chameleonTK / continual-learning-for-HAR
A continual model for human activity recognition (called HAR-GAN). It is based on a technique called `generative replay` which two models (classifier and generator) are trainined in the same time to keep learning a new task but also retrain previously learned knwoledge.
☆18Updated 2 years ago
Alternatives and similar repositories for continual-learning-for-HAR:
Users that are interested in continual-learning-for-HAR are comparing it to the libraries listed below
- Source code for "Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data" (KDD 2020)☆54Updated 4 years ago
- Code repository for few-shot human activity recognition (FSHAR) in ESWA☆9Updated 5 years ago
- Code for our AAAI-2021 paper "Latent Independent Excitation for Generalizable Sensor-based Cross-Person Activity Recognition".☆37Updated 3 years ago
- Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition☆11Updated 2 years ago
- Improving Human Activity Recognition through Self-training with Unlabeled Data☆40Updated 3 years ago
- Benchmarking continual learning techniques for Human Activity Recognition data. We offer interesting insights on how the performance tech…☆51Updated last year
- Contrastive Learning (SimCLR) for Human Activity Recognition☆75Updated 3 years ago
- ☆60Updated 2 years ago
- A brain-inspired version of generative replay for continual learning with deep neural networks (e.g., class-incremental learning on CIFAR…☆234Updated last year
- Implementation of Contrastive Predictive Coding for Human Activity Recognition☆28Updated 2 years ago
- Demo code for the MDAN paper.☆122Updated 5 years ago
- Multiple Source Domain Adaptation with Adversarial Learning☆21Updated 4 years ago
- Source code for paper: UniTS: Short-Time Fourier Inspired Neural Networks for Sensory Time Series Classification☆19Updated 3 years ago
- This is the Pytorch implementation of LwF☆74Updated 3 months ago
- The source code and collected data for the Meta-HAR (WWW 2021) paper.☆32Updated 2 years ago
- PyTorch Implementation of iCaRL☆115Updated 5 years ago
- Implementation of Learning without Forgetting paper☆132Updated 4 years ago
- Continual Learning in Recurrent Neural Networks☆37Updated 3 years ago
- Offering recent HAR papers collection☆26Updated 3 years ago
- Unofficial PyTorch implementation of DeepMind's PNAS 2017 paper "Overcoming Catastrophic Forgetting"☆272Updated 8 months ago
- ☆98Updated 2 years ago
- COCOA: Cross Modality Contrastive Learning for Sensor Data☆25Updated 2 years ago
- ☆20Updated last year
- PyTorch implementation of DANN (Domain-Adversarial Training of Neural Networks)☆131Updated last year
- A Keras framework for Adversarial Domain Adaptation☆34Updated 4 years ago
- Evaluate three types of task shifting with popular continual learning algorithms.☆519Updated 3 years ago
- Code for Unsupervised Multi-Source Domain Adaptation for Regression paper☆17Updated 4 years ago
- An implementation of Deep Adaptation Network with pytorch☆111Updated 6 years ago
- Implementation of DANN with pytorch☆49Updated 5 years ago
- Contrastive Adversarial Learning for Multi-Source Time Series Domain Adaptation☆27Updated 3 years ago