This is a official repository of SimViT.

Last update: Dec 15, 2022

Related tags

Overview

SimViT

This is a official repository of SimViT. We will open our models and codes about object detection and semantic segmentation soon. Our code references the PVT, thanks a lot for their outstanding work!

For details see SimViT: Exploring a Simple Vision Transformer with sliding windows.

Citation

If you use this code for a paper, please cite:

SimViT

@misc{li2021simvit,
      title={SimViT: Exploring a Simple Vision Transformer with sliding windows}, 
      author={Gang Li and Di Xu and Xing Cheng and Lingyu Si and Changwen Zheng},
      year={2021},
      eprint={2112.13085},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Contact

This repo is currently maintained by Gang Li(@ucasligang) and Di Xu(@HanielF).

Owner

ligang

I am a Ph.D student from the University of Chinese Academy of Science (UCAS), studying computer vision, especially self-supervised learning.

GitHub Repository

An open source library for face detection in images. The face detection speed can reach 1000FPS.

libfacedetection This is an open source library for CNN-based face detection in images. The CNN model has been converted to static variables in C sour

11.4k Dec 27, 2022

Deploy recommendation engines with Edge Computing

RecoEdge: Bringing Recommendations to the Edge A one stop solution to build your recommendation models, train them and, deploy them in a privacy prese

131 Jan 02, 2023

Towards the D-Optimal Online Experiment Design for Recommender Selection (KDD 2021)

Towards the D-Optimal Online Experiment Design for Recommender Selection (KDD 2021) Contact 0 Jan 11, 2022

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

3k Dec 26, 2022

PartImageNet is a large, high-quality dataset with part segmentation annotations

PartImageNet: A Large, High-Quality Dataset of Parts We will release our dataset and scripts soon after cleaning and approval. Introduction PartImageN

77 Nov 30, 2022

Models Supported: AlbUNet [18, 34, 50, 101, 152] (1D and 2D versions for Single and Multiclass Segmentation, Feature Extraction with supports for Deep Supervision and Guided Attention)

AlbUNet-1D-2D-Tensorflow-Keras This repository contains 1D and 2D Signal Segmentation Model Builder for AlbUNet and several of its variants developed

1 Nov 15, 2021

CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation

CDGAN CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation CDGAN Implementation in PyTorch This is the imple

6 Apr 19, 2022

Distributionally robust neural networks for group shifts

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization This code implements the g

151 Dec 25, 2022

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

News December 27: v1.1.0 New loss functions: CentroidTripletLoss and VICRegLoss Mean reciprocal rank + per-class accuracies See the release notes Than

5k Jan 05, 2023

CLIPImageClassifier wraps clip image model from transformers

CLIPImageClassifier CLIPImageClassifier wraps clip image model from transformers. CLIPImageClassifier is initialized with the argument classes, these

6 Sep 12, 2022

This repository contains code for the paper "Disentangling Label Distribution for Long-tailed Visual Recognition", published at CVPR' 2021

Disentangling Label Distribution for Long-tailed Visual Recognition (CVPR 2021) Arxiv link Blog post This codebase is built on Causal Norm. Install co

85 Oct 18, 2022

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.

Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning Overview This code is for paper: Not All Unlabeled Data are Equa

22 Nov 23, 2022

This is a official repository of SimViT.

Related tags

Overview

SimViT

Citation

Contact

Owner

ligang

An open source library for face detection in images. The face detection speed can reach 1000FPS.

Deploy recommendation engines with Edge Computing

Towards the D-Optimal Online Experiment Design for Recommender Selection (KDD 2021)

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

PartImageNet is a large, high-quality dataset with part segmentation annotations

Models Supported: AlbUNet [18, 34, 50, 101, 152] (1D and 2D versions for Single and Multiclass Segmentation, Feature Extraction with supports for Deep Supervision and Guided Attention)

CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation

Distributionally robust neural networks for group shifts

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

CLIPImageClassifier wraps clip image model from transformers

This repository contains code for the paper "Disentangling Label Distribution for Long-tailed Visual Recognition", published at CVPR' 2021

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.

UI2I via StyleGAN2 - Unsupervised image-to-image translation method via pre-trained StyleGAN2 network

Log4j JNDI inj. vuln scanner

FG-transformer-TTS Fine-grained style control in transformer-based text-to-speech synthesis

Repository for self-supervised landmark discovery

Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Code for reproducing experiments in "Improved Training of Wasserstein GANs"

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

This is a official repository of SimViT.

Related tags

Overview

SimViT

Citation

Contact

Owner

ligang

An open source library for face detection in images. The face detection speed can reach 1000FPS.

Deploy recommendation engines with Edge Computing

Towards the D-Optimal Online Experiment Design for Recommender Selection (KDD 2021)

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

PartImageNet is a large, high-quality dataset with part segmentation annotations

Models Supported: AlbUNet [18, 34, 50, 101, 152] (1D and 2D versions for Single and Multiclass Segmentation, Feature Extraction with supports for Deep Supervision and Guided Attention)

CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation

Distributionally robust neural networks for group shifts

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

CLIPImageClassifier wraps clip image model from transformers

This repository contains code for the paper "Disentangling Label Distribution for Long-tailed Visual Recognition", published at CVPR' 2021

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing.

UI2I via StyleGAN2 - Unsupervised image-to-image translation method via pre-trained StyleGAN2 network

Log4j JNDI inj. vuln scanner

FG-transformer-TTS Fine-grained style control in transformer-based text-to-speech synthesis

Repository for self-supervised landmark discovery

Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Code for reproducing experiments in "Improved Training of Wasserstein GANs"

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.