DER: Dynamically Expandable Representation for Class Incremental Learning

• URL: http://arxiv.org/abs/2103.16788v1
• Date: Wed, 31 Mar 2021 03:16:44 GMT
• Title: DER: Dynamically Expandable Representation for Class Incremental Learning
• Authors: Shipeng Yan, Jiangwei Xie, Xuming He
• Abstract summary: We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence. We propose a novel two-stage learning approach that utilizes a dynamically expandable representation for more effective incremental concept modeling. We conduct extensive experiments on the three class incremental learning benchmarks and our method consistently outperforms other methods with a large margin.
• Score: 30.573653645134524
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence. In particular, we consider the task setting of incremental learning with limited memory and aim to achieve better stability-plasticity trade-off. To this end, we propose a novel two-stage learning approach that utilizes a dynamically expandable representation for more effective incremental concept modeling. Specifically, at each incremental step, we freeze the previously learned representation and augment it with additional feature dimensions from a new learnable feature extractor. This enables us to integrate new visual concepts with retaining learned knowledge. We dynamically expand the representation according to the complexity of novel concepts by introducing a channel-level mask-based pruning strategy. Moreover, we introduce an auxiliary loss to encourage the model to learn diverse and discriminate features for novel concepts. We conduct extensive experiments on the three class incremental learning benchmarks and our method consistently outperforms other methods with a large margin.

Related papers

• Latent-Predictive Empowerment: Measuring Empowerment without a Simulator [56.53777237504011]
  We present Latent-Predictive Empowerment (LPE), an algorithm that can compute empowerment in a more practical manner. LPE learns large skillsets by maximizing an objective that is a principled replacement for the mutual information between skills and states.
  arXiv  Detail & Related papers  (2024-10-15T00:41:18Z)
• Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillation [48.071162716120334]
  We study how the multimodal nature of the input affects the learning dynamics of a model. Motivated by this observation, we propose a modality-aware feature distillation (MAFED) approach.
  arXiv  Detail & Related papers  (2024-06-27T16:12:57Z)
• Mitigating Forgetting in Online Continual Learning via Contrasting Semantically Distinct Augmentations [22.289830907729705]
  Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one. Main challenge comes from the "catastrophic forgetting" issue -- the inability to well remember the learnt knowledge while learning the new ones.
  arXiv  Detail & Related papers  (2022-11-10T05:29:43Z)
• Anti-Retroactive Interference for Lifelong Learning [65.50683752919089]
  We design a paradigm for lifelong learning based on meta-learning and associative mechanism of the brain. It tackles the problem from two aspects: extracting knowledge and memorizing knowledge. It is theoretically analyzed that the proposed learning paradigm can make the models of different tasks converge to the same optimum.
  arXiv  Detail & Related papers  (2022-08-27T09:27:36Z)
• FOSTER: Feature Boosting and Compression for Class-Incremental Learning [52.603520403933985]
  Deep neural networks suffer from catastrophic forgetting when learning new categories. We propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively.
  arXiv  Detail & Related papers  (2022-04-10T11:38:33Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)
• Continual Representation Learning for Biometric Identification [47.15075374158398]
  We propose a new continual learning (CL) setting, namely continual representation learning'', which focuses on learning better representation in a continuous way. We demonstrate that existing CL methods can improve the representation in the new setting, and our method achieves better results than the competitors.
  arXiv  Detail & Related papers  (2020-06-08T10:18:06Z)
• Progressive Learning and Disentanglement of Hierarchical Representations [10.201945347770643]
  We present a strategy to progressively learn independent hierarchical representations from high- to low-levels of abstractions. We quantitatively demonstrate the ability of the presented model to improve disentanglement in comparison to existing works.
  arXiv  Detail & Related papers  (2020-02-24T21:19:38Z)

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.