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

High-fidelity 3D Model Compression based on Key Spheres

Self-Supervised Image Denoising via Iterative Data Refinement

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation (ICCV 2021)

Sharpness-Aware Minimization for Efficiently Improving Generalization

Create Data & AI apps in 20 lines of code with Shimoku

Implementation of the ALPHAMEPOL algorithm, presented in Unsupervised Reinforcement Learning in Multiple Environments.

Set of models for classifcation of 3D volumes

Coursera - Quiz & Assignment of Coursera

A pre-trained language model for social media text in Spanish

Action Recognition for Self-Driving Cars

The Official Repository for "Generalized OOD Detection: A Survey"

NEG loss implemented in pytorch

Simple reference implementation of GraphSAGE.

CVPR2022 paper "Dense Learning based Semi-Supervised Object Detection"

Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image

Deep Anomaly Detection with Outlier Exposure (ICLR 2019)

MMFlow is an open source optical flow toolbox based on PyTorch

A model which classifies reviews as positive or negative.

Benchmark spaces - Benchmarks of how well different two dimensional spaces work for clustering algorithms

Text2Art is an AI art generator powered with VQGAN + CLIP and CLIPDrawer models