Erik Valle's repositories
Dantzig-Algorithm-for-Earth-Mover-s-Distance-Wasserstein-
Dantzig's algorithm for parameters initialization given the Earth Mover's Distance (Wasserstein distance) model
Automating-Workflows-with-GitHub-Actions
Automating Workflows with GitHub Actions, published by Packt
awesome-public-datasets
A topic-centric list of HQ open datasets.
clvision-challenge-2022
CVPR 2022 Continual Learning in Computer Vision Workshop Challenge
DAFormer
Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation [CVPR22]
dataset-api
The ApolloScape Open Dataset for Autonomous Driving and its Application.
Dynamic-Trajectory-Predictor
Repo for the paper 'Forecasting Pedestrian Trajectory with Machine-Annotated Training Data'. IV 2019
GitHubGraduation-2022
Join the GitHub Graduation Yearbook and "walk the stage" on June 11.
imbalanced-dataset-sampler
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
opencv-1
Open Source Computer Vision Library
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
SB-WBF
Consensus focus for object detection. Case I: Ensembling of multiple models.
SDR
PyTorch implementation of: Michieli U. and Zanuttigh P., "Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations", CVPR 2021.
SSDA-YOLO
Codes for my paper "SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection"
SST
Paper and Codes for “Embracing Single Stride 3D Object Detector with Sparse Transformer” (CVPR 2022)
StyleGAN-nada
Update to TF2
stylegan2-ada
StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation
Surface-Defect-Detection
📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.
SurroundDepth
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
Video-K-Net
Code for our CVPR-2022 work: Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
Weighted-Boxes-Fusion
Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.