Semi-supervised semantic segmentation is the task of doing semantic segmentation in a semi-supervised way.
( Image credit: AdaptSegNet )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach.
Ranked #3 on Visual Object Tracking on YouTube-VOS
We propose a method for semi-supervised semantic segmentation using an adversarial network.
In addition, our work presents a comprehensive analysis of different GAN architectures for semi-supervised segmentation, showing recent techniques like feature matching to yield a higher performance than conventional adversarial training approaches.
Deep convolutional neural networks (DCNNs) trained on a large number of images with strong pixel-level annotations have recently significantly pushed the state-of-art in semantic image segmentation.
We propose a novel deep neural network architecture for semi-supervised semantic segmentation using heterogeneous annotations.
To leverage the unlabeled examples, we enforce a consistency between the main decoder predictions and those of the auxiliary decoders, taking as inputs different perturbed versions of the encoder's output, and consequently, improving the encoder's representations.
The ability to understand visual information from limited labeled data is an important aspect of machine learning.
Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are unsatisfactory due to their need for dense outputs.