Pengchuan Zhang's Projects
Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(2020) paper
Blind source separation in a noisy environment using global optimization
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
Implementation for the CVPR2019 paper "Graphical Contrastive Losses for Scene Graph Generation"
[Arxiv2022] Egocentric Video-Language Pretraining
Portfolio Management Framework for risk and performance analysis 投资组合管理
A faster pytorch implementation of faster r-cnn
Pytorch code for our ECCV 2018 paper "Graph R-CNN for Scene Graph Generation" and other papers
heterogeneous treatment effect
Matlab code for the paper: https://arxiv.org/pdf/1607.00702.pdf
PyTorch implementation of Levenshtein Transformer
Longformer: The Long-Document Transformer
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2
Visualizer for neural network, deep learning and machine learning models
Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)
Oscar and VinVL
PyTorch tutorials demonstrating modern techniques with readable code
A beautiful, simple, clean, and responsive Jekyll theme for academics
Benchmark for LP-relaxed robustness verification of ReLU-networks
Statistical Adaptive Stochastic Optimization
A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).
Code for our NeurIPS 2019 spotlight "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"
Stable Diffusion web UI
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
visualize vision and vision-language data in tsv format