Pixel-Level Matching for Video Object Segmentation Using Convolutional Neural Networks
Jae Shin Yoon,Francois Rameau,Junsik Kim,Seokju Lee,Seunghak Shin,In So Kweon +5 more
- pp 2186-2195
Reads0
Chats0
TLDR
In this paper, the pixel-level similarity between two object units is used to distinguish the target area from the background on the basis of the pixel level similarity between the two objects.Abstract:
We propose a novel video object segmentation algorithm based on pixel-level matching using Convolutional Neural Networks (CNN). Our network aims to distinguish the target area from the background on the basis of the pixel-level similarity between two object units. The proposed network represents a target object using features from different depth layers in order to take advantage of both the spatial details and the category-level semantic information. Furthermore, we propose a feature compression technique that drastically reduces the memory requirements while maintaining the capability of feature representation. Two-stage training (pretraining and fine-tuning) allows our network to handle any target object regardless of its category (even if the object’s type does not belong to the pre-training data) or of variations in its appearance through a video sequence. Experiments on large datasets demonstrate the effectiveness of our model - against related methods - in terms of accuracy, speed, and stability. Finally, we introduce the transferability of our network to different domains, such as the infrared data domain.read more
Citations
More filters
Proceedings ArticleDOI
Fast Online Object Tracking and Segmentation: A Unifying Approach
TL;DR: This method improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task, and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second.
Journal ArticleDOI
A survey on deep learning and its applications
TL;DR: The structural principle, the characteristics, and some kinds of classic models of deep learning, such as stacked auto encoder, deep belief network, deep Boltzmann machine, and convolutional neural network are described.
Proceedings ArticleDOI
Fast Video Object Segmentation by Reference-Guided Mask Propagation
TL;DR: A deep Siamese encoder-decoder network is proposed that is designed to take advantage of mask propagation and object detection while avoiding the weaknesses of both approaches, and achieves accuracy competitive with state-of-the-art methods while running in a fraction of time compared to others.
Proceedings ArticleDOI
Efficient Video Object Segmentation via Network Modulation
TL;DR: In this paper, a modulator is trained to manipulate the intermediate layers of the segmentation network given limited visual and spatial information of the target object, which achieves similar accuracy as fine-tuning.
Proceedings ArticleDOI
See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks
TL;DR: In this paper, a co-attention Siamese network (COSNet) is proposed to address the unsupervised video object segmentation task from a holistic view.
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: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
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.
Proceedings ArticleDOI
Learning Multi-domain Convolutional Neural Networks for Visual Tracking
Hyeonseob Nam,Bohyung Han +1 more
TL;DR: A novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network using a large set of videos with tracking ground-truths to obtain a generic target representation.
Proceedings ArticleDOI
Hierarchical Convolutional Features for Visual Tracking
TL;DR: This paper adaptively learn correlation filters on each convolutional layer to encode the target appearance and hierarchically infer the maximum response of each layer to locate targets.