Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency
Reads0
Chats0
TLDR
This work proposes an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images, and achieves significant improvement over existing methods, especially when trained with very few labeled samples.Abstract:
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification with limited data has only drawn attention recently. In this work, we propose an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images. The proposed approach relies on adversarial training with a feature matching loss to learn from unlabeled images. It uses two network branches that link semi-supervised classification with semi-supervised segmentation including self-training. The dual-branch approach reduces both the low-level and the high-level artifacts typical when training with few labels. The approach attains significant improvement over existing methods, especially when trained with very few labeled samples. On several standard benchmarks—PASCAL VOC 2012, PASCAL-Context, and Cityscapes—the approach achieves new state-of-the-art in semi-supervised learning.read more
Citations
More filters
Proceedings ArticleDOI
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
TL;DR: In this article, a cross pseudo supervision (CPS) regularization is proposed to encourage high similarity between the predictions of two segmentation networks for the same input image, and expand training data by using the unlabeled data with pseudo labels.
Proceedings ArticleDOI
DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Yuxuan Zhang,Huan Ling,Jun Gao,Kangxue Yin,Jean-Francois Lafleche,Adela Barriuso,Antonio Torralba,Sanja Fidler +7 more
TL;DR: DatasetGAN as discussed by the authors uses GANs to generate high-quality semantically segmented images, which can then be used for training any computer vision architecture just as real datasets are.
Book ChapterDOI
Guided Collaborative Training for Pixel-Wise Semi-Supervised Learning
TL;DR: Guided Collaborative Training (GCT) as discussed by the authors is a semi-supervised learning framework for pixel-wise tasks, which can be applied to a wide range of pixelwise tasks without structural adaptation.
Posted Content
Semi-supervised semantic segmentation needs strong, varied perturbations
TL;DR: This work finds that adapted variants of the recently proposed CutOut and CutMix augmentation techniques yield state-of-the-art semi-supervised semantic segmentation results in standard datasets.
Posted Content
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
TL;DR: This work presents a simple and novel re-design of pseudo-labeling to generate well-calibrated structured pseudo labels for training with unlabeled or weakly-labeled data and demonstrates the effectiveness of the proposed pseudo- labeling strategy in both low-data and high-data regimes.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.