Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?

• URL: http://arxiv.org/abs/2305.09275v1
• Date: Tue, 16 May 2023 08:29:33 GMT
• Title: Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
• Authors: Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim, Philip H.S. Torr, Adel Bibi, Bernard Ghanem
• Abstract summary: We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy. We show that this metric is unreliable, as even vacuous blind classifiers can achieve unrealistically high online accuracy. Existing OCL algorithms can also achieve high online accuracy, but perform poorly in retaining useful information.
• Score: 135.71855998537347
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy, which measures the accuracy of the model on the immediate next few samples. However, we show that this metric is unreliable, as even vacuous blind classifiers, which do not use input images for prediction, can achieve unrealistically high online accuracy by exploiting spurious label correlations in the data stream. Our study reveals that existing OCL algorithms can also achieve high online accuracy, but perform poorly in retaining useful information, suggesting that they unintentionally learn spurious label correlations. To address this issue, we propose a novel metric for measuring adaptation based on the accuracy on the near-future samples, where spurious correlations are removed. We benchmark existing OCL approaches using our proposed metric on large-scale datasets under various computational budgets and find that better generalization can be achieved by retaining and reusing past seen information. We believe that our proposed metric can aid in the development of truly adaptive OCL methods. We provide code to reproduce our results at https://github.com/drimpossible/EvalOCL.

Related papers

• Label-free Monitoring of Self-Supervised Learning Progress [1.2289361708127877]
  Self-supervised learning (SSL) is an effective method for exploiting unlabelled data to learn a high-level embedding space. In this study, we propose several evaluation metrics which can be applied on the embeddings of unlabelled data.
  arXiv  Detail & Related papers  (2024-09-10T16:04:10Z)
• Towards Robust and Interpretable EMG-based Hand Gesture Recognition using Deep Metric Meta Learning [37.21211404608413]
  We propose a shift to deep metric-based meta-learning in EMG PR to supervise the creation of meaningful and interpretable representations. We derive a robust class proximity-based confidence estimator that leads to a better rejection of incorrect decisions.
  arXiv  Detail & Related papers  (2024-04-17T23:37:50Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation [15.728090002818963]
  Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels. In this paper, we aim to find an evaluation metric capable of assessing the quality of a transferred model without access to target validation labels.
  arXiv  Detail & Related papers  (2023-08-01T05:01:05Z)
• Estimating Large Language Model Capabilities without Labeled Test Data [51.428562302037534]
  Large Language Models (LLMs) have the impressive ability to perform in-context learning (ICL) from only a few examples. We propose the task of ICL accuracy estimation, in which we predict the accuracy of an LLM when doing in-context learning on a new task.
  arXiv  Detail & Related papers  (2023-05-24T06:55:09Z)
• Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering [15.3566963926257]
  This paper advocates a new principle for in-context learning (ICL): self-adaptive in-context learning. The self-adaption mechanism is introduced to help each sample find an in-context example permutation that can derive the correct prediction. Our self-adaptive ICL method achieves a 40% relative improvement over the common practice setting.
  arXiv  Detail & Related papers  (2022-12-20T15:55:21Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)
• ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning [52.831894583501395]
  Continual learning assumes the incoming data are fully labeled, which might not be applicable in real applications. We propose deep Online Replay with Discriminator Consistency (ORDisCo) to interdependently learn a classifier with a conditional generative adversarial network (GAN) We show ORDisCo achieves significant performance improvement on various semi-supervised learning benchmark datasets for SSCL.
  arXiv  Detail & Related papers  (2021-01-02T09:04:14Z)
• Meta-Generating Deep Attentive Metric for Few-shot Classification [53.07108067253006]
  We present a novel deep metric meta-generation method to generate a specific metric for a new few-shot learning task. In this study, we structure the metric using a three-layer deep attentive network that is flexible enough to produce a discriminative metric for each task. We gain surprisingly obvious performance improvement over state-of-the-art competitors, especially in the challenging cases.
  arXiv  Detail & Related papers  (2020-12-03T02:07:43Z)
• Calibrated neighborhood aware confidence measure for deep metric learning [0.0]
  Deep metric learning has been successfully applied to problems in few-shot learning, image retrieval, and open-set classifications. measuring the confidence of a deep metric learning model and identifying unreliable predictions is still an open challenge. This paper focuses on defining a calibrated and interpretable confidence metric that closely reflects its classification accuracy.
  arXiv  Detail & Related papers  (2020-06-08T21:05:38Z)

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.