Learning to segment with image-level annotations

Wei, Yunchao; Liang, Xiaodan; Chen, Yunpeng; Jie, Zequn; Xiao, Yanhui; Zhao, Yao; Yan, Shuicheng

doi:10.1016/j.patcog.2016.01.015

Cited by 96 publications

(70 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…expectation maximization (EM) [33] , curriculum learning [34] , self-paced learning [35] , etc. ) are widely used in the weakly-supervised tasks [9,[36][37][38][39][40][41] . For example, [36] adopts the expectation maximization (EM) algorithm to dynamically predict semantic foreground and background pixels by using an alternative training procedure.…”

Section: Iterative Learning Methodsmentioning

confidence: 99%

Weakly-supervised object detection via mining pseudo ground truth bounding-boxes

Zhang

Bai

Ding

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

a b s t r a c tRecently, weakly-supervised object detection has attracted much attention, since it does not require expensive bounding-box annotations while training the network. Although significant progress has also been made, there is still a large gap on the performance between weakly-supervised and fully-supervised object detection. To mitigate this gap, some works try to use the pseudo ground truths generated by a weakly-supervised detector to train a supervised detector. However, such approaches incline to find the most representative parts instead of the whole body of an object, and only seek one ground truth bounding-box per class even though many same-class instances exist in an image. To address these issues, we propose a weakly-supervised to fully-supervised framework (W2F), where a weakly-supervised detector is implemented using multiple instance learning. And then, we propose a pseudo ground-truth excavation (PGE) algorithm to find the accurate pseudo ground truth bounding-box for each instance. Moreover, the pseudo ground-truth adaptation (PGA) algorithm is designed to further refine those pseudo ground truths mined by PGE algorithm. Finally, the mined pseudo ground truths are used as supervision to train a fully-supervised detector. Additionally, we also propose an iterative ground-truth learning (IGL) approach, which enhances the quality of the pseudo ground truths by using the predictions of the fullysupervised detector iteratively. Extensive experiments on the challenging PASCAL VOC 2007 and 2012 benchmarks strongly demonstrate the effectiveness of our method. We obtain 53.1% and 49.4% mAP on VOC2007 and VOC2012 respectively, which is a significant improvement over previous state-of-the-art methods.

show abstract

Section: Iterative Learning Methodsmentioning

confidence: 99%

Weakly-supervised object detection via mining pseudo ground truth bounding-boxes

Zhang

Bai

Ding

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…To improve the localization performance, some approaches [58][59][60][61] have proposed to exploit the notion of objectness, either by incorporating it in the loss function [58,59], or by employing pre-trained network as external objectness module [60,61]. Another promising way to improve the segmentation performance is to utilize additional weakly supervised images, such as web images, to train CNNs, such as [62,63].…”

Section: Weakly Supervised Semantic Segmentationmentioning

confidence: 99%

A review of semantic segmentation using deep neural networks

Guo

Liu

Georgiou

et al. 2017

Int J Multimed Info Retr

618

263

View full text Add to dashboard Cite

During the long history of computer vision, one of the grand challenges has been semantic segmentation which is the ability to segment an unknown image into different parts and objects (e.g., beach, ocean, sun, dog, swimmer). Furthermore, segmentation is even deeper than object recognition because recognition is not necessary for segmentation. Specifically, humans can perform image segmentation without even knowing what the objects are (for example, in satellite imagery or medical X-ray scans, there may be several objects which are unknown, but they can still be segmented within the image typically for further investigation). Performing segmentation without knowing the exact identity of all objects in the scene is an important part of our visual understanding process which can give us a powerful model to understand the world and also be used to improve or augment existing computer vision techniques. Herein this work, we review the field of semantic segmentation as pertaining to deep convolutional neural networks. We provide comprehensive coverage of the top approaches and summarize the strengths, weaknesses and major challenges.

show abstract

“…Here we review the CNN-based approaches as these methods [13,14,15,16,17,18,19,20,21,22] provide good segmentation quality on the challenging PASCAL VOC benchmark. Early works [13,14,16] extend the MultipleInstance Learning (MIL) [24] framework for weakly supervised semantic segmentation, where the loss functions are built on the image tags level.…”

Section: Related Workmentioning

confidence: 99%

“…Image tags represent which object class(es) are present in the image. They are usually much easier and faster to obtain than the other human annotations described above, and have thus been used in many weakly supervised semantic segmentation methods [13,14,15,16,17,18,19,20,21,22]. However, as opposed to the segmentation masks obtained by the pixel-wise annotations, image tags do not indicate the location of the object(s) in the image, therefore making semantic segmentation much more challenging.…”

Section: Introductionmentioning

confidence: 99%

Webly Supervised Semantic Segmentation

Jin

Segovia

Süsstrunk

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We propose a weakly supervised semantic segmentation algorithm that uses image tags for supervision. We apply the tags in queries to collect three sets of web images, which encode the clean foregrounds, the common backgrounds, and realistic scenes of the classes. We introduce a novel three-stage training pipeline to progressively learn semantic segmentation models. We first train and refine a class-specific shallow neural network to obtain segmentation masks for each class. The shallow neural networks of all classes are then assembled into one deep convolutional neural network for end-to-end training and testing. Experiments show that our method notably outperforms previous state-of-the-art weakly supervised semantic segmentation approaches on the PASCAL VOC 2012 segmentation benchmark. We further apply the class-specific shallow neural networks to object segmentation and obtain excellent results.

show abstract

Learning to segment with image-level annotations

Cited by 96 publications

References 22 publications

Weakly-supervised object detection via mining pseudo ground truth bounding-boxes

Weakly-supervised object detection via mining pseudo ground truth bounding-boxes

A review of semantic segmentation using deep neural networks

Webly Supervised Semantic Segmentation

Contact Info

Product

Resources

About