research
∙
09/14/2023
Efficiently Robustify Pre-trained Models
A recent trend in deep learning algorithms has been towards training lar...
share
research
∙
09/12/2023
Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation
We propose a new paradigm to automatically generate training data with a...
research
∙
06/15/2023
Robustness Analysis on Foundational Segmentation Models
Due to the increase in computational resources and accessibility of data...
research
∙
05/29/2023
Controllable Text-to-Image Generation with GPT-4
Current text-to-image generation models often struggle to follow textual...
research
∙
03/15/2023
PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining
A rich representation is key to general robotic manipulation, but existi...
research
∙
12/15/2022
EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
We propose EM-PASTE: an Expectation Maximization(EM) guided Cut-Paste co...
research
∙
09/22/2022
Learning to Simulate Realistic LiDARs
Simulating realistic sensors is a challenging part in data generation fo...
research
∙
07/22/2022
Neural-Sim: Learning to Generate Training Data with NeRF
Training computer vision models usually requires collecting and labeling...
research
∙
07/11/2022
Scaling Novel Object Detection with Weakly Supervised Detection Transformers
Weakly supervised object detection (WSOD) enables object detectors to be...
research
∙
07/11/2022
TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs
3D scene graphs (3DSGs) are an emerging description; unifying symbolic, ...
research
∙
07/05/2022
Multi-modal Robustness Analysis Against Language and Visual Perturbations
Joint visual and language modeling on large-scale datasets has recently ...
research
∙
07/04/2022
Large-scale Robustness Analysis of Video Action Recognition Models
We have seen a great progress in video action recognition in recent year...
research
∙
06/20/2022
DALL-E for Detection: Language-driven Context Image Synthesis for Object Detection
Object cut-and-paste has become a promising approach to efficiently gene...
research
∙
03/29/2022
Image Retrieval from Contextual Descriptions
The ability to integrate context, including perceptual and temporal cues...
research
∙
01/12/2022
Robust Contrastive Learning against Noisy Views
Contrastive learning relies on an assumption that positive pairs contain...
research
∙
11/17/2021
Learning to Align Sequential Actions in the Wild
State-of-the-art methods for self-supervised sequential action alignment...
research
∙
10/21/2020
Prediction of Object Geometry from Acoustic Scattering Using Convolutional Neural Networks
Acoustic scattering is strongly influenced by boundary geometry of objec...
research
∙
10/06/2020
RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
Although 3D Convolutional Neural Networks (CNNs) are essential for most ...
research
∙
08/16/2020
AutoSimulate: (Quickly) Learning Synthetic Data Generation
Simulation is increasingly being used for generating large labelled data...
research
∙
01/21/2020
Deep Depth Prior for Multi-View Stereo
It was recently shown that the structure of convolutional neural network...
research
∙
10/30/2019
Fast acoustic scattering using convolutional neural networks
Diffracted scattering and occlusion are important acoustic effects in in...
research
∙
09/16/2019
Learning Controls Using Cross-Modal Representations: Bridging Simulation and Reality for Drone Racing
Machines are a long way from robustly solving open-world perception-cont...
research
∙
03/15/2019
Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
Standard 3D reconstruction pipelines assume stationary world, therefore ...
research
∙
02/25/2019
Privacy-Preserving Action Recognition using Coded Aperture Videos
The risk of unauthorized remote access of streaming video from networked...
research
∙
02/09/2019
Photorealistic Image Synthesis for Object Instance Detection
We present an approach to synthesize highly photorealistic images of 3D ...
research
∙
08/07/2016
Playing for Data: Ground Truth from Computer Games
Recent progress in computer vision has been driven by high-capacity mode...
research
∙
10/13/2015
SemanticPaint: A Framework for the Interactive Segmentation of 3D Scenes
We present an open-source, real-time implementation of SemanticPaint, a ...
research
∙
02/11/2015
Conditional Random Fields as Recurrent Neural Networks
Pixel-level labelling tasks, such as semantic segmentation, play a centr...
research
∙
10/16/2013