• Corpus ID: 245130922

n-CPS: Generalising Cross Pseudo Supervision to n networks for Semi-Supervised Semantic Segmentation

@article{Filipiak2021nCPSGC,
  title={n-CPS: Generalising Cross Pseudo Supervision to n networks for Semi-Supervised Semantic Segmentation},
  author={D. Filipiak and Piotr Tempczyk and Marek Cygan},
  journal={ArXiv},
  year={2021},
  volume={abs/2112.07528}
}
The recent cross pseudo supervision (CPS) approach is a state-of-the-art method for semi-supervised semantic segmentation, which trains two neural networks with a custom cross supervision. As we observe that only one of those networks is used in the inference phase, we suggest using both networks using voting and generalising it to more than two networks. As a result, we present n -CPS, a generalisation of CPS that uses n simultaneously trained subnetworks that learn from each other through one… 

Figures and Tables from this paper

Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students

This paper proposes a novel Semi-supervised Learning approach, called Transformer-CNN Cohort (TCC), that consists of two stu- dents with one based on the vision transformer (ViT) and the otherbased on the CNN, and validate the TCC framework on Cityscapes and Pascal VOC 2012 datasets, which outperforms existing semi- supervised methods by a large margin.

AMM-FuseNet: Attention-Based Multi-Modal Image Fusion Network for Land Cover Mapping

Land cover mapping provides spatial information on the physical properties of the Earth’s surface for various classes of wetlands, artificial surface and constructions, vineyards, water bodies, etc.

SHREC 2022: pothole and crack detection in the road pavement using images and RGB-D data

This paper describes the methods submitted for evaluation to the SHREC 2022 track on pothole and crack detection in the road pavement and shows that the scenario is of great interest and that the use of RGB-D data is still challenging in this context.

References

SHOWING 1-10 OF 18 REFERENCES

Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

This paper proposes a novel consistency regularization approach, called cross pseudo supervision (CPS), which imposes the consistency on two segmentation networks perturbed with different initialization for the same input image.

Bootstrapping Semantic Segmentation with Regional Contrast

ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative pixels, with minimal additional memory footprint, and consistently improves performance in both semisupervised and supervised semantic segmentation methods, achieving smoother segmentation boundaries and faster convergence.

Guided Collaborative Training for Pixel-wise Semi-Supervised Learning

A new SSL framework, named Guided Collaborative Training (GCT), is presented, with two main technical contributions, that addresses the issues caused by the dense outputs through a novel flaw detector and can be applied to a wide range of pixel-wise tasks without structural adaptation.

Semi-Supervised Semantic Segmentation With Cross-Consistency Training

This work observes that for semantic segmentation, the low-density regions are more apparent within the hidden representations than within the inputs, and proposes cross-consistency training, where an invariance of the predictions is enforced over different perturbations applied to the outputs of the encoder.

Semi-supervised semantic segmentation needs strong, high-dimensional perturbations

This work analyzes the problem of semantic segmentation and finds that the data distribution does not exhibit low density regions separating classes and offers this as an explanation for why semi-supervised segmentation is a challenging problem.

Deep High-Resolution Representation Learning for Visual Recognition

The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems.

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Patches are cut and pasted among training images where the ground truth labels are also mixed proportionally to the area of the patches, and CutMix consistently outperforms state-of-the-art augmentation strategies on CIFAR and ImageNet classification tasks, as well as on ImageNet weakly-supervised localization task.

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network.

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks, but it becomes unwieldy when learning large datasets, so Mean Teacher, a method that averages model weights instead of label predictions, is proposed.

Pyramid Scene Parsing Network

This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.