Related papers: Deep Steganalysis: End-to-End Learning with Superv…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…

We propose a novel deep learning method for local self-supervised representation learning that does not require labels nor end-to-end backpropagation but exploits the natural order in data instead. Inspired by the observation that…

End-to-end analyses of data from high-energy physics experiments using machine and deep learning techniques have emerged in recent years. These analyses use deep learning algorithms to go directly from low-level detector information…

In this paper, we present a novel end-to-end network architecture to estimate fundamental matrix directly from stereo images. To establish a complete working pipeline, different deep neural networks in charge of finding correspondences in…

Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously…

In recent times, deep learning-based steganalysis classifiers became popular due to their state-of-the-art performance. Most deep steganalysis classifiers usually extract noise residuals using high-pass filters as preprocessing steps and…

The success of deep learning is frequently described as the ability to train all parameters of a network on a specific application in an end-to-end fashion. Yet, several design choices on the camera level, including the pixel layout of the…

We introduce the Deep Edge Filter, a novel approach that applies high-pass filtering to deep neural network features to improve model generalizability. Our method is motivated by our hypothesis that neural networks encode task-relevant…

For almost 10 years, the detection of a hidden message in an image has been mainly carried out by the computation of Rich Models (RM), followed by classification using an Ensemble Classifier (EC). In 2015, the first study using a…

We present a state-of-the-art image recognition system, Deep Image, developed using end-to-end deep learning. The key components are a custom-built supercomputer dedicated to deep learning, a highly optimized parallel algorithm using new…

Deep networks have recently enjoyed enormous success when applied to recognition and classification problems in computer vision, but their use in graphics problems has been limited. In this work, we present a novel deep architecture that…

Learning fine-grained image similarity is a challenging task. It needs to capture between-class and within-class image differences. This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric…

Machine learning approaches to auditory object recognition are traditionally based on engineered features such as those derived from the spectrum or cepstrum. More recently, end-to-end classification systems in image and auditory…

Deep learning is regarded as a promising solution for reversible steganography. There is an accelerating trend of representing a reversible steo-system by monolithic neural networks, which bypass intermediate operations in traditional…

Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…

Adoption of deep learning in image steganalysis is still in its initial stage. In this paper we propose a generic hybrid deep-learning framework for JPEG steganalysis incorporating the domain knowledge behind rich steganalytic models. Our…

Recent advances in incorporating neural networks into particle filters provide the desired flexibility to apply particle filters in large-scale real-world applications. The dynamic and measurement models in this framework are learnable…

We present a novel end-to-end deep learning-based adaptation control algorithm for frequency-domain adaptive system identification. The proposed method exploits a deep neural network to map observed signal features to corresponding…

Deep learning based methods have seen a massive rise in popularity for hyperspectral image classification over the past few years. However, the success of deep learning is attributed greatly to numerous labeled samples. It is still very…

Deep kernel map networks have shown excellent performances in various classification problems including image annotation. Their general recipe consists in aggregating several layers of singular value decompositions (SVDs) -- that map data…