Stars
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Semantic Segmentation Architectures Implemented in PyTorch
DeepLab v3+ model in PyTorch. Support different backbones.
Implementation of Convolutional LSTM in PyTorch.
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
Code for our CVPR2021 paper coordinate attention
alfred-py: A deep learning utility library for **human**, more detail about the usage of lib to: https://zhuanlan.zhihu.com/p/341446046
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
a reimplementation of Holistically-Nested Edge Detection in PyTorch
Video Object Segmentation using Space-Time Memory Networks
The official PyTorch implementation of CVPR 2020 paper "Improving Convolutional Networks with Self-Calibrated Convolutions"
EGNet:Edge Guidance Network for Salient Object Detection (ICCV 2019)
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision (CVPR 2020 Oral)
MAST: A Memory-Augmented Self-supervised Tracker (CVPR 2020)
(IJCV 2024 & ECCV 2020 Oral) Towards Diverse Binary Segmentation via A Simple yet General Gated Network
Temporally Distributed Networks for Fast Video Semantic Segmentation
Motion-Attentive Transition for Zero-Shot Video Object Segmentation (AAAI2020&TIP2021)
PyTorch implementation of the CVPR 2019 paper “Pyramid Feature Attention Network for Saliency Detection”
🎨 Automatic Image Colorization using TensorFlow based on Residual Encoder Network
a transductive approach for video object segmentation
Motion Guided Attention for Video Salient Object Detection, ICCV 2019
Codes for the CVPR2020 paper "Label Decoupling Framework for Salient Object Detection"
training script for space time memory network
Anchor Diffusion for Unsupervised Video Object Segmentation
