Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

Official PyTorch implementation of "Learning a Neural Solver for Multiple Object Tracking" (CVPR 2020 Oral).

Unofficial PyTorch implementation of "Learning a Neural Solver for Multiple Object Tracking"

Source codes for the paper "Learning Diverse Features with Part-Level Resolution for Person Re-Identification"

TrackR-CNN baseline method for Multi-Object Tracking and Segmentation (MOTS)

[ICCV 2019] "ABD-Net: Attentive but Diverse Person Re-Identification" https://arxiv.org/abs/1908.01114

Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Code for "Deep Snake for Real-Time Instance Segmentation" CVPR 2020 oral

The code for the CVPR2019 paper Bi-Directional Cascade Network for Perceptual Edge Detection

Deforming kernels to adapt towards object deformation. In ICLR 2020.

Learning Unsupervised Video Object Segmentation through Visual Attention (CVPR19, PAMI20)

See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks (CVPR19)

Source code for "On the Relationship between Self-Attention and Convolutional Layers"

Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

[WACV 2020] DeOccNet: Learning to See Through Foreground Occlusions in Light Fields

A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.

Models and examples built with TensorFlow

⏰ AI conference deadline countdowns

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

Implementation of NeurIPS 2019 paper "Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior"

Torchreid: Deep learning person re-identification in PyTorch.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

SoftTriple (ICCV2019) in pytorch