UVO_Challenge

Team Alpes_runner Solutions

This is an official repo for our UVO Challenge solutions for Image/Video-based open-world segmentation. Our team "Alpes_runner" achieved the best performance on both Image/Video-based benchmarks. More details about the workshop can be found here.

Technical Reports

For Track 1: paper
For Track 2: paper

Models

Detection

Model	Pretrained datasets	Finetuned datasets	links
UVO_Detector	COCO	-	config/weights
UVO_Detector	COCO	UVO	config/weights

Segmentation

Model	Pretrained datasets	Finetuned datasets	links
UVO_Segementor	COCO	-	weights
UVO_Segmentor	COCO, PASCAL, OpenImage	-	config/weights
UVO_Segmentor	COCO, PASCAL, OpenImage	UVO	config/weights

Citation

If you find this project useful in your research, please consider cite:

@article{du20211st,
  title={1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021},
  author={Du, Yuming and Guo, Wen and Xiao, Yang and Lepetit, Vincent},
  journal={arXiv preprint arXiv:2110.10239},
  year={2021}
}

@article{du20211st,
  title={1st Place Solution for the UVO Challenge on Video-based Open-World Segmentation 2021},
  author={Du, Yuming and Guo, Wen and Xiao, Yang and Lepetit, Vincent},
  journal={arXiv preprint arXiv:2110.11661},
  year={2021}
}

Contact

Feel free to contact me or open a new issue if you have any questions.

Video-based open-world segmentation

Related tags

Overview

UVO_Challenge

Team Alpes_runner Solutions

Technical Reports

Models

Citation

Contact

Owner

Yuming Du

Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...

Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

🏆 The 1st Place Submission to AICity Challenge 2021 Natural Language-Based Vehicle Retrieval Track (Alibaba-UTS submission)

Listing arxiv - Personalized list of today's articles from ArXiv

Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions

Weighted K Nearest Neighbors (kNN) algorithm implemented on python from scratch.

Implement some metaheuristics and cost functions

The Unsupervised Reinforcement Learning Benchmark (URLB)

Source for the paper "Universal Activation Function for machine learning"

Dynamic Graph Event Detection

Understanding the Effects of Datasets Characteristics on Offline Reinforcement Learning

Hyperbolic Hierarchical Clustering.

Deep Learning to Create StepMania SM FIles

Parametric Contrastive Learning (ICCV2021)

Transferable Unrestricted Attacks, which won 1st place in CVPR’21 Security AI Challenger: Unrestricted Adversarial Attacks on ImageNet.

Application of K-means algorithm on a music dataset after a dimensionality reduction with PCA

An image processing project uses Viola-jones technique to detect faces and then use SIFT algorithm for recognition.

Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning

Non-stationary GP package written from scratch in PyTorch