Train 3D segmentation model using labeled 2D images and raw 3D data
… there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras.
However, due to high labeling costs, ground-truth 3D semantic segmentation annotations are limited …
… investigate how to use only those labeled 2D image collections to supervise training 3D semantic segmentation models.
Our approach is to train a 3D model from pseudo-labels derived from 2D semantic image segmentations using multiview fusion.
… proposed network architecture, 2D3DNet, achieves significantly better performance (+6.2–11.4 mIoU) than baselines …
Survey of deep learning to re-identify people seen by multiple cameras
… person re-identification (Re-ID) … goal is to retrieve persons with the same identity from different cameras.
State of AI Report 2021 (Benaich and Hogarth) (includes Computer Vision)
State of AI Report 2021
Kaggle 2021 survey on ML and Data Science
State of Data Science and Machine Learning 2021
Kaggle Executive Summary of survey on Machine Learning and Data Science
Kaggle PDF https://storage.googleapis.com/kaggle-media/surveys/Kaggle's%20State%20of%20Machine%20Learning%20and%20Data%20Science%202021.pdf
* Half between 22 and 34 in age
* Live in India or U.S.
* Have a Master’s degree
Image classifier explains features used and how to modify them to change output
Explaining in Style: Training a GAN to explain a classifier in StyleSpace
arXiv paper abstract https://arxiv.org/abs/2104.13369
arXiv PDF paper https://arxiv.org/pdf/2104.13369.pdf
Project page https://explaining-in-style.github.io
Image classification models can depend on multiple … attributes … An explanation…
Improved multi-object tracking by associating all detection boxes
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
arXiv paper abstract https://arxiv.org/abs/2110.06864
arXiv PDF paper https://arxiv.org/pdf/2110.06864.pdf
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos.
Most methods … objects with low detection scores, e.g. occluded…
Make images in-focus at every pixel with the dual-pixel cameras in smartphones
… a method that takes as input a single dual-pixel image, and simultaneously estimates the image’s defocus map — the…
Improve road lane detection by using multiple images with neural networks
A Hybrid Spatial-temporal Sequence-to-one Neural Network Model for Lane Detection
DeepAI paper abstract https://deepai.org/publication/a-hybrid-spatial-temporal-sequence-to-one-neural-network-model-for-lane-detection
arXiv PDF paper https://arxiv.org/ftp/arxiv/papers/2110/2110.04079.pdf
Reliable and accurate lane detection is of vital importance for the safe performance of Lane Keeping Assistance and Lane Departure Warning…
Identify human actions on objects and their locations after training on image captions
Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions
arXiv paper abstract https://arxiv.org/abs/2110.03562v1
arXiv PDF paper https://arxiv.org/pdf/2110.03562v1.pdf
… introduce the task of weakly supervised learning for detecting human and object interactions in videos.