code for SSH
@article{jiang2021ssh,
title={SSH: A Self-Supervised Framework for Image Harmonization},
author={Jiang, Yifan and Zhang, He and Zhang, Jianming and Wang, Yilin and Lin, Zhe and Sunkavalli, Kalyan and Chen, Simon and Amirghodsi, Sohrab and Kong, Sarah and Wang, Zhangyang},
journal={arXiv preprint arXiv:2108.06805},
year={2021}
}
great work!!! I have a question about the LUTs: "Given one input image, there exist hundreds of LUTs that can be applied to generate its stylized versions and dramatically enrich the training data", is that mean, there are "hundreds of LUTs" templates for you to process the images during the training phase? if yes, where can I get these LUTs? thanks a lot.
Hello.
In the supplementary material, I would like to ask why the input channel of the content network is 4 , is it adding mask in addition to the picture input of three channels? If so, why the input channel of reference network is three channels without mask channel?
Nice work. Would you mind providing training datasets, or sharing the method and details in the collection process?
Looking forward to your reply, thanks.
Hi, I've tried to run demo but it doesn't work.
It seems there is no requirements.txt in this repository, could you please add?
Also there is no colour_checker_detection directory in this folder.
Thanks!
Hi, I encounter "opt" not defined problem. I can't find where opt is declared. And the class OPT is empty. Does that mean user have to define their own OPT ?
Chasing Sparsity in Vision Transformers: An End-to-End Exploration Codes for [Preprint] Chasing Sparsity in Vision Transformers: An End-to-End Explora
Self-Damaging Contrastive Learning Introduction The recent breakthrough achieved by contrastive learning accelerates the pace for deploying unsupervis
BNN - BN = ? Training Binary Neural Networks without Batch Normalization Codes for this paper BNN - BN = ? Training Binary Neural Networks without Bat
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models Codes for this paper The Lottery Tickets Hypo
The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy Codes for this paper: [CVPR 2022] The Pr
Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study Codes for [Preprint] Bag of Tricks for Training Deeper Graph
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective [PDF] Wuyang Chen, Xinyu Gong, Zhangyang Wang In ICLR 2
Undistillable: Making A Nasty Teacher That CANNOT teach students "Undistillable: Making A Nasty Teacher That CANNOT teach students" Haoyu Ma, Tianlong
Graph Contrastive Learning Automated PyTorch implementation for Graph Contrastive Learning Automated [talk] [poster] [appendix] Yuning You, Tianlong C
AutoSF The code for our paper "AutoSF: Searching Scoring Functions for Knowledge Graph Embedding" and this paper has been accepted by ICDE2020. News:
TransFG: A Transformer Architecture for Fine-grained Recognition Official PyTorch code for the paper: TransFG: A Transformer Architecture for Fine-gra
CPT: Efficient Deep Neural Network Training via Cyclic Precision Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin Accep
Super-SloMo PyTorch implementation of "Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation" by Jiang H., Sun
SuMa++: Efficient LiDAR-based Semantic SLAM This repository contains the implementation of SuMa++, which generates semantic maps only using three-dime
Temporal Query Networks for Fine-grained Video Understanding ?? This repository contains the implementation of CVPR2021 paper Temporal_Query_Networks
Graph Convolutional Networks for Hyperspectral Image Classification Danfeng Hong, Lianru Gao, Jing Yao, Bing Zhang, Antonio Plaza, Jocelyn Chanussot T
ARAE Code for the paper "Adversarially Regularized Autoencoders (ICML 2018)" by Zhao, Kim, Zhang, Rush and LeCun https://arxiv.org/abs/1706.04223 Disc
Bridging Multi-Task Learning and Meta-Learning Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Trainin
Rank & Sort Loss for Object Detection and Instance Segmentation The official implementation of Rank & Sort Loss. Our implementation is based on mmdete
64 Dec 8, 2022
80 Nov 23, 2022
64 Dec 17, 2022
307 Jan 3, 2023
26 Oct 25, 2022
2.9k Jan 3, 2023
701 Dec 30, 2022
55 Dec 21, 2022
154 Dec 13, 2022
399 Jan 2, 2023
57 Dec 15, 2022
229 Dec 20, 2022