research
∙
07/14/2023
DreamTeacher: Pretraining Image Backbones with Deep Generative Models
In this work, we introduce a self-supervised feature representation lear...
share
research
∙
09/26/2022
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
We introduce VISOR, a new dataset of pixel annotations and a benchmark s...
research
∙
02/08/2022
Causal Scene BERT: Improving object detection by searching for challenging groups of data
Modern computer vision applications rely on learning-based perception mo...
research
∙
10/07/2021
ATISS: Autoregressive Transformers for Indoor Scene Synthesis
The ability to synthesize realistic and diverse indoor furniture layouts...
research
∙
04/26/2021
Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
Data is the engine of modern computer vision, which necessitates collect...
research
∙
09/01/2020
Fed-Sim: Federated Simulation for Medical Imaging
Labelling data is expensive and time consuming especially for domains su...
research
∙
08/24/2020
Interactive Annotation of 3D Object Geometry using 2D Scribbles
Inferring detailed 3D geometry of the scene is crucial for robotics appl...
research
∙
08/20/2020
Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Procedural models are being widely used to synthesize scenes for graphic...
research
∙
04/19/2020
Learning to Evaluate Perception Models Using Planner-Centric Metrics
Variants of accuracy and precision are the gold-standard by which the co...
research
∙
04/25/2019
Meta-Sim: Learning to Generate Synthetic Datasets
Training models to high-end performance requires availability of large l...
research
∙
04/16/2019
Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations
We tackle the problem of semantic boundary prediction, which aims to ide...
research
∙
03/16/2019
Fast Interactive Object Annotation with Curve-GCN
Manually labeling objects by tracing their boundaries is a laborious pro...
research
∙
12/01/2018
Lifelong Learning for Image Captioning by Asking Natural Language Questions
In order to bring artificial agents into our lives, we will need to go b...
research
∙
06/07/2018
Color Sails: Discrete-Continuous Palettes for Deep Color Exploration
We present color sails, a discrete-continuous color gamut representation...
research
∙
03/26/2018
Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
Manually labeling datasets with object masks is extremely time consuming...
research
∙
11/24/2016