Scott Jing's repositories
awesome-interpretable-transfer-learning
Paper and resources collections about interpretable AI (XAI)
AMF_GZS_SBIR
Implementation of AMF for GZS-SBIR
APN-ZSL
This is a PyTorch implementation of the paper "Attribute Prototype Network for Zero-Shot Learning".
Awesome-explainable-AI
A collection of research materials on explainable AI/ML
awesome-open-vocabulary-segmentation
A collection of AWESOME things about open-vocabulary segmentation
CDTrans
[ICLR2022] CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
Dynamic-Vision-Transformer
Accelerating T2t-ViT by 1.6-3.6x.
evidential-deep-learning
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!
LED2-Net
CVPR 2021 Oral paper "LED2-Net: Monocular 360Ëš Layout Estimation via Differentiable Depth Rendering" official PyTorch implementation.
LGT-Net
This is PyTorch implementation of our paper "LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network".(CVPR'22)
Machine-Learning-From-Scratch
Implementation of popular ML algorithms from scratch
mvit
Code Release for MViTv2 on Image Recognition.
pedestrian_intent_action_detection
Code for our paper "Coupling Intent and Action for Pedestrian Crossing Behavior Prediction"
ProtoProp
Code for the NeurIPS 2021 paper "Independent Prototype Propagation for Zero-Shot Compositionality"
scottjingtt.github.io
Scott's Homepage
SDAT
Source code for "A Closer Look at Smoothness in Domain Adversarial Training", ICML 2022
SHOT-plus
code for our paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"
STR-PIP
Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
TFKT
Implementation of TFKT - IEEE TIP
Training-for-the-Future
Official code release for the NeurIPS 2021 article Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time
TransDA
This is an official implementation for "Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation"
TVT
Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation