Alert button
Picture for Piotr Dollár

Piotr Dollár

Alert button

Segment Anything

Apr 05, 2023
Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, Ross Girshick

Figure 1 for Segment Anything
Figure 2 for Segment Anything
Figure 3 for Segment Anything
Figure 4 for Segment Anything
Viaarxiv icon

The effectiveness of MAE pre-pretraining for billion-scale pretraining

Mar 23, 2023
Mannat Singh, Quentin Duval, Kalyan Vasudev Alwala, Haoqi Fan, Vaibhav Aggarwal, Aaron Adcock, Armand Joulin, Piotr Dollár, Christoph Feichtenhofer, Ross Girshick, Rohit Girdhar, Ishan Misra

Figure 1 for The effectiveness of MAE pre-pretraining for billion-scale pretraining
Figure 2 for The effectiveness of MAE pre-pretraining for billion-scale pretraining
Figure 3 for The effectiveness of MAE pre-pretraining for billion-scale pretraining
Figure 4 for The effectiveness of MAE pre-pretraining for billion-scale pretraining
Viaarxiv icon

Revisiting Weakly Supervised Pre-Training of Visual Perception Models

Jan 20, 2022
Mannat Singh, Laura Gustafson, Aaron Adcock, Vinicius de Freitas Reis, Bugra Gedik, Raj Prateek Kosaraju, Dhruv Mahajan, Ross Girshick, Piotr Dollár, Laurens van der Maaten

Figure 1 for Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Figure 2 for Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Figure 3 for Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Figure 4 for Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Viaarxiv icon

Masked Autoencoders Are Scalable Vision Learners

Dec 02, 2021
Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick

Figure 1 for Masked Autoencoders Are Scalable Vision Learners
Figure 2 for Masked Autoencoders Are Scalable Vision Learners
Figure 3 for Masked Autoencoders Are Scalable Vision Learners
Figure 4 for Masked Autoencoders Are Scalable Vision Learners
Viaarxiv icon

Early Convolutions Help Transformers See Better

Jul 12, 2021
Tete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Dollár, Ross Girshick

Figure 1 for Early Convolutions Help Transformers See Better
Figure 2 for Early Convolutions Help Transformers See Better
Figure 3 for Early Convolutions Help Transformers See Better
Figure 4 for Early Convolutions Help Transformers See Better
Viaarxiv icon

Boundary IoU: Improving Object-Centric Image Segmentation Evaluation

Mar 30, 2021
Bowen Cheng, Ross Girshick, Piotr Dollár, Alexander C. Berg, Alexander Kirillov

Figure 1 for Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
Figure 2 for Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
Figure 3 for Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
Figure 4 for Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
Viaarxiv icon

Fast and Accurate Model Scaling

Mar 11, 2021
Piotr Dollár, Mannat Singh, Ross Girshick

Figure 1 for Fast and Accurate Model Scaling
Figure 2 for Fast and Accurate Model Scaling
Figure 3 for Fast and Accurate Model Scaling
Figure 4 for Fast and Accurate Model Scaling
Viaarxiv icon

Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details

Feb 01, 2021
Achal Dave, Piotr Dollár, Deva Ramanan, Alexander Kirillov, Ross Girshick

Figure 1 for Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
Figure 2 for Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
Figure 3 for Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
Figure 4 for Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
Viaarxiv icon