point in time.
In contrast to the major body of work in continual learning, data streams are processed in an online fashion.
We obtain state-of-the-art performance by a significant margin on eight benchmarks, including three highly imbalanced data streams.
arXiv Detail & Related papers (2020-09-02T09:39:26Z) - Incremental Learning In Online Scenario [8.885829189810197]
Current state-of-the-art incremental learning methods require a long time to train the model whenever new classes are added.
We propose an incremental learning framework that can work in the challenging online learning scenario.
arXiv Detail & Related papers (2020-03-30T02:24:26Z)
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.