rahafaljundi / Expert-Gate
We introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process, data from previous tasks cannot be stored and hence is not available when learning a new task. A critical issue in such context,…
☆11Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for Expert-Gate
- Generative Feature Replay For Class-Incremental Learning☆36Updated 4 years ago
- Overcoming Catastrophic Forgetting by Incremental Moment Matching (IMM)☆34Updated 6 years ago
- Code for Paper "Incremental Few-Shot Learning with Attention Attractor Networks"☆119Updated 4 years ago
- ICCV 2019 Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild☆79Updated last year
- Pytorch implementation of ACCV18 paper "Revisiting Distillation and Incremental Classifier Learning."☆107Updated 4 months ago
- Codebase for "Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning". This is a ServiceNow Research pro…☆103Updated 2 years ago
- ☆53Updated 5 years ago
- The rep for the RotateNetworks in ICPR18, Beijing, China.☆33Updated 6 years ago
- pytorch implementation of Large Scale Incremental Learning☆64Updated 4 years ago
- Memory Aware Synapses method implementation code☆94Updated 6 years ago
- PyTorch implementation of AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs☆24Updated last year
- Lifelong Learning with Dynamically Expandable Networks☆20Updated 6 years ago
- AR1* with Latent Replay, implemented in PyTorch☆31Updated 4 years ago
- Implementation of Bayesian Gradient Descent☆37Updated last year
- ☆16Updated 6 years ago
- A pytorch compatible data loader to create sequence of tasks for Continual Learning☆33Updated 4 years ago
- Code to accompany our paper "Continual Learning Through Synaptic Intelligence" ICML 2017☆98Updated 6 years ago
- ☆71Updated last year
- PyTorch implementation of "Continual Learning with Deep Generative Replay", NIPS 2017☆156Updated 7 years ago
- Official implementation of "iTAML : An Incremental Task-Agnostic Meta-learning Approach". CVPR 2020☆95Updated last year
- Official code for ICLR 2020 paper "A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning."☆98Updated 4 years ago
- (NeurIPS 2020) Meta-Consolidation for Continual Learning☆36Updated 3 years ago
- Official implementation of the Averaged Gradient Episodic Memory (A-GEM) in Tensorflow☆201Updated 3 years ago
- DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks https://arxiv.org/abs/1901.09229☆66Updated 3 years ago
- PyTorch code for NeurIPSW 2020 paper (4th Workshop on Meta-Learning) "Few-Shot Unsupervised Continual Learning through Meta-Examples"☆20Updated 4 years ago
- ☆44Updated 6 years ago
- Codebase for "Online Continual Learning with Maximally Interfered Retrieval"☆99Updated last year
- Official Implementation of "Random Path Selection for Incremental Learning" paper. NeurIPS 2019☆53Updated last year
- ☆70Updated 4 years ago
- Semantic Drift Compensation for Class-Incremental Learning (CVPR2020)☆118Updated 4 years ago