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 last year
Related projects: ⓘ
- Source code for "Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data" (KDD 2020)☆52Updated 3 years ago
- Code repository for few-shot human activity recognition (FSHAR) in ESWA☆9Updated 4 years ago
- Contrastive Learning (SimCLR) for Human Activity Recognition☆69Updated 3 years ago
- Source code for paper: UniTS: Short-Time Fourier Inspired Neural Networks for Sensory Time Series Classification☆19Updated 2 years ago
- Code for the paper "Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptation", Buffelli D., Vandin F.,…☆15Updated 2 years ago
- Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition☆11Updated last year
- Code for our AAAI-2021 paper "Latent Independent Excitation for Generalizable Sensor-based Cross-Person Activity Recognition".☆33Updated 2 years ago
- [TKDD 2023] AdaTime: A Benchmarking Suite for Domain Adaptation on Time Series Data☆176Updated last year
- ☆53Updated last year
- ☆21Updated 11 months ago
- A curated list of time series augmentation resources.☆64Updated 2 years ago
- DANN in TensorFlow 2.0☆43Updated 2 years ago
- Code for our paper Self Supervised Learning for Semi Supervised Time Series Classification PAKDD 2020☆16Updated 4 years ago
- Improving Human Activity Recognition through Self-training with Unlabeled Data☆35Updated 3 years ago
- Implementation of Contrastive Predictive Coding for Human Activity Recognition☆25Updated 2 years ago
- ☆34Updated 9 months ago
- Attend and Discriminate: Beyond the State-of-the-Art for Human Activity Recognition Using Wearable Sensors☆22Updated 3 years ago
- Encoding human activity by considering salient sensors and time points.☆40Updated last year
- ResNet-1D and Variable Length Pooling for time series data like speech☆33Updated 5 years ago
- A simple implementation of domain adversarial training with GAN loss in Keras☆59Updated 6 years ago
- TTS-CGAN: A Transformer Time-Series Conditional GAN for Biosignal Data Augmentation☆68Updated last year
- ☆83Updated this week
- Code for "ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System"☆14Updated 5 years ago
- Data augmentation for multivariate time series classification☆24Updated 5 years ago
- A Keras framework for Adversarial Domain Adaptation☆34Updated 4 years ago
- Variational Adversarial Deep Domain Adaptation implementation (TensorFlow 1.x)☆10Updated 5 years ago
- PyTorch implementation of DANN (Domain-Adversarial Training of Neural Networks)☆119Updated 9 months ago
- Domain-Adaptive Recurrent Neural Network for driving manoeuver anticipation, built in Keras☆33Updated 5 years ago
- ☆136Updated last year
- pytorch code of multi scale 1d resnet, we hope it will help your research☆212Updated 3 years ago