Open-source alternatives to Audio Visual Forensics

This is an interactive notebook-based course that teaches machine learning from Python fundamentals through deep learning and natural language processing. It uses real datasets and multiple frameworks within a structured, hands-on curriculum that combines concise explanations with executable code cells, built-in datasets, and embedded exercise checkpoints. Learning progresses through data preparation and exploration, classical machine learning workflows, computer vision with convolutional neural networks, and natural language processing with deep learning, all delivered as a cohesive progressi

This is an educational curriculum for building and training neural networks using PyTorch. It serves as a deep learning training guide and resource, providing a structured series of lessons on tensor computation and architecture development. The course uses an interactive learning model that synchronizes academic theory with practice. It pairs theoretical lecture slides with exercise-driven notebooks, requiring students to implement model logic within predefined templates to validate their conceptual understanding. The curriculum covers a broad range of deep learning capabilities, including

TensorFlow Similarity is a Python framework designed for training neural networks to learn high-dimensional vector representations and perform similarity-based retrieval. It provides a comprehensive toolkit for metric learning, enabling the development of systems that group similar items together in vector space and identify them through distance-based comparisons. The library distinguishes itself by integrating specialized training techniques, such as contrastive and triplet-based learning, with robust data management tools that ensure stable model convergence. It supports self-supervised re

This is the code for MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification. An multiple-layer feature-matching generative adversarial networks (MARTA GANs) to learn a representation using only unlabeled data.

Change Point Detection techniques aim to capture changes in trends and sequences in time-series data to describe the underlying behaviour of the system. Detecting changes and anomalies in the web services, the trend of applications usage can provide valuable insights into the system. However,…

This repository contains the code for DABS, a benchmark for domain-agnostic self-supervised learning algorithms. The basic components of the benchmark can be found in datasets, encoders, and algorithms. Training is implemented with the PyTorch Lightning framework, logging with Weights and…

Beijing Jiaotong University, YanShan University, A*Star

This project is a PyTorch vision transformer framework designed for self-supervised learning. It implements a model that trains visual representations using a momentum teacher and self-distillation without the need for labeled data. The library functions as an image feature extractor and visual attention visualizer, allowing for the generation of high-dimensional vectors and the rendering of self-attention maps as heatmaps or videos to analyze model focus. It provides comprehensive tools for downstream vision evaluation, including linear probe classification, k-nearest neighbor categorizatio

This repository contains the Pytorch implementation of Representative Forgery Mining for Fake Face Detection. If you find our code useful in your research, please cite:

Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective •A new CVAE structure that using frequency as a condition. •Using global and local frequency information makes CVAE better reconstruct normal patterns.

KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networks (ICML2025)

Beijing Jiaotong University, YanShan University

This is the official code for a PyTorch implementation of Neural Transformation Learning reported in the paper Neural Transformation Learning for Deep Anomaly Detection Beyond Images by Chen Qiu et al. The paper is published in ICML 2021 and can be found here https://arxiv.org/abs/2103.16440.…

This code is the official PyTorch implementation of our NeurIPS'25 Paper: CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling.

中文文档

Figure 1. Two different strategies for localizing temporal anomalies.

RANSynCoders (or RANCoders) is an unsupervised deep learning architecture for real-time anomaly detection and localizaiton within large multivariate time series. The method utilizes synchrony-analysis on latent representations for adjusting asynchronous variates fed into an encoder, bootstrap…

Offical implementation of "Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series" (ICLR 2022). [paper](https://openreview.net/pdf?id=45L_dgP48Vd)

Exathlon

This repository contains derived datasets, implementation of methods experimented and introduced in the paper titled "NSF-MAP: Neurosymbolic Multimodal Fusion for Robust and Interpretable Anomaly Prediction in Assembly Pipelines".

Source code of CIKM'22 paper: TFAD: A Decomposition Time Series Anomaly Detection Architecture with Frequency Analysis Chaoli Zhang, Tian Zhou, Qingsong Wen, Liang Sun, "TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Freq Analysis,” in Proc. 31st ACM International…

This is a PyTorch library and framework for self-supervised vision learning. It provides an implementation of masked autoencoders and vision transformers designed to learn image representations by reconstructing masked image patches from unlabeled data. The project features a distributed training pipeline that scales workloads across multiple GPU nodes. This infrastructure includes multi-node orchestration and gradient accumulation to manage large batch sizes and coordinate resource requests across clusters. The toolkit covers a complete workflow from self-supervised masked pre-training to d

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Landmark Recurrent Network: An efficient and robust framwork for Deepfakes detection

Davide Cozzolino, Andreas Rössler, Justus Thies, Matthias Nießner, Luisa Verdoliva

Code implementation for : Graph Neural Network-Based Anomaly Detection in Multivariate Time Series(AAAI'21)