research
∙
04/05/2023
Segment Anything
We introduce the Segment Anything (SA) project: a new task, model, and d...
share
research
∙
03/23/2023
The effectiveness of MAE pre-pretraining for billion-scale pretraining
This paper revisits the standard pretrain-then-finetune paradigm used in...
research
∙
03/30/2022
Exploring Plain Vision Transformer Backbones for Object Detection
We explore the plain, non-hierarchical Vision Transformer (ViT) as a bac...
research
∙
01/20/2022
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Model pre-training is a cornerstone of modern visual recognition systems...
research
∙
11/22/2021
Benchmarking Detection Transfer Learning with Vision Transformers
Object detection is a central downstream task used to test if pre-traine...
research
∙
11/18/2021
PyTorchVideo: A Deep Learning Library for Video Understanding
We introduce PyTorchVideo, an open-source deep-learning library that pro...
research
∙
11/11/2021
Masked Autoencoders Are Scalable Vision Learners
This paper shows that masked autoencoders (MAE) are scalable self-superv...
research
∙
06/28/2021
Early Convolutions Help Transformers See Better
Vision transformer (ViT) models exhibit substandard optimizability. In p...
research
∙
04/29/2021
A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
We present a large-scale study on unsupervised spatiotemporal representa...
research
∙
03/30/2021
Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
We present Boundary IoU (Intersection-over-Union), a new segmentation ev...
research
∙
03/11/2021
Fast and Accurate Model Scaling
In this work we analyze strategies for convolutional neural network scal...
research
∙
02/01/2021
Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
By design, average precision (AP) for object detection aims to treat all...
research
∙
05/16/2020
Large scale weakly and semi-supervised learning for low-resource video ASR
Many semi- and weakly-supervised approaches have been investigated for o...
research
∙
03/30/2020
Designing Network Design Spaces
In this work, we present a new network design paradigm. Our goal is to h...
research
∙
03/26/2020
Are Labels Necessary for Neural Architecture Search?
Existing neural network architectures in computer vision — whether desig...
research
∙
03/09/2020
Improved Baselines with Momentum Contrastive Learning
Contrastive unsupervised learning has recently shown encouraging progres...
research
∙
12/17/2019
PointRend: Image Segmentation as Rendering
We present a new method for efficient high-quality image segmentation of...
research
∙
12/02/2019
A Multigrid Method for Efficiently Training Video Models
Training competitive deep video models is an order of magnitude slower t...
research
∙
11/13/2019
Momentum Contrast for Unsupervised Visual Representation Learning
We present Momentum Contrast (MoCo) for unsupervised visual representati...
research
∙
10/27/2019
Training ASR models by Generation of Contextual Information
Supervised ASR models have reached unprecedented levels of accuracy, tha...
research
∙
08/15/2019
PHYRE: A New Benchmark for Physical Reasoning
Understanding and reasoning about physics is an important ability of int...
research
∙
08/08/2019
LVIS: A Dataset for Large Vocabulary Instance Segmentation
Progress on object detection is enabled by datasets that focus the resea...
research
∙
04/02/2019
Exploring Randomly Wired Neural Networks for Image Recognition
Neural networks for image recognition have evolved through extensive man...
research
∙
03/28/2019
TensorMask: A Foundation for Dense Object Segmentation
Sliding-window object detectors that generate bounding-box object predic...
research
∙
01/08/2019
Panoptic Feature Pyramid Networks
The recently introduced panoptic segmentation task has renewed our commu...
research
∙
12/12/2018
Long-Term Feature Banks for Detailed Video Understanding
To understand the world, we humans constantly need to relate the present...
research
∙
11/21/2018
Rethinking ImageNet Pre-training
We report competitive results on object detection and instance segmentat...
research
∙
05/02/2018
Exploring the Limits of Weakly Supervised Pretraining
State-of-the-art visual perception models for a wide range of tasks rely...
research
∙
01/16/2018
Low-Shot Learning from Imaginary Data
Humans can quickly learn new visual concepts, perhaps because they can e...
research
∙
01/03/2018
Panoptic Segmentation
We propose and study a novel 'Panoptic Segmentation' (PS) task. Panoptic...
research
∙
12/12/2017
Data Distillation: Towards Omni-Supervised Learning
We investigate omni-supervised learning, a special regime of semi-superv...
research
∙
12/04/2017
Learning by Asking Questions
We introduce an interactive learning framework for the development and t...
research
∙
11/28/2017
Learning to Segment Every Thing
Existing methods for object instance segmentation require all training i...
research
∙
11/21/2017
Non-local Neural Networks
Both convolutional and recurrent operations are building blocks that pro...
research
∙
08/07/2017
Focal Loss for Dense Object Detection
The highest accuracy object detectors to date are based on a two-stage a...
research
∙
06/08/2017
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Deep learning thrives with large neural networks and large datasets. How...
research
∙
05/10/2017
Inferring and Executing Programs for Visual Reasoning
Existing methods for visual reasoning attempt to directly map inputs to ...
research
∙
03/20/2017
Mask R-CNN
We present a conceptually simple, flexible, and general framework for ob...
research
∙
12/20/2016
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
When building artificial intelligence systems that can reason and answer...
research
∙
12/19/2016
Learning Features by Watching Objects Move
This paper presents a novel yet intuitive approach to unsupervised featu...
research
∙
12/09/2016
Feature Pyramid Networks for Object Detection
Feature pyramids are a basic component in recognition systems for detect...
research
∙
11/16/2016
Aggregated Residual Transformations for Deep Neural Networks
We present a simple, highly modularized network architecture for image c...
research
∙
06/09/2016
Low-shot Visual Recognition by Shrinking and Hallucinating Features
Low-shot visual learning---the ability to recognize novel object categor...
research
∙
04/13/2016
Visual Storytelling
We introduce the first dataset for sequential vision-to-language, and ex...
research
∙
04/13/2016
Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks
As 3D movie viewing becomes mainstream and Virtual Reality (VR) market e...
research
∙
04/12/2016
Training Region-based Object Detectors with Online Hard Example Mining
The field of object detection has made significant advances riding on th...
research
∙
12/22/2015
Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels
When human annotators are given a choice about what to label in an image...
research
∙
12/14/2015
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
It is well known that contextual and multi-scale representations are imp...
research
∙
11/19/2015
Reducing Overfitting in Deep Networks by Decorrelating Representations
One major challenge in training Deep Neural Networks is preventing overf...
research
∙
06/08/2015