Book ChapterDOI
Weakly-Supervised Semantic Segmentation by Redistributing Region Scores Back to the Pixels
Josip Krapac,Siniša Šegvić +1 more
- pp 377-388
TLDR
This work addresses the problem of semantic segmentation of objects in weakly supervised setting, when only image-wide labels are available, by describing an image with a set of pre-trained convolutional features and embeding this set into a Fisher vector.Abstract:
We address the problem of semantic segmentation of objects in weakly supervised setting, when only image-wide labels are available. We describe an image with a set of pre-trained convolutional features and embed this set into a Fisher vector. We apply the learned image classifier on the set of all image regions and propagate the region scores back to the pixels. Compared to the alternatives the proposed method is simple, fast in inference, and especially in training. The method displays very good performance of on two standard semantic segmentation benchmarks.read more
Citations
More filters
Book ChapterDOI
Seed, expand and constrain: Three principles for weakly-supervised image segmentation
TL;DR: It is shown experimentally that training a deep convolutional neural network using the proposed loss function leads to substantially better segmentations than previous state-of-the-art methods on the challenging PASCAL VOC 2012 dataset.
Posted Content
Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation
TL;DR: In this article, a new loss function for weakly-supervised training of semantic image segmentation models based on three guiding principles is introduced: to seed with weak localization cues, expand objects based on the information about which classes can occur in an image, and constrain the segmentations to coincide with object boundaries.
Journal ArticleDOI
Saliency guided deep network for weakly-supervised image segmentation
Fengdong Sun,Wenhui Li +1 more
TL;DR: Li et al. as mentioned in this paper proposed a self-attention saliency method to generate subtle saliency maps and render the location cues grow as seeds by seeded region growing method to expand pixel-level labels extent.
Dissertation
Restoring the balance between stuff and things in scene understanding
TL;DR: This thesis investigates how the recognition of stuff differs from things and develops methods that are suitable to deal with both, and presents COCO-Stuff – the largest existing dataset with dense stuff and thing annotations.
Journal ArticleDOI
Bag of contour fragments for improvement of object segmentation
TL;DR: This paper proposes a specific shape feature, Fisher shape (a form of bag of contour fragments), and combines this with the appearance feature with multiple kernel learning to create a pipeline of object segmentation system.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
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.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: 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.
Posted Content
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: Faster R-CNN as discussed by the authors proposes a Region Proposal Network (RPN) to generate high-quality region proposals, which are used by Fast R-NN for detection.