Related papers: Reconstructing Fine-Grained Network Data using Aut…

Fine-grained annotations---e.g. dense image labels, image segmentation and text tagging---are useful in many ML applications but they are labor-intensive to generate. Moreover there are often systematic, structured errors in these…

Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task…

Federated Learning (FL) emerged as a paradigm for conducting machine learning across broad and decentralized datasets, promising enhanced privacy by obviating the need for direct data sharing. However, recent studies show that attackers can…

Over the years, computer vision researchers have spent an immense amount of effort on designing image features for the visual object recognition task. We propose to incorporate this valuable experience to guide the task of training deep…

Autoencoders are neural network formulations where the input and output of the network are identical and the goal is to identify the hidden representation in the provided datasets. Generally, autoencoders project the data nonlinearly onto a…

Semantic segmentation consists in classifying each pixel of an image by assigning it to a specific label chosen from a set of all the available ones. During the last few years, a lot of attention shifted to this kind of task. Many computer…

In this paper, we explore a novel model reusing task tailored for graph neural networks (GNNs), termed as "deep graph reprogramming". We strive to reprogram a pre-trained GNN, without amending raw node features nor model parameters, to…

Video anomaly detection is often seen as one-class classification (OCC) problem due to the limited availability of anomaly examples. Typically, to tackle this problem, an autoencoder (AE) is trained to reconstruct the input with training…

Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as…

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence. While recent approaches achieve some degree of CL in deep neural networks, they either (1) grow…

Thousands of people suffer from cranial injuries every year. They require personalized implants that need to be designed and manufactured before the reconstruction surgery. The manual design is expensive and time-consuming leading to…

Structure aware graph generation aims to generate graphs that satisfy given topological properties. It has applications in domains such as drug discovery, social network modeling, and knowledge graph construction. Unlike existing methods…

In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated…

Key to successfully deal with complex contemporary datasets is the development of tractable models that account for the irregular structure of the information at hand. This paper provides a comprehensive and unifying view of several…

In this paper, we build autoencoder based pipelines for extreme end-to-end image compression based on Ball\'e's approach, which is the state-of-the-art open source implementation in image compression using deep learning. We deepened the…

The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding, weakly supervised action recognition and localization in…

All the existing image steganography methods use manually crafted features to hide binary payloads into cover images. This leads to small payload capacity and image distortion. Here we propose a convolutional neural network based…

Reverse engineering of undocumented protocols is a common task in security analyses of networked services. The communication itself, captured in traffic traces, contains much of the necessary information to perform such a protocol reverse…

Deep neural networks have been widely used in computer vision. There are several well trained deep neural networks for the ImageNet classification challenge, which has played a significant role in image recognition. However, little work has…

Sentence embeddings are commonly used in text clustering and semantic retrieval tasks. State-of-the-art sentence representation methods are based on artificial neural networks fine-tuned on large collections of manually labeled sentence…