Representation Learning with Very Limited Images: Zero-shot Unsupervised and Synthetic Learning in the Era of Big Models


Data-free Model Fusion with Generator Assistants
Luyao Shi,
Prashanth Vijayaraghavan,
Ehsan Degan
[pdf] [supp]
[bibtex]
@InProceedings{Shi_2024_CVPR, author = {Shi, Luyao and Vijayaraghavan, Prashanth and Degan, Ehsan}, title = {Data-free Model Fusion with Generator Assistants}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7731-7739} }

POPE: 6-DoF Promptable Pose Estimation of Any Object in Any Scene with One Reference
Zhiwen Fan,
Panwang Pan,
Peihao Wang,
Yifan Jiang,
Dejia Xu,
Zhangyang Wang
[pdf] [supp]
[bibtex]
@InProceedings{Fan_2024_CVPR, author = {Fan, Zhiwen and Pan, Panwang and Wang, Peihao and Jiang, Yifan and Xu, Dejia and Wang, Zhangyang}, title = {POPE: 6-DoF Promptable Pose Estimation of Any Object in Any Scene with One Reference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7771-7781} }

Enhancing 2D Representation Learning with a 3D Prior
Mehmet Aygun,
Prithviraj Dhar,
Zhicheng Yan,
Oisin Mac Aodha,
Rakesh Ranjan
[pdf] [arXiv]
[bibtex]
@InProceedings{Aygun_2024_CVPR, author = {Aygun, Mehmet and Dhar, Prithviraj and Yan, Zhicheng and Mac Aodha, Oisin and Ranjan, Rakesh}, title = {Enhancing 2D Representation Learning with a 3D Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7750-7760} }

A Method of Moments Embedding Constraint and its Application to Semi-Supervised Learning
Michael Majurski,
Sumeet Menon,
Parniyan Favardin,
David Chapman
[pdf]
[bibtex]
@InProceedings{Majurski_2024_CVPR, author = {Majurski, Michael and Menon, Sumeet and Favardin, Parniyan and Chapman, David}, title = {A Method of Moments Embedding Constraint and its Application to Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7809-7818} }

Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning
Xin Xing,
Zhexiao Xiong,
Abby Stylianou,
Srikumar Sastry,
Liyu Gong,
Nathan Jacobs
[pdf] [arXiv]
[bibtex]
@InProceedings{Xing_2024_CVPR, author = {Xing, Xin and Xiong, Zhexiao and Stylianou, Abby and Sastry, Srikumar and Gong, Liyu and Jacobs, Nathan}, title = {Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7799-7808} }

i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?
Kevin Zhang,
Zhiqiang Shen
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Kevin and Shen, Zhiqiang}, title = {i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7740-7749} }

`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning
Joshua Feinglass,
Jayaraman J. Thiagarajan,
Rushil Anirudh,
T.S. Jayram,
Yezhou Yang
[pdf] [arXiv]
[bibtex]
@InProceedings{Feinglass_2024_CVPR, author = {Feinglass, Joshua and Thiagarajan, Jayaraman J. and Anirudh, Rushil and Jayram, T.S. and Yang, Yezhou}, title = {`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7791-7798} }

Federated Learning with a Single Shared Image
Sunny Soni,
Aaqib Saeed,
Yuki M. Asano
[pdf] [supp]
[bibtex]
@InProceedings{Soni_2024_CVPR, author = {Soni, Sunny and Saeed, Aaqib and Asano, Yuki M.}, title = {Federated Learning with a Single Shared Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7782-7790} }

PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination
Anant Khandelwal
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khandelwal_2024_CVPR, author = {Khandelwal, Anant}, title = {PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7819-7828} }

Prompt Learning with One-Shot Setting based Feature Space Analysis in Vision-and-Language Models
Yuki Hirohashi,
Tsubasa Hirakawa,
Takayoshi Yamashita,
Hironobu Fujiyoshi
[pdf] [supp]
[bibtex]
@InProceedings{Hirohashi_2024_CVPR, author = {Hirohashi, Yuki and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu}, title = {Prompt Learning with One-Shot Setting based Feature Space Analysis in Vision-and-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7761-7770} }