The ORBIT dataset is a collection of videos of objects in clean and cluttered scenes recorded by people who are blind/low-vision on a mobile phone. The dataset is presented with a teachable object recognition benchmark task which aims to drive few-shot learning on challenging real-world data.
microsoft
machine-learning
computer-vision
video
benchmark
dataset
classification
few-shot-learning
meta-learning
object-recognition
Обновлено 2024-08-13 03:27:45 +03:00
CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
deep-learning
computer-vision
pytorch
generative-adversarial-network
image-manipulation
gans
cocosnet
image-synthesis
image-translation
image-generation
Обновлено 2024-07-25 14:07:42 +03:00
Python toolchain for SOLO.
Обновлено 2024-07-16 12:13:36 +03:00
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation (CVPR 2021)
deep-learning
computer-vision
neural-network
semantic-segmentation
semi-supervised-learning
domain-adaptation
pseudo-label
Обновлено 2023-07-07 00:28:52 +03:00
Improving Generalization via Scalable Neighborhood Component Analysis
deep-learning
computer-vision
transfer-learning
visual-recognition
eccv-2018
few-shot-learning
nearest-neighbors
Обновлено 2023-06-12 22:02:13 +03:00
Cross-domain Correspondence Learning for Exemplar-based Image Translation. (CVPR 2020 Oral)
deep-learning
computer-vision
pytorch
generative-adversarial-network
gans
image-manipulation
cocosnet
image-synthesis
image-translation
Обновлено 2022-12-07 08:35:12 +03:00
Solo plugin to Voxel FiftyOne
Обновлено 2022-11-30 19:29:45 +03:00
Drone Racing @ NeurIPS 2019, built on Microsoft AirSim
microsoft
machine-learning
computer-vision
robotics-simulation
robotics
airsim
motion-planning
drones
unreal-engine
drone-racing
neurips-competition
robotics-competition
Обновлено 2022-08-13 02:58:26 +03:00
This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.
Обновлено 2022-06-22 07:21:09 +03:00
A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.
unity
machine-learning
deep-learning
computer-vision
robotics
manipulation
perception
physics-simulation
pose-estimation
robotics-simulation
simulation
ur3-robot-arm
ros
urdf
motion-planning
synthetic-data
trajectory-generation
tutorial
model-training
autonomy
Обновлено 2022-04-13 20:50:31 +03:00
Deep Learning for Seismic Imaging and Interpretation
microsoft
deep-learning
computer-vision
neural-networks
segmentation
seismic-processing
seismic
seismic-data
seismic-imaging
seismic-inversion
Обновлено 2020-09-19 01:18:20 +03:00