Related papers: PixelCNN++: Improving the PixelCNN with Discretize…
The purpose of binary segmentation models is to determine which pixels belong to an object of interest (e.g., which pixels in an image are part of roads). The models assign a logit score (i.e., probability) to each pixel and these are…
While Mixed-integer linear programming (MILP) is NP-hard in general, practical MILP has received roughly 100--fold speedup in the past twenty years. Still, many classes of MILPs quickly become unsolvable as their sizes increase, motivating…
Joint image filters are used to transfer structural details from a guidance picture used as a prior to a target image, in tasks such as enhancing spatial resolution and suppressing noise. Previous methods based on convolutional neural…
One of the issues faced in training Generative Adversarial Nets (GANs) and their variants is the problem of mode collapse, wherein the training stability in terms of the generative loss increases as more training data is used. In this…
Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation…
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core of our method is a fully parallelizable hierarchical…
We introduce the Probabilistic Generative Adversarial Network (PGAN), a new GAN variant based on a new kind of objective function. The central idea is to integrate a probabilistic model (a Gaussian Mixture Model, in our case) into the GAN…
Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised node classification in recent years. However, the problem of insufficient supervision, together with representation collapse, largely limits the performance…
In this work we introduce a differentiable version of the Compositional Pattern Producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but the weights are learned. A Lamarckian algorithm, that combines…
Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overlapping layouts.…
In recent years there have been multiple successful attempts tackling document processing problems separately by designing task specific hand-tuned strategies. We argue that the diversity of historical document processing tasks prohibits to…
Nowadays, online screen sharing and remote cooperation are becoming ubiquitous. However, the screen content may be downsampled and compressed during transmission, while it may be displayed on large screens or the users would zoom in for…
We introduce the DNNLikelihood, a novel framework to easily encode, through Deep Neural Networks (DNN), the full experimental information contained in complicated likelihood functions (LFs). We show how to efficiently parametrise the LF,…
Particle track reconstruction is traditionally computationally challenging due to the combinatorial nature of the tracking algorithms employed. Recent developments have focused on novel algorithms with graph neural networks (GNNs), which…
Graph Neural Networks (GNNs) have achieved significant success across various domains by leveraging graph structures in data. Existing spectral GNNs, which use low-degree polynomial filters to capture graph spectral properties, may not…
Time, cost, and energy efficiency are critical considerations in Deep-Learning (DL), particularly when processing long texts. Transformers, which represent the current state of the art, exhibit quadratic computational complexity relative to…
Spectral-spatial classification of hyperspectral images has been the subject of many studies in recent years. In the presence of only very few labeled pixels, this task becomes challenging. In this paper we address the following two…
Multi-plane light converter (MPLC) designs supporting hundreds of modes are attractive in high-throughput optical communications. These photonic structures typically comprise >10 phase masks in free space, with millions of independent…
Lightweight design, as a key approach to mitigate disparity between computational requirements of deep learning models and hardware performance, plays a pivotal role in advancing application of deep learning technologies on mobile and…
These years much effort has been devoted to improving the accuracy or relevance of the recommendation system. Diversity, a crucial factor which measures the dissimilarity among the recommended items, received rather little scrutiny.…