📚 Supported Methods

🌱 Class-Incremental Learning

CNN-based methods

  • Joint: update models using all the data from all classes.
  • Finetune: baseline method which simply updates model using current data.
  • LwF: Learning without Forgetting. ECCV 2016 [paper]
  • EWC: Overcoming catastrophic forgetting in neural networks. PNAS 2017 [paper]
  • iCaRL: Incremental Classifier and Representation Learning. CVPR 2017 [paper]
  • BiC: Large Scale Incremental Learning. CVPR 2019 [paper]
  • WA: Maintaining Discrimination and Fairness in Class Incremental Learning. CVPR 2020 [paper]
  • DER: Dynamically Expandable Representation for Class Incremental Learning. CVPR 2021 [paper]
  • Coil: Co-Transport for Class-Incremental Learning. ACM MM 2021 [paper]
  • GEM: Gradient Episodic Memory for Continual Learning. NIPS 2017 [paper]
  • SSRE: Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning. CVPR 2022 [paper]
  • FOSTER: Feature Boosting and Compression for Class-incremental Learning. ECCV 2022 [paper]
  • FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning. WACV 2023 [paper]
  • MEMO: Memory-Efficient Class-Incremental Learning. ICLR 2023 [paper]

ViT-based methods

  • Joint: update models using all the data from all classes.

Few-shot class-incremental learning

  • Alice: Few-Shot Class-Incremental Learning from an Open-Set Perspective. ECCV 2022 [paper]
  • FACT: Forward Compatible Few-Shot Class-Incremental Learning. CVPR 2022 [paper]
  • SAVC: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning. CVPR 2023 [paper]

🚨 Out-of-Distribution Detection

CNN-based Methods

  • MSP: A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. ICLR 2017 [paper]
  • ODIN: Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks. ICLR 2018 [paper]
  • MDS: A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. NeurIPS 2018 [paper]
  • MLS: Scaling Out-of-Distribution Detection for Real-World Settings. ICML 2022 [paper]
  • ViM: Out-Of-Distribution with Virtual-logit Matching. CVPR 2022 [paper]
  • FDBD: Fast Decision Boundary based Out-of-Distribution Detector. ICML 2024 [paper]
  • VOS: Learning What You Don't Know by Virtual Outlier Synthesis. ICLR 2022 [paper]
  • LogitNorm: Mitigating Neural Network Overconfidence with Logit Normalization. ICML 2022 [paper]
  • DML: Decoupling MaxLogit for Out-of-Distribution Detection. CVPR 2023 [paper]

CLIP-based Methods

  • MCM: Delving into Out-of-Distribution Detection with Vision-Language Representations. NeurIPS 2022 [paper]
  • GLMCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection. IJCV 2025 [paper]
  • CoOp: Learning to Prompt for Vision-Language Models. IJCV 2022 [paper]
  • LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning. NeurIPS 2023 [paper]
  • SCT: Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection. NeurIPS 2024 [paper]
  • DPM: Vision-Language Dual-Pattern Matching for Out-of-Distribution Detection. ECCV 2024 [paper]

🔍 Novel Class Discovery

TBD

🧬 Data Augmentation

TBD