IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay

• URL: http://arxiv.org/abs/2104.10588v1
• Date: Wed, 21 Apr 2021 15:32:11 GMT
• Title: IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay
• Authors: Jian Jiang, Edoardo Cetin, Oya Celiktutan
• Abstract summary: Incremental learning aims to enable machine learning models to continuously acquire new knowledge given new classes. Saving a subset of training samples of previously seen classes in the memory and replaying them during new training phases is proven to be an efficient and effective way to fulfil this aim. However, finding a trade-off between the model performance and the number of samples to save for each class is still an open problem for replay-based incremental learning.
• Score: 4.8666876477091865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Incremental learning aims to enable machine learning models to continuously acquire new knowledge given new classes, while maintaining the knowledge already learned for old classes. Saving a subset of training samples of previously seen classes in the memory and replaying them during new training phases is proven to be an efficient and effective way to fulfil this aim. It is evident that the larger number of exemplars the model inherits the better performance it can achieve. However, finding a trade-off between the model performance and the number of samples to save for each class is still an open problem for replay-based incremental learning and is increasingly desirable for real-life applications. In this paper, we approach this open problem by tapping into a two-step compression approach. The first step is a lossy compression, we propose to encode input images and save their discrete latent representations in the form of codes that are learned using a hierarchical Vector Quantised Variational Autoencoder (VQ-VAE). In the second step, we further compress codes losslessly by learning a hierarchical latent variable model with bits-back asymmetric numeral systems (BB-ANS). To compensate for the information lost in the first step compression, we introduce an Information Back (IB) mechanism that utilizes real exemplars for a contrastive learning loss to regularize the training of a classifier. By maintaining all seen exemplars' representations in the format of `codes', Discrete Representation Replay (DRR) outperforms the state-of-art method on CIFAR-100 by a margin of 4% accuracy with a much less memory cost required for saving samples. Incorporated with IB and saving a small set of old raw exemplars as well, the accuracy of DRR can be further improved by 2% accuracy.

Related papers

• A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks [81.2624272756733]
  In dense retrieval, deep encoders provide embeddings for both inputs and targets. We train a small parametric corrector network that adjusts stale cached target embeddings. Our approach matches state-of-the-art results even when no target embedding updates are made during training.
  arXiv  Detail & Related papers  (2024-09-03T13:29:13Z)
• Exemplar-Free Class Incremental Learning via Incremental Representation [26.759108983223115]
  We propose a textbfsimple Incremental Representation (IR) framework for efCIL without constructing old pseudo-features. IR utilizes dataset augmentation to cover a suitable feature space and prevents the model from forgetting by using a single L2 space maintenance loss.
  arXiv  Detail & Related papers  (2024-03-24T16:29:50Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning [56.29097276129473]
  We propose a simple yet effective framework, named Learning Prompt with Distribution-based Feature Replay (LP-DiF) To prevent the learnable prompt from forgetting old knowledge in the new session, we propose a pseudo-feature replay approach. When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt.
  arXiv  Detail & Related papers  (2024-01-03T07:59:17Z)
• Adaptive Cross Batch Normalization for Metric Learning [75.91093210956116]
  Metric learning is a fundamental problem in computer vision. We show that it is equally important to ensure that the accumulated embeddings are up to date. In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration.
  arXiv  Detail & Related papers  (2023-03-30T03:22:52Z)
• A Memory Transformer Network for Incremental Learning [64.0410375349852]
  We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to class-incremental learning results in the "catastrophic forgetting" of previously seen classes. One of the most successful existing methods has been the use of a memory of exemplars, which overcomes the issue of catastrophic forgetting by saving a subset of past data into a memory bank and utilizing it to prevent forgetting when training future tasks.
  arXiv  Detail & Related papers  (2022-10-10T08:27:28Z)
• Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning [73.24988226158497]
  We consider the high-impact problem of Data-Free Class-Incremental Learning (DFCIL) We propose a novel incremental distillation strategy for DFCIL, contributing a modified cross-entropy training and importance-weighted feature distillation. Our method results in up to a 25.1% increase in final task accuracy (absolute difference) compared to SOTA DFCIL methods for common class-incremental benchmarks.
  arXiv  Detail & Related papers  (2021-06-17T17:56:08Z)
• 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)

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.