Open-source alternatives to TransMix

Paper published at ICML22. Link to our paper: https://icml.cc/virtual/2022/spotlight/18038

ROCKET · MINIROCKET · HYDRA

by Mutian Xu, Runyu Ding, Hengshuang Zhao, and Xiaojuan Qi.

:construction: WIP :construction:

This is the author code of "Learnable Dynamic Temporal Pooling for Time Series Classification" (AAAI 2021). - We employ (and customize) the fast CUDA implementation of soft-dtw (based on pytorch), publicly available at https://github.com/Maghoumi/pytorch-softdtw-cuda. - For more details of…

This code provides a PyTorch implementation and pretrained models for DepthContrast, as described in the paper Self-Supervised Pretraining of 3D Features on any Point-Cloud.

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

Fairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning. The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ

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

Code release for SLIP Self-supervision meets Language-Image Pre-training