Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data

• URL: http://arxiv.org/abs/2204.08932v1
• Date: Tue, 19 Apr 2022 15:15:18 GMT
• Title: Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data
• Authors: Yu-Ming Tang, Yi-Xing Peng, Wei-Shi Zheng
• Abstract summary: We develop a learnable feature generator to diversify exemplars by adaptively generating diverse counterparts of exemplars. We introduce semantic contrastive learning to enforce the generated samples to be semantic consistent with exemplars. Our method does not bring any extra inference cost and outperforms state-of-the-art methods on two benchmarks.
• Score: 69.30452751012568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural network (DNN) suffers from catastrophic forgetting when learning incrementally, which greatly limits its applications. Although maintaining a handful of samples (called `exemplars`) of each task could alleviate forgetting to some extent, existing methods are still limited by the small number of exemplars since these exemplars are too few to carry enough task-specific knowledge, and therefore the forgetting remains. To overcome this problem, we propose to `imagine` diverse counterparts of given exemplars referring to the abundant semantic-irrelevant information from unlabeled data. Specifically, we develop a learnable feature generator to diversify exemplars by adaptively generating diverse counterparts of exemplars based on semantic information from exemplars and semantically-irrelevant information from unlabeled data. We introduce semantic contrastive learning to enforce the generated samples to be semantic consistent with exemplars and perform semanticdecoupling contrastive learning to encourage diversity of generated samples. The diverse generated samples could effectively prevent DNN from forgetting when learning new tasks. Our method does not bring any extra inference cost and outperforms state-of-the-art methods on two benchmarks CIFAR-100 and ImageNet-Subset by a clear margin.

Related papers

• Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks [10.556477506959888]
  Existing methods often encounter difficulties in drawing accurate class prototypes from support set samples. Recent approaches attempt to incorporate external knowledge or pre-trained language models to augment data, but this requires additional resources. We propose a novel solution by adequately leveraging the information within the task itself.
  arXiv  Detail & Related papers  (2024-10-14T12:47:11Z)
• Semi-Supervised Variational Adversarial Active Learning via Learning to Rank and Agreement-Based Pseudo Labeling [6.771578432805963]
  Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples. We introduce novel techniques that significantly improve the use of abundant unlabeled data during training. We demonstrate the superior performance of our approach over the state of the art on various image classification and segmentation benchmark datasets.
  arXiv  Detail & Related papers  (2024-08-23T00:35:07Z)
• Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels [63.16824565919966]
  This paper proposes to use confusing samples proactively without label correction. A Virtual Category (VC) is assigned to each confusing sample in such a way that it can safely contribute to the model optimisation. Our intriguing findings highlight the usage of VC learning in dense vision tasks.
  arXiv  Detail & Related papers  (2023-12-02T16:23:52Z)
• Multi-Label Knowledge Distillation [86.03990467785312]
  We propose a novel multi-label knowledge distillation method. On one hand, it exploits the informative semantic knowledge from the logits by dividing the multi-label learning problem into a set of binary classification problems. On the other hand, it enhances the distinctiveness of the learned feature representations by leveraging the structural information of label-wise embeddings.
  arXiv  Detail & Related papers  (2023-08-12T03:19:08Z)
• BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning [93.38239238988719]
  We propose to enable deep neural networks with the ability to learn the sample relationships from each mini-batch. BatchFormer is applied into the batch dimension of each mini-batch to implicitly explore sample relationships during training. We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications.
  arXiv  Detail & Related papers  (2022-03-03T05:31:33Z)
• Latent-Insensitive Autoencoders for Anomaly Detection and Class-Incremental Learning [0.0]
  We introduce Latent-Insensitive Autoencoder (LIS-AE) where unlabeled data from a similar domain is utilized as negative examples to shape the latent layer (bottleneck) of a regular autoencoder. We treat class-incremental learning as multiple anomaly detection tasks by adding a different latent layer for each class and use other available classes in task as negative examples to shape each latent layer.
  arXiv  Detail & Related papers  (2021-10-25T16:53:49Z)
• Learning with Different Amounts of Annotation: From Zero to Many Labels [19.869498599986006]
  Training NLP systems typically assume access to annotated data that has a single human label per example. We explore new annotation distribution schemes, assigning multiple labels per example for a small subset of training examples. Introducing such multi label examples at the cost of annotating fewer examples brings clear gains on natural language inference task and entity typing task.
  arXiv  Detail & Related papers  (2021-09-09T16:48:41Z)
• Dash: Semi-Supervised Learning with Dynamic Thresholding [72.74339790209531]
  We propose a semi-supervised learning (SSL) approach that uses unlabeled examples to train models. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection.
  arXiv  Detail & Related papers  (2021-09-01T23:52:29Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

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.