A W-Net deep learning model detects asteroids in TESS data independently of trajectory by rotating training image cubes and using adaptive normalization for data scaling.
arXiv preprint arXiv:1711.08506 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this paper, we revisit the problem of purely unsupervised image segmentation and propose a novel deep architecture for this problem. We borrow recent ideas from supervised semantic segmentation methods, in particular by concatenating two fully convolutional networks together into an autoencoder--one for encoding and one for decoding. The encoding layer produces a k-way pixelwise prediction, and both the reconstruction error of the autoencoder as well as the normalized cut produced by the encoder are jointly minimized during training. When combined with suitable postprocessing involving conditional random field smoothing and hierarchical segmentation, our resulting algorithm achieves impressive results on the benchmark Berkeley Segmentation Data Set, outperforming a number of competing methods.
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
method 1polarities
use method 1representative citing papers
A method for incremental semantic class discovery that builds a segmented 3D map from RGBD frames and identifies new classes from unlabeled coherent regions, achieving 10.7 Hz updates on NYUDv2.
DW-Net improves the accuracy versus computational cost Pareto front over standard U-Nets for 2D and 3D multi-scale flow benchmarks by stacking multiple waves while keeping training settings identical.
The study evaluates different Conditional Random Fields for post-processing image segmentation on low-quality satellite imagery and high-quality aerial photographs to identify the best approach for improved clarity.
DeepTEGINN is a deep learning toolbox combining image processing and graph theory to automate graph extraction from brain tissue images as an alternative to manual tracing.
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
citing papers explorer
-
Trajectory-Agnostic Asteroid Detection in TESS with Deep Learning
A W-Net deep learning model detects asteroids in TESS data independently of trajectory by rotating training image cubes and using adaptive normalization for data scaling.
-
Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
A method for incremental semantic class discovery that builds a segmented 3D map from RGBD frames and identifies new classes from unlabeled coherent regions, achieving 10.7 Hz updates on NYUDv2.
-
Deep Wave Network for Modeling Multi-Scale Physical Dynamics
DW-Net improves the accuracy versus computational cost Pareto front over standard U-Nets for 2D and 3D multi-scale flow benchmarks by stacking multiple waves while keeping training settings identical.
-
Post Processing of image segmentation using Conditional Random Fields
The study evaluates different Conditional Random Fields for post-processing image segmentation on low-quality satellite imagery and high-quality aerial photographs to identify the best approach for improved clarity.
-
DeepTEGINN: Deep Learning Based Tools to Extract Graphs from Images of Neural Networks
DeepTEGINN is a deep learning toolbox combining image processing and graph theory to automate graph extraction from brain tissue images as an alternative to manual tracing.
-
Understanding Deep Learning Techniques for Image Segmentation
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.