-
Xiamen University
- Xiamen, Fujian, China
Stars
Datasets, Transforms and Models specific to Computer Vision
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
A faster pytorch implementation of faster r-cnn
Minimal PyTorch implementation of YOLOv3
Count the MACs / FLOPs of your PyTorch model.
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
Collection of generative models in Pytorch version.
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
A PyTorch implementation of MobileNet V2 architecture and pretrained model.
Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
PyTorch DataLoaders implemented with DALI for accelerating image preprocessing
Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.
[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning. In ICCV 2019.
torchsummaryX: Improved visualization tool of torchsummary
Semi-supervised Domain Adaptation via Minimax Entropy
Pytorch implementation of our paper accepted by CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map
[ECCV2020] Knowledge Distillation Meets Self-Supervision
Global Reasoning module for visual recognition
PyTorch implementation for Convolutional Networks with Adaptive Inference Graphs
An extension version of our paper accepted by CVPR 2020, Oral -- HRank: Filter Pruning using High-Rank Feature Map
Pytorch implementation of our paper accepted by IJCAI 2020 -- Channel Pruning via Automatic Structure Search
ResNet with Shift, Depthwise, or Convolutional Operations for CIFAR-100, CIFAR-10 on PyTorch
Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation