ExCon: Explanation-driven Supervised Contrastive Learning

Link to the paper: https://arxiv.org/pdf/2111.14271.pdf

Contributors of this repo:

Zhibo Zhang ([email protected])
Jongseong Jang ([email protected])
Ruiwen Li ([email protected])

Run ExCon:

python3 ExCon/main_supcon.py --epochs=200 --explainer="GradCAM" --dataset="cifar100" --batch_size=256 --method="Ex_SupCon" --learning_rate=0.5 --temp=0.1 --cosine --negative_pair=1 --validation=1 --background_anchor=0 --exp_epochs=0

If you use our code, please cite our paper:

@misc{zhang2021excon,
      title={ExCon: Explanation-driven Supervised Contrastive Learning for Image Classification},
      author={Zhibo Zhang and Jongseong Jang and Chiheb Trabelsi and Ruiwen Li and Scott Sanner and Yeonjeong Jeong and Dongsub Shim},
      year={2021},
      eprint={2111.14271},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Reference Repos:

[1] https://github.com/HobbitLong/SupContrast

ExCon: Explanation-driven Supervised Contrastive Learning

Related tags

Overview

ExCon: Explanation-driven Supervised Contrastive Learning

Link to the paper: https://arxiv.org/pdf/2111.14271.pdf

Contributors of this repo:

Run ExCon:

Reference Repos:

Owner

Zhibo (Darren) Zhang

BridgeGAN - Tensorflow implementation of Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation.

A PyTorch Toolbox for Face Recognition

For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training.

NeWT: Natural World Tasks

This repository builds a basic vision transformer from scratch so that one beginner can understand the theory of vision transformer.

Deep Learning (with PyTorch)

A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK

Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

Torchreid: Deep learning person re-identification in PyTorch.

[CVPR 2021] MiVOS - Scribble to Mask module

Dados coletados e programas desenvolvidos no processo de iniciação científica

Codebase for Image Classification Research, written in PyTorch.

Codes for realizing theories learned from Data Mining, Machine Learning, Deep Learning without using the present Python packages.

A command line simple note taking app

A novel Engagement Detection with Multi-Task Training (ED-MTT) system

This repo provides a demo for the CVPR 2021 paper "A Fourier-based Framework for Domain Generalization" on the PACS dataset.

Trainable PyTorch reproduction of AlphaFold 2

Official TensorFlow code for the forthcoming paper

RuDOLPH: One Hyper-Modal Transformer can be creative as DALL-E and smart as CLIP

Local Multi-Head Channel Self-Attention for FER2013