Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

• URL: http://arxiv.org/abs/2112.04731v5
• Date: Sun, 7 Apr 2024 17:09:58 GMT
• Title: Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
• Authors: Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip Torr, Song Bai, Vincent Y. F. Tan,
• Abstract summary: We study the difference between a na"ively-trained initial-phase model and the oracle model. We propose Class-wise Decorrelation (CwD) that effectively regularizes representations of each class to scatter more uniformly. Our CwD is simple to implement and easy to plug into existing methods.
• Score: 141.35105358670316
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class Incremental Learning (CIL) aims at learning a multi-class classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Previous works mainly focus on mitigating forgetting in phases after the initial one. However, we find that improving CIL at its initial phase is also a promising direction. Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance. Motivated by this, we study the difference between a na\"ively-trained initial-phase model and the oracle model. Specifically, since one major difference between these two models is the number of training classes, we investigate how such difference affects the model representations. We find that, with fewer training classes, the data representations of each class lie in a long and narrow region; with more training classes, the representations of each class scatter more uniformly. Inspired by this observation, we propose Class-wise Decorrelation (CwD) that effectively regularizes representations of each class to scatter more uniformly, thus mimicking the model jointly trained with all classes (i.e., the oracle model). Our CwD is simple to implement and easy to plug into existing methods. Extensive experiments on various benchmark datasets show that CwD consistently and significantly improves the performance of existing state-of-the-art methods by around 1\% to 3\%. Code will be released.

Related papers

• Covariance-based Space Regularization for Few-shot Class Incremental Learning [25.435192867105552]
  Few-shot Class Incremental Learning (FSCIL) requires the model to continually learn new classes with limited labeled data. Due to the limited data in incremental sessions, models are prone to overfitting new classes and suffering catastrophic forgetting of base classes. Recent advancements resort to prototype-based approaches to constrain the base class distribution and learn discriminative representations of new classes.
  arXiv  Detail & Related papers  (2024-11-02T08:03:04Z)
• 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)
• Subclass-balancing Contrastive Learning for Long-tailed Recognition [38.31221755013738]
  Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. We propose a novel subclass-balancing contrastive learning'' approach that clusters each head class into multiple subclasses of similar sizes as the tail classes. We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-06-28T05:08:43Z)
• Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer [9.356870107137093]
  In class-incremental learning, the model is expected to learn new classes continually while maintaining knowledge on previous classes. We propose two distillation-based objectives for class incremental learning.
  arXiv  Detail & Related papers  (2022-08-07T16:28:02Z)
• Class-Incremental Learning with Strong Pre-trained Models [97.84755144148535]
  Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes) We explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. Our proposed method is robust and generalizes to all analyzed CIL settings.
  arXiv  Detail & Related papers  (2022-04-07T17:58:07Z)
• Self-Supervised Class Incremental Learning [51.62542103481908]
  Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time.
  arXiv  Detail & Related papers  (2021-11-18T06:58:19Z)
• Class-Balanced Distillation for Long-Tailed Visual Recognition [100.10293372607222]
  Real-world imagery is often characterized by a significant imbalance of the number of images per class, leading to long-tailed distributions. In this work, we introduce a new framework, by making the key observation that a feature representation learned with instance sampling is far from optimal in a long-tailed setting. Our main contribution is a new training method, that leverages knowledge distillation to enhance feature representations.
  arXiv  Detail & Related papers  (2021-04-12T08:21:03Z)
• Few-Shot Incremental Learning with Continually Evolved Classifiers [46.278573301326276]
  Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. We propose a Continually Evolved CIF ( CEC) that employs a graph model to propagate context information between classifiers for adaptation.
  arXiv  Detail & Related papers  (2021-04-07T10:54:51Z)
• CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition [52.66360172784038]
  We propose a clustering-based model, which considers all training samples at once, instead of optimizing for each instance individually. We call the proposed method CLASTER and observe that it consistently improves over the state-of-the-art in all standard datasets.
  arXiv  Detail & Related papers  (2021-01-18T12:46:24Z)

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.