Related papers: Vehicle classification using ResNets, localisation…
Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers…
This paper presents a Convolutional Neural Network (CNN) approach for counting and locating objects in high-density imagery. To the best of our knowledge, this is the first object counting and locating method based on a feature map…
Data-augmentation is key to the training of neural networks for image classification. This paper first shows that existing augmentations induce a significant discrepancy between the typical size of the objects seen by the classifier at…
We trained a deep all-convolutional neural network with masked global pooling to perform single-label classification for acoustic scene classification and multi-label classification for domestic audio tagging in the DCASE-2016 contest. Our…
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224x224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this…
We introduce a novel weighted convolution operator that enhances traditional convolutional neural networks (CNNs) by integrating a spatial density function into the convolution operator. This extension enables the network to differentially…
Object detection systems based on the deep convolutional neural network (CNN) have recently made ground- breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are…
We propose an efficient transfer learning method for adapting ImageNet pre-trained Convolutional Neural Network (CNN) to fine-grained image classification task. Conventional transfer learning methods typically face the trade-off between…
Deep learning methods have been successfully applied to remote sensing problems for several years. Among these methods, CNN based models have high accuracy in solving the land classification problem using satellite or aerial images.…
While novel computer vision architectures are gaining traction, the impact of model architectures is often related to changes or exploring in training methods. Identity mapping-based architectures ResNets and DenseNets have promised…
Cervical cancer is the second most common cancer among women and a leading cause of mortality. Many attempts have been made to develop an effective Computer Aided Diagnosis (CAD) system; however, their performance remains limited. Using…
Promising results for subjective image quality prediction have been achieved during the past few years by using convolutional neural networks (CNN). However, the use of CNNs for high resolution image quality assessment remains a challenge,…
In this paper, we present a new dataset for "distracted driver" posture estimation. In addition, we propose a novel system that achieves 95.98% driving posture estimation classification accuracy. The system consists of a…
We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a…
Rock Classification is an essential geological problem since it provides important formation information. However, exploration on this problem using convolutional neural networks is not sufficient. To tackle this problem, we propose two…
In speaker verification, the extraction of voice representations is mainly based on the Residual Neural Network (ResNet) architecture. ResNet is built upon convolution layers which learn filters to capture local spatial patterns along all…
Channel pruning is one of the predominant approaches for accelerating deep neural networks. Most existing pruning methods either train from scratch with a sparsity inducing term such as group lasso, or prune redundant channels in a…
Recent results suggest that state-of-the-art saliency models perform far from optimal in predicting fixations. This lack in performance has been attributed to an inability to model the influence of high-level image features such as objects.…
Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of…
This paper proposes to learn high-performance deep ConvNets with sparse neural connections, referred to as sparse ConvNets, for face recognition. The sparse ConvNets are learned in an iterative way, each time one additional layer is…