Code for the paper "On the importance of cross-task features for class-incremental learning"
MIT License
Implementation of Open-Set Likelihood Maximization for Few-Shot Learning
Codebase for Continual Prototype Evolution (CoPE) to attain perpetually representative prototypes...
SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]
Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
GLM (General Language Model)
Official repository of ”Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-...
A simple method to perform semi-supervised learning with limited data.
Official repository for the paper "Self-Supervised Models are Continual Learners" (CVPR 2022)
Code for "A Comprehensive Empirical Evaluation on Online Continual Learning" ICCVW 2023 VCL Workshop
Official implementation of "A Unified Objective for Novel Class Discovery", ICCV2021 (Oral)
A large-scale benchmark and learning environment.
Continual Hyperparameter Selection Framework. Compares 11 state-of-the-art Lifelong Learning meth...
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 basel...
PyTorch codes for "Iterative Token Evaluation and Refinement for Real-World Super-Resolution", AA...
Pytorch code of for our CVPR 2018 paper "Neural Baby Talk"