Related papers: Tiny CNN for feature point description for documen…

In this study, we focus on extracting knowledgeable snippets and annotating knowledgeable documents from Web corpus, consisting of the documents from social media and We-media. Informally, knowledgeable snippets refer to the text describing…

Research has shown that Convolutional Neural Networks (CNN) can be effectively applied to text classification as part of a predictive coding protocol. That said, most research to date has been conducted on data sets with short documents…

We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide anchor structures for learned filters, which localize, score…

There have been numerous image restoration methods based on deep convolutional neural networks (CNNs). However, most of the literature on this topic focused on the network architecture and loss functions, while less detailed on the training…

Learning discriminative representations of unlabelled data is a challenging task. Contrastive self-supervised learning provides a framework to learn meaningful representations using learned notions of similarity measures from simple pretext…

The fundamental problem in short-text classification is \emph{feature sparseness} -- the lack of feature overlap between a trained model and a test instance to be classified. We propose \emph{ClassiNet} -- a network of classifiers trained…

This paper evaluates the viability of using fixed language models for training text classification networks on low-end hardware. We combine language models with a CNN architecture and put together a comprehensive benchmark with 8 datasets…

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating…

In this paper, we present an ultra lightweight system that can effectively recognize different circuit components in an image with very limited training data. Along with the system, we also release the data set we created for the task. A…

We address the problem of predicting similarity between a pair of handwritten document images written by different individuals. This has applications related to matching and mining in image collections containing handwritten content. A…

A large number of deep learning models have been proposed for the text matching problem, which is at the core of various typical natural language processing (NLP) tasks. However, existing deep models are mainly designed for the semantic…

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the…

Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform…

As in many other scientific domains, we face a fundamental problem when using machine learning to identify proteins from mass spectrometry data: large ground truth datasets mapping inputs to correct outputs are extremely difficult to…

Understanding how a complex machine learning model makes a classification decision is essential for its acceptance in sensitive areas such as health care. Towards this end, we present PatchNet, a method that provides the features indicative…

Convolutional Neural Networks have made their mark in various fields of computer vision in recent years. They have achieved state-of-the-art performance in the field of document analysis as well. However, CNNs require a large amount of…

The purpose of mid-level visual element discovery is to find clusters of image patches that are both representative and discriminative. Here we study this problem from the prospective of pattern mining while relying on the recently…

A foundational task for the digital analysis of documents is text line segmentation. However, automating this process with deep learning models is challenging because it requires large, annotated datasets that are often unavailable for…

Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models are gaining increasing popularity for text classification due…