图像生成 - arXivDaily 专题

2210.16870 2022-11-01 cs.CV cs.LG 57%

A simple, efficient and scalable contrastive masked autoencoder for learning visual representations

Shlok Mishra, Joshua Robinson, Huiwen Chang, David Jacobs, Aaron Sarna, Aaron Maschinot, Dilip Krishnan

专题命中效率与蒸馏：diffusion(abstract)；分类 cs.CV

Comments Mishra and Robinson contributed equally

2209.11178 2022-10-21 cs.LG cs.CV 57%

Poisson Flow Generative Models

Yilun Xu, Ziming Liu, Max Tegmark, Tommi Jaakkola

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2022

2209.14097 2022-09-29 eess.IV cs.CV cs.LG 57%

Data Augmentation using Feature Generation for Volumetric Medical Images

Khushboo Mehra, Hassan Soliman, Soumya Ranjan Sahoo

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments 8 pages, 11 figures

2008.01910 2022-09-13 eess.IV cs.CV 57%

Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN

Li Sun, Junxiang Chen, Yanwu Xu, Mingming Gong, Ke Yu, Kayhan Batmanghelich

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments Paper accepted to IEEE Journal of Biomedical and Health Informatics, code available at https://github.com/batmanlab/HA-GAN

Journal ref in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 8, pp. 3966-3975, Aug. 2022

2209.03793 2022-09-09 cs.CV cs.LG 57%

Lightweight Long-Range Generative Adversarial Networks

Bowen Li, Thomas Lukasiewicz

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

2208.08781 2022-08-19 cs.LG cs.CV 57%

Efficient data-driven gap filling of satellite image time series using deep neural networks with partial convolutions

Marius Appel

专题命中效率与蒸馏：inpainting(abstract)；分类 cs.CV

Comments This work has not yet been peer-reviewed and is provided by the contributing author(s) as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis

2112.15358 2022-08-15 cs.CV 57%

Conditional Generative Data-free Knowledge Distillation

Xinyi Yu, Ling Yan, Yang Yang, Libo Zhou, Linlin Ou

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

2207.05415 2022-07-13 cs.GR cs.NA math.NA 57%

Rendering along the Hilbert Curve

Alexander Keller, Carsten Wächter, Nikolaus Binder

专题命中效率与蒸馏：image synthesis(abstract)；分类 cs.GR

2111.15097 2022-07-13 cs.CV cs.LG cs.NE 57%

EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs

Guohao Ying, Xin He, Bin Gao, Bo Han, Xiaowen Chu

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments Accepted in ECCV2022, Guohao Yin and Xin He contributed equally

2207.04228 2022-07-12 cs.CV cs.LG cs.NA math.NA 57%

Batch-efficient EigenDecomposition for Small and Medium Matrices

Yue Song, Nicu Sebe, Wei Wang

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments Accepted by ECCV22

2206.02102 2022-06-07 cs.LG cs.AI cs.CV cs.NA math.NA 57%

AUTM Flow: Atomic Unrestricted Time Machine for Monotonic Normalizing Flows

Difeng Cai, Yuliang Ji, Huan He, Qiang Ye, Yuanzhe Xi

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments 20 pages, 3 figures

2203.01993 2022-05-09 cs.CV 57%

Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values

Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments 20 pages, 16 figures, CVPR 2022 Oral, Camera Ready

2203.14702 2022-03-29 cs.CV cs.LG stat.ML 57%

Bi-level Doubly Variational Learning for Energy-based Latent Variable Models

Ge Kan, Jinhu Lü, Tian Wang, Baochang Zhang, Aichun Zhu, Lei Huang, Guodong Guo, Hichem Snoussi

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments CVPR 2022

2108.06227 2022-03-22 cs.CV cs.AI cs.LG 57%

SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation

Chenyu You, Yuan Zhou, Ruihan Zhao, Lawrence Staib, James S. Duncan

专题命中效率与蒸馏：image synthesis(abstract)；分类 cs.CV

Comments IEEE Transactions on Medical Imaging (IEEE-TMI) 2022

2110.06607 2022-01-24 cs.CV cs.RO 57%

THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou, Bogdan Stanciulescu, Fabien Moutarde

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

2012.00888 2022-01-10 cs.CV cs.CG cs.LG 57%

DiffusionNet: Discretization Agnostic Learning on Surfaces

Nicholas Sharp, Souhaib Attaiki, Keenan Crane, Maks Ovsjanikov

专题命中效率与蒸馏：diffusion(abstract)；分类 cs.CV

Comments Published in ACM Transactions on Graphics, presented at SIGGRAPH 2022

2105.12723 2022-01-03 cs.CV 57%

Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding

Zizhao Zhang, Han Zhang, Long Zhao, Ting Chen, Sercan O. Arik, Tomas Pfister

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments AAAI2022

2106.07631 2021-12-28 cs.CV 57%

Improved Transformer for High-Resolution GANs

Long Zhao, Zizhao Zhang, Ting Chen, Dimitris N. Metaxas, Han Zhang

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2021 (with updated ImageNet results). Code is available at https://github.com/google-research/hit-gan

2110.00375 2021-12-15 cs.NE cs.CV cs.LG 57%

Fully Spiking Variational Autoencoder

Hiromichi Kamata, Yusuke Mukuta, Tatsuya Harada

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments Accepted to AAAI2022

2112.00730 2021-12-03 eess.IV cs.CV 57%

Highly accelerated MR parametric mapping by undersampling the k-space and reducing the contrast number simultaneously with deep learning

Yanjie Zhu, Haoxiang Li, Yuanyuan Liu, Muzi Guo, Guanxun Cheng, Gang Yang, Haifeng Wang, Dong Liang

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments 27 pages,11 figures. Submitted to Magnetic Resonance in Medicine

2111.07346 2021-11-16 cs.IR cs.CV 57%

A Study on the Efficient Product Search Service for the Damaged Image Information

Yonghyun Kim

专题命中效率与蒸馏：inpainting(abstract)；分类 cs.CV

Comments 5 pages, 8 figures

2003.08936 2021-11-12 cs.CV eess.IV 57%

GAN Compression: Efficient Architectures for Interactive Conditional GANs

Muyang Li, Ji Lin, Yaoyao Ding, Zhijian Liu, Jun-Yan Zhu, Song Han

专题命中效率与蒸馏：image synthesis(abstract)；分类 cs.CV

2106.13929 2021-10-04 cs.CV 57%

Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification

Huafeng Li, Kaixiong Xu, Jinxing Li, Guangming Lu, Yong Xu, Zhengtao Yu, David Zhang

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments 14 pages,8 figures

2108.13344 2021-08-31 cs.CV cs.AI 57%

Enlisting 3D Crop Models and GANs for More Data Efficient and Generalizable Fruit Detection

Zhenghao Fei, Alex Olenskyj, Brian N. Bailey, Mason Earles

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

2108.09285 2021-08-23 cs.CV eess.IV 57%

Zoom, Enhance! Measuring Surveillance GAN Up-sampling

Jake Sparkman, Abdalla Al-Ayrot, Utkarsh Contractor

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

2107.09060 2021-07-21 eess.IV cs.AI cs.CV cs.LG 57%

LAPNet: Non-rigid Registration derived in k-space for Magnetic Resonance Imaging

Thomas Küstner, Jiazhen Pan, Haikun Qi, Gastao Cruz, Christopher Gilliam, Thierry Blu, Bin Yang, Sergios Gatidis, René Botnar, Claudia Prieto

专题命中效率与蒸馏：diffusion(abstract)；分类 cs.CV

2107.03742 2021-07-09 cs.CV cs.LG 57%

Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation

Nikolay Jetchev, Gökhan Yildirim, Christian Bracher, Roland Vollgraf

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments code available at https://github.com/zalandoresearch/gpa

2009.00210 2021-07-07 cs.CV 57%

Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition

Yang Liu, Keze Wang, Guanbin Li, Liang Lin

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments This paper focuses on the sensor-to-vision heterogenous action recognition problem. Code is available at https://github.com/YangLiu9208/SAKDN

2107.01900 2021-07-07 cs.LG cs.CV 57%

On The Distribution of Penultimate Activations of Classification Networks

Minkyo Seo, Yoonho Lee, Suha Kwak

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments 8 pages, UAI 2021, The first two authors equally contributed

2103.00430 2021-06-17 cs.CV cs.LG eess.IV 57%

Training Generative Adversarial Networks in One Stage

Chengchao Shen, Youtan Yin, Xinchao Wang, Xubin Li, Jie Song, Mingli Song

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments Accepted to CVPR 2021

1. 效率与蒸馏 2542 篇

A simple, efficient and scalable contrastive masked autoencoder for learning visual representations

Poisson Flow Generative Models

Data Augmentation using Feature Generation for Volumetric Medical Images

Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN

Lightweight Long-Range Generative Adversarial Networks

Efficient data-driven gap filling of satellite image time series using deep neural networks with partial convolutions

Conditional Generative Data-free Knowledge Distillation

Rendering along the Hilbert Curve

EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs

Batch-efficient EigenDecomposition for Small and Medium Matrices

AUTM Flow: Atomic Unrestricted Time Machine for Monotonic Normalizing Flows

Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values

Bi-level Doubly Variational Learning for Energy-based Latent Variable Models

SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation

THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling

DiffusionNet: Discretization Agnostic Learning on Surfaces

Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding

Improved Transformer for High-Resolution GANs

Fully Spiking Variational Autoencoder

Highly accelerated MR parametric mapping by undersampling the k-space and reducing the contrast number simultaneously with deep learning

A Study on the Efficient Product Search Service for the Damaged Image Information

GAN Compression: Efficient Architectures for Interactive Conditional GANs

Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification

Enlisting 3D Crop Models and GANs for More Data Efficient and Generalizable Fruit Detection

Zoom, Enhance! Measuring Surveillance GAN Up-sampling

LAPNet: Non-rigid Registration derived in k-space for Magnetic Resonance Imaging

Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation

Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition

On The Distribution of Penultimate Activations of Classification Networks

Training Generative Adversarial Networks in One Stage