Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network

  title={Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network},
  author={Suha Kwak and Seunghoon Hong and Bohyung Han},
  booktitle={AAAI Conference on Artificial Intelligence},
We propose a weakly supervised semantic segmentation algorithm based on deep neural networks, which relies on imagelevel class labels only. [] Key Method To this end, we propose Superpixel Pooling Network (SPN), which utilizes superpixel segmentation of input image as a pooling layout to reflect low-level image structure for learning and inferring semantic segmentation. The initial annotations generated by SPN are then used to learn another neural network that estimates pixelwise semantic labels.

Figures and Tables from this paper

Weakly Supervised Semantic Segmentation Based on Superpixel Sampling Clustering Networks

    Junsheng XiaoHuajun XuXiaojun Ma
    Computer Science
    Proceedings of the 2nd International Conference on Computer Science and Software Engineering - CSSE 2019
  • 2019
In this paper, the non-conductible superpixel sampling algorithm SLIC is transformed into derivable by relaxing restrictions, added to the deep convolutional neural network to achieve end-to-end training, and the center of the superpixel is dynamically obtained step by step.

Weakly Supervised Semantic Segmentation by Multiple Group Cosegmentation

A new strategy, which first obtains the foregrounds of each class by multiple group cosegmentation, and then combines the results to form the semantic segmentation, is proposed, which outperforms many existing weakly supervised semantic segmentsation methods.

Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation

    Jiwoon AhnSuha Kwak
    Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
On the PASCAL VOC 2012 dataset, a DNN learned with segmentation labels generated by the method outperforms previous models trained with the same level of supervision, and is even as competitive as those relying on stronger supervision.

GraphNet: Learning Image Pseudo Annotations for Weakly-Supervised Semantic Segmentation

This paper proposes a novel graph convolutional network-based method, called GraphNet, to learn pixel-wise labels from weak annotations, which is effective to predict the pixel labels with scribble or bounding box annotations.

Scale-Aware Feature Network for Weakly Supervised Semantic Segmentation

The proposed SAFN uses an attention module to learn the relative weights of multi-scale features in a modified fully convolutional network with dilated convolutions, which leads to efficient enlargements of the receptive fields of view and produces dense object localization maps.

SAL:Selection and Attention Losses for Weakly Supervised Semantic Segmentation

An end-to-end semantic segmentation network SAL-Net is proposed, which reaches state-of-the-art performance with mean IoU (mIoU) as 62.5% and 66.6% on the test set by taking VGG16 network and ResNet101 network as the baselines respectively, which demonstrates the superiority of the proposed algorithm over eight representative weakly supervised segmentation methods.

SPMF-Net: Weakly Supervised Building Segmentation by Combining Superpixel Pooling and Multi-Scale Feature Fusion

The proposed weakly supervised semantic segmentation method takes the image-level label as supervision information in a classification network that combines superpixel pooling and multi-scale feature fusion structures to improve the intactness and boundary accuracy of a detected building.

Transferable Semi-supervised Semantic Segmentation

A novel transferable semi-supervised semantic segmentation model that can transfer the learned segmentation knowledge from a few strong categories with pixel- level annotations to unseen weak categories with only image-level annotations is proposed, significantly broadening the applicable territory of deep segmentation models.

Weakly Supervised Learning with Deep Convolutional Neural Networks for Semantic Segmentation: Understanding Semantic Layout of Images with Minimum Human Supervision

This article provides a comprehensive overview of weakly supervised approaches for semantic segmentation, describing how the approaches overcome the limitations and discuss research directions worthy of investigation to improve performance.

Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation

The decoupled architecture enables the algorithm to learn classification and segmentation networks separately based on the training data with image-level and pixel-wise class labels, respectively, and facilitates to reduce search space for segmentation effectively by exploiting class-specific activation maps obtained from bridging layers.

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Expectation-Maximization (EM) methods for semantic image segmentation model training under weakly supervised and semi-supervised settings are developed and extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 image segmentsation benchmark, while requiring significantly less annotation effort.

From image-level to pixel-level labeling with Convolutional Networks

A Convolutional Neural Network-based model is proposed, which is constrained during training to put more weight on pixels which are important for classifying the image, and which beats the state of the art results in weakly supervised object segmentation task by a large margin.

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF).

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

This work proposes Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space of a CNN, and demonstrates the generality of this new learning framework.

Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation

This work shows how to improve semantic segmentation through the use of contextual information, specifically, ' patch-patch' context between image regions, and 'patch-background' context, and formulate Conditional Random Fields with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches.

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

    Jifeng DaiKaiming HeJian Sun
    Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
This paper proposes a method that achieves competitive accuracy but only requires easily obtained bounding box annotations, and yields state-of-the-art results on PASCAL VOC 2012 and PASCal-CONTEXT.

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

This paper proposes to use scribbles to annotate images, and develops an algorithm to train convolutional networks for semantic segmentation supervised by scribbles, which shows excellent results on the PASCALCONTEXT dataset thanks to extra inexpensive scribble annotations.

Fully Convolutional Multi-Class Multiple Instance Learning

This work proposes a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network that exploits the further supervision given by images with multiple labels.