Related papers: Structured Binary Neural Networks for Accurate Ima…
We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model,…
Brain tumor classification using MRI images is critical in medical diagnostics, where early and accurate detection significantly impacts patient outcomes. While recent advancements in deep learning (DL), particularly CNNs, have shown…
Graph Neural Networks have a limitation of solely processing features on graph nodes, neglecting data on high-dimensional structures such as edges and triangles. Simplicial Convolutional Neural Networks (SCNN) represent higher-order…
Deep-neural-network-based image reconstruction has demonstrated promising performance in medical imaging for under-sampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is…
Quantization based model compression serves as high performing and fast approach for inference that yields models which are highly compressed when compared to their full-precision floating point counterparts. The most extreme quantization…
This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary…
Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount…
Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel approach to decomposing multiple human bodies into semantic part…
Since convolutional neural networks perform well in learning generalizable image priors from large-scale data, these models have been widely used in image denoising tasks. However, the computational complexity increases dramatically as well…
Segmentation of white matter lesions and deep grey matter structures is an important task in the quantification of magnetic resonance imaging in multiple sclerosis. In this paper we explore segmentation solutions based on convolutional…
This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may…
Automated medical image analysis has a significant value in diagnosis and treatment of lesions. Brain tumors segmentation has a special importance and difficulty due to the difference in appearances and shapes of the different tumor regions…
Word spotting has become a field of strong research interest in document image analysis over the last years. Recently, AttributeSVMs were proposed which predict a binary attribute representation. At their time, this influential method…
Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution…
Deep learning, e.g., convolutional neural networks (CNNs), has achieved great success in image processing and computer vision especially in high level vision applications such as recognition and understanding. However, it is rarely used to…
We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.…
Convolutional Neural Networks (CNNs) have been successful in solving tasks in computer vision including medical image segmentation due to their ability to automatically extract features from unstructured data. However, CNNs are sensitive to…
Given a pedestrian image as a query, the purpose of person re-identification is to identify the correct match from a large collection of gallery images depicting the same person captured by disjoint camera views. The critical challenge is…
This paper describes a CNN where all CNN style 2D convolution operations that lower to matrix matrix multiplication are fully binary. The network is derived from a common building block structure that is consistent with a constructive proof…
Convolutional neural networks (CNNs) have received increasing attention over the last few years. They were initially conceived for image categorization, i.e., the problem of assigning a semantic label to an entire input image. In this paper…