Pengchuan Zhang's repositories
Intrinsic-sparse-mode-decomposition
Matlab code for the paper: https://arxiv.org/pdf/1607.00702.pdf
faster-rcnn.pytorch
A faster pytorch implementation of faster r-cnn
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
ASL
Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(2020) paper
ContrastiveLosses4VRD
Implementation for the CVPR2019 paper "Graphical Contrastive Losses for Scene Graph Generation"
EgoVLP
[Arxiv2022] Egocentric Video-Language Pretraining
graph-rcnn.pytorch
Pytorch code for our ECCV 2018 paper "Graph R-CNN for Scene Graph Generation" and other papers
levenshtein_transformer
PyTorch implementation of Levenshtein Transformer
longformer
Longformer: The Long-Document Transformer
MiniGPT-4
Open-sourced codes for MiniGPT-4 and MiniGPT-v2
netron
Visualizer for neural network, deep learning and machine learning models
neural-motifs
Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)
Oscar
Oscar and VinVL
pzzhang
A beautiful, simple, clean, and responsive Jekyll theme for academics
robust-verify-benchmark
Benchmark for LP-relaxed robustness verification of ReLU-networks
SceneGraphParser_SpaCy
A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).
smoothing-adversarial
Code for our NeurIPS 2019 spotlight "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"
stable-diffusion-webui
Stable Diffusion web UI
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
understanding-momentum
Code for the paper "Understanding the Role of Momentum in Stochastic Gradient Methods"
VILLA
Research Code for NeurIPS 2020 Spotlight paper "Large-Scale Adversarial Training for Vision-and-Language Representation Learning": UNITER adversarial training part
ViP-LLaVA
[CVPR2024] ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts