Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness



Francesco Pinto , Harry Yang , Ser-Nam Lim , Philip H. S. Torr , Puneet K. Dokania

* 22 pages, 18 figures 

   Access Paper or Ask Questions

How robust are pre-trained models to distribution shift?



Yuge Shi , Imant Daunhawer , Julia E. Vogt , Philip H. S. Torr , Amartya Sanyal


   Access Paper or Ask Questions

Catastrophic overfitting is a bug but also a feature



Guillermo Ortiz-Jiménez , Pau de Jorge , Amartya Sanyal , Adel Bibi , Puneet K. Dokania , Pascal Frossard , Gregory Rogéz , Philip H. S. Torr

* 24 pages, 19 figures, 1 table. Work partially presented at Adversarial Machine Learning Workshop at ICML 2022 

   Access Paper or Ask Questions

Zero-Shot Logit Adjustment



Dubing Chen , Yuming Shen , Haofeng Zhang , Philip H. S. Torr

* IJCAI 2022 

   Access Paper or Ask Questions

Towards the Semantic Weak Generalization Problem in Generative Zero-Shot Learning: Ante-hoc and Post-hoc



Dubing Chen , Yuming Shen , Haofeng Zhang , Philip H. S. Torr


   Access Paper or Ask Questions

BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion



Kejie Li , Yansong Tang , Victor Adrian Prisacariu , Philip H. S. Torr

* Accepted at CVPR 2022 

   Access Paper or Ask Questions

Local and Global GANs with Semantic-Aware Upsampling for Image Generation



Hao Tang , Ling Shao , Philip H. S. Torr , Nicu Sebe

* Accepted to TPAMI, an extended version of a paper published in CVPR 2020. arXiv admin note: substantial text overlap with arXiv:1912.12215 

   Access Paper or Ask Questions

Make Some Noise: Reliable and Efficient Single-Step Adversarial Training



Pau de Jorge , Adel Bibi , Riccardo Volpi , Amartya Sanyal , Philip H. S. Torr , Grégory Rogez , Puneet K. Dokania


   Access Paper or Ask Questions

Learning to Hash Naturally Sorts



Yuming Shen , Jiaguo Yu , Haofeng Zhang , Philip H. S. Torr , Menghan Wang

* Preprint 

   Access Paper or Ask Questions

1
2
3
4
5
6
7
>>