类增量学习(Class-Incremental Learning)领域部分经典论文汇总

2022.03.08 正在逐步完善补充中

只简单找了一小部分

CVPR
  • [link] [code] [iCaRL] [17]
    iCaRL: Incremental Classifier and Representation Learning

  • [link] [code] [BiC] [19]
    Large Scale Incremental Learning

  • [link] [code] [LUCIR] [19]
    Learning a Unified Classifier Incrementally via Rebalancing

  • [link] [code] [LwM] [19]
    Learning Without Memorizing

  • [link] [code] [Mnemonics] [20]
    Mnemonics Training: Multi-Class Incremental Learning Without Forgetting

  • [link] [code] [SDC] [20]
    Semantic Drift Compensation for Class-Incremental Learning

  • [link] [code] [WA] [20]
    Maintaining Discrimination and Fairness in Class Incremental Learning

  • [link] [code] [FSCIL] [20]
    Few-Shot Class-Incremental Learning

  • [link] [code] [AANet] [21]
    Adaptive Aggregation Networks for Class-Incremental Learning

  • [link] [code] [DDE] [21]
    Distilling Causal Effect of Data in Class-Incremental Learning

  • [link] [code] [DER] [21]
    DER: Dynamically Expandable Representation for Class Incremental Learning

  • [link] [code] [PASS] [21]
    Prototype Augmentation and Self-Supervision for Incremental Learning

  • [link] [code] [SPPR] [21]
    Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

  • [link] [code] [SAKD] [21]
    Semantic-Aware Knowledge Distillation for Few-Shot Class-Incremental Learning

  • [link] [code] [FCIL] [22]
    Federated Class-Incremental Learning

  • [link] [code] [FACT] [22]
    Forward Compatible Few-Shot Class-Incremental Learning

  • [link] [code] [NECIL] [22]
    Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

  • [link] [code] [SP] [22]
    Class-Incremental Learning with Strong Pre-trained Models

  • [link] [code] [AFC] [22]
    Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation

  • [link] [code] [C-FSCIL] [22]
    Constrained Few-shot Class-incremental Learning

  • [link] [code] [DIY-FSCIL] [22]
    Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches

  • [link] [code] [CwD] [22]
    Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning


ICCV
  • [link] [code] [IL2M] [19]
    IL2M: Class Incremental Learning With Dual Memory

  • [link] [code] [SPB] [21]
    Striking a Balance between Stability and Plasticity for Class-Incremental Learning

  • [link] [code] [DFCIL] [21]
    Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

  • [link] [code] [SS-IL] [21]
    SS-IL: Separated Softmax for Incremental Learning


ECCV
  • [link] [code] [LwF] [16]
    Learning without Forgetting

  • [link] [code] [EEIL] [18]
    End-to-End Incremental Learning

  • [link] [code] [TPCIL] [20]
    Topology-Preserving Class-Incremental Learning

  • [link] [code] [PODNet] [20]
    PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning

  • [link] [code] [R-DFCIL] [22]
    R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning


AAAI
  • [link] [code] [S&B] [21]
    Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network

  • [link] [code] [ASER] [21]
    Online Class-Incremental Continual Learning with Adversarial Shapley Value

  • [link] [code] [D-Collab] [21]
    DeepCollaboration: Collaborative Generative and Discriminative Models for Class Incremental Learning


MM
  • [link] [code] [COIL] [21]
    Co-Transport for Class-Incremental Learning

IJCAI
  • [link] [code] [KCCIOL] [21]
    Knowledge Consolidation based Class Incremental Online Learning with Limited Data

ACCV
  • [link] [code] [FGP] [20]
    Class-incremental Learning with Rectified Feature-Graph Preservation

BMVC
  • [link] [code] [ICWR] [20]
    Initial Classifier Weights Replay for Memoryless Class Incremental Learning

PNAS
  • [link] [code] [EWC] [17]
    Overcoming Catastrophic Forgetting in Neural Networks
  • 11
    点赞
  • 67
    收藏
    觉得还不错? 一键收藏
  • 7
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 7
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值