18.1k citations · 35.5k across the 59 of their papers we have counts for
8 papers · 1 filter
Masked Autoencoders Are Scalable Vision Learners
Kaiming He, Xinlei Chen, Saining Xie +3
This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and…
Benchmarking Detection Transfer Learning with Vision Transformers
Yanghao Li, Saining Xie, Xinlei Chen +3
Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object…
PyTorchVideo: A Deep Learning Library for Video Understanding
Haoqi Fan, Tullie Murrell, Heng Wang +13
We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tas…
Early Convolutions Help Transformers See Better
Tete Xiao, Mannat Singh, Eric Mintun +3
Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and tra…
A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
Christoph Feichtenhofer, Haoqi Fan, Bo Xiong +2
We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simp…
Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
Bowen Cheng, Ross Girshick, Piotr Dollár +2
We present Boundary IoU (Intersection-over-Union), a new segmentation evaluation measure focused on boundary quality. We perform an extensive analysis across different error types…
Fast and Accurate Model Scaling
Piotr Dollár, Mannat Singh, Ross Girshick
In this work we analyze strategies for convolutional neural network scaling; that is, the process of scaling a base convolutional network to endow it with greater computational com…
Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
Achal Dave, Piotr Dollár, Deva Ramanan +2
By design, average precision (AP) for object detection aims to treat all classes independently: AP is computed independently per category and averaged. On one hand, this is desirab…