Related papers: Parallel Multiscale Autoregressive Density Estimat…

The effectiveness of Convolutional Neural Networks (CNNs)in classifying image data has been thoroughly demonstrated. In order to explain the classification to humans, methods for visualizing classification evidence have been developed in…

In this paper, we introduce a simple but quite effective recognition framework dubbed D-PCN, aiming at enhancing feature extracting ability of CNN. The framework consists of two parallel CNNs, a discriminator and an extra classifier which…

Despite the substantial progress in recent years, the image captioning techniques are still far from being perfect.Sentences produced by existing methods, e.g. those based on RNNs, are often overly rigid and lacking in variability. This…

Convolutional Neural Networks (CNNs) have exhibited great performance in discriminative feature learning for complex visual tasks. Besides discrimination power, interpretability is another important yet under-explored property for CNNs. One…

Language Models based on recurrent neural networks have dominated recent image caption generation tasks. In this paper, we introduce a Language CNN model which is suitable for statistical language modeling tasks and shows competitive…

Measuring the naturalness of images is important to generate realistic images or to detect unnatural regions in images. Additionally, a method to measure naturalness can be complementary to Convolutional Neural Network (CNN) based features,…

Convolutional Networks have dominated the field of computer vision for the last ten years, exhibiting extremely powerful feature extraction capabilities and outstanding classification performance. The main strategy to prolong this trend…

Convolutional neural networks (CNNs) tend to become a standard approach to solve a wide array of computer vision problems. Besides important theoretical and practical advances in their design, their success is built on the existence of…

Recently, it has been demonstrated that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have concentrated on raising the quantitative quality of super-resolved (SR)…

This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application. Prior neural networks, such as ResNet, tend…

The ever-increasing data demand craves advancements in high-speed and energy-efficient computing hardware. Analog optical neural network (ONN) processors have emerged as a promising solution, offering benefits in bandwidth and energy…

Diffusion models have become a leading method for generative modeling of both image and scientific data. As these models are costly to train and \emph{evaluate}, reducing the inference cost for diffusion models remains a major goal.…

We explore architectures for general pixel-level prediction problems, from low-level edge detection to mid-level surface normal estimation to high-level semantic segmentation. Convolutional predictors, such as the fully-convolutional…

We propose a generative model that can infer a distribution for the underlying spatial signal conditioned on sparse samples e.g. plausible images given a few observed pixels. In contrast to sequential autoregressive generative models, our…

The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all…

Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. Several works have extended GANs to image inpainting by conditioning the generation with parts of the image to be reconstructed. Despite their…

The Convolutional Neural Network (CNN) has achieved great success in image classification. The classification model can also be utilized at image or patch level for many other applications, such as object detection and segmentation. In this…

Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence. Although some works use the Convolution…

In the last few years, we have witnessed the rise of a series of deep learning methods to generate synthetic images that look extremely realistic. These techniques prove useful in the movie industry and for artistic purposes. However, they…

Maintaining natural image statistics is a crucial factor in restoration and generation of realistic looking images. When training CNNs, photorealism is usually attempted by adversarial training (GAN), that pushes the output images to lie on…