Joint Training of Generic CNN-CRF Models with Stochastic Optimization

Kirillov, Alexander; Schlesinger, Dmitrij; Zheng, Shuai; Savchynskyy, Bogdan; Torr, Philip H. S.; Rother, Carsten

doi:10.1007/978-3-319-54184-6_14

Cited by 14 publications

(15 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where T m and F m are the sets of labels and features in the m-th frame in the training dataset. Generally, this minimization problem is intractable and various approximation techniques, such as contrastive divergence (CD) [24] or its variant [25], are employed in existing DNN-CRF approaches. Our problem of important/unimportant people classification, however, basically is small.…”

Section: Trainingmentioning

confidence: 99%

Finding Important People in a Video Using Deep Neural Networks with Conditional Random Fields

Otani

Nishida

Nakashima

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Finding important regions is essential for applications, such as content-aware video compression and video retargeting to automatically crop a region in a video for small screens. Since people are one of main subjects when taking a video, some methods for finding important regions use a visual attention model based on face/pedestrian detection to incorporate the knowledge that people are important. However, such methods usually do not distinguish important people from passers-by and bystanders, which results in false positives. In this paper, we propose a deep neural network (DNN)-based method, which classifies a person into important or unimportant, given a video containing multiple people in a single frame and captured with a hand-held camera. Intuitively, important/unimportant labels are highly correlated given that corresponding people's spatial motions are similar. Based on this assumption, we propose to boost the performance of our important/unimportant classification by using conditional random fields (CRFs) built upon the DNN, which can be trained in an end-to-end manner. Our experimental results show that our method successfully classifies important people and the use of a DNN with CRFs improves the accuracy.

show abstract

Section: Trainingmentioning

confidence: 99%

Finding Important People in a Video Using Deep Neural Networks with Conditional Random Fields

Otani

Nishida

Nakashima

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…The convolutional layer only connects each neuron of the output to a small region (window) of the input which is referred to as a feature map, thus greatly reducing the number of parameters. CNN has demonstrated itself as one of the most successful tools in the area of computer vision [40][41][42][43][44], and more recently, it also found applications in natural language processing [45][46][47][48][49][50].…”

Section: Introductionmentioning

confidence: 99%

Hybrid quantum-classical convolutional neural networks

Liu

Lim

Wood

et al. 2021

Sci. China Phys. Mech. Astron.

142

View full text Add to dashboard Cite

Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or contexts. In parallel, quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations, which could generate distributions that are hard for a classical computer to produce. Here we propose a hybrid quantum-classical convolutional neural network (QCCNN), inspired by convolutional neural networks (CNNs) but adapted to quantum computing to enhance the feature mapping process. QCCNN is friendly to currently noisy intermediate-scale quantum computers, in terms of both number of qubits as well as circuit's depths, while retaining important features of classical CNN, such as nonlinearity and scalability. We also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical algorithms. We demonstrate the potential of this architecture by applying it to a Tetris dataset, and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN with the same structure.

show abstract

“…CRFs have been used to model important geometric characteristics such as shape, region connectivity, contextual information between regions and so on. For these reasons, there has been a recent trend on exploring the integration of CNN and CRF methods [25], [26], [27], [28]. For example, Liu et.…”

Section: Introductionmentioning

confidence: 99%

Conditional Random Field and Deep Feature Learning for Hyperspectral Image Classification

Alam

Zhou

Liew

et al. 2019

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, convolutional neural network (CNN) has established itself as a powerful model in segmentation and classification by demonstrating excellent performances. The use of a graphical model such as a conditional random field (CRF) contributes further in capturing contextual information and thus improving the segmentation performance. In this paper, we propose a method to segment hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF. We use multiple spectral cubes to learn deep features using CNN, and then formulate deep CRF with CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between patches consisting of three-dimensional data cubes. Furthermore, we introduce a deep deconvolution network that improves the segmentation masks. We also introduced a new dataset and experimented our proposed method on it along with several widely adopted benchmark datasets to evaluate the effectiveness of our method. By comparing our results with those from several state-of-the-art models, we show the promising potential of our method.

show abstract

Joint Training of Generic CNN-CRF Models with Stochastic Optimization

Cited by 14 publications

References 32 publications

Finding Important People in a Video Using Deep Neural Networks with Conditional Random Fields

Finding Important People in a Video Using Deep Neural Networks with Conditional Random Fields

Hybrid quantum-classical convolutional neural networks

Conditional Random Field and Deep Feature Learning for Hyperspectral Image Classification

Contact Info

Product

Resources

About