Search Results for author:
Found 78 papers, 37 papers with code
Pedagogical Principles in the Online Teaching of Text Mining: A Retrospection
The ongoing COVID-19 pandemic has brought online education to the forefront of pedagogical discussions.
Less is More -- Towards parsimonious multi-task models using structured sparsity
In this work, we introduce channel-wise l1/l2 group sparsity in the shared convolutional layers parameters (or weights) of the multi-task learning model.
ReLU and Addition-based Gated RNN
It is demonstrated that the novel gating mechanism can capture long-term dependencies for a standard synthetic sequence learning task while significantly reducing computational costs such that execution time is reduced by half on CPU and by one-third under encryption.
Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?
Detailed experiments have been conducted to study the robustness of self-supervised learning methods on distribution shifts and image corruptions.
Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images
Upon integrating query modifications in the DETR, we outperform prior works and achieve new state-of-the-art results with the mAP of 96. 9\%, 95. 7\% and 99. 3\% on TableBank, PubLaynet, PubTables, respectively.
Ranked #3 on
Document Layout Analysis
on PubLayNet val
Performance of data-driven inner speech decoding with same-task EEG-fMRI data fusion and bimodal models
Decoding inner speech from the brain signal via hybridisation of fMRI and EEG data is explored to investigate the performance benefits over unimodal models.
Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer
Table detection is the task of classifying and localizing table objects within document images.
Robust and Fast Vehicle Detection using Augmented Confidence Map
Vehicle detection in real-time scenarios is challenging because of the time constraints and the presence of multiple types of vehicles with different speeds, shapes, structures, etc.
NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset
In this paper, we propose a methodology for task 10 of SemEval23, focusing on detecting and classifying online sexism in social media posts.
Learning Self-Supervised Representations for Label Efficient Cross-Domain Knowledge Transfer on Diabetic Retinopathy Fundus Images
Most of the existing DR image classification methods are based on supervised learning which requires a lot of time-consuming and expensive medical domain experts-annotated data for training.
Domain Adaptable Self-supervised Representation Learning on Remote Sensing Satellite Imagery
The proposed approach investigates the knowledge transfer of selfsupervised representations across the distinct source and target data distributions in depth in the remote sensing data domain.
Deep Perceptual Similarity is Adaptable to Ambiguous Contexts
The concept of image similarity is ambiguous, and images can be similar in one context and not in another.
WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models
Our proposed method is able to generate realistic word image samples from different writer styles, by using class index styles and text content prompts without the need of adversarial training, writer recognition, or text recognition.
Ranked #1 on
HTR
on IAM
Functional Knowledge Transfer with Self-supervised Representation Learning
This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer.
Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
We study the influence of different activation functions in the output layer of deep neural network models for soft and hard label prediction in the learning with disagreement task.
A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions
Deep perceptual loss is a type of loss function in computer vision that aims to mimic human perception by using the deep features extracted from neural networks.
Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets
Hence, we also contribute a new, large Swedish bias-labelled dataset (of 2 million samples), translated from the English version and train the SotA mT5 model on it.
Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification
This work presents a novel self-supervised representation learning method to learn efficient representations without labels on images from a 3DPM sensor (3-Dimensional Particle Measurement; estimates the particle size distribution of material) utilizing RGB images and depth maps of mining material on the conveyor belt.
Multi-Task Meta Learning: learn how to adapt to unseen tasks
In particular, it focuses simultaneous learning of multiple tasks, an element of MTL and promptly adapting to new tasks, a quality of meta learning.
Ranked #93 on
Semantic Segmentation
on NYU Depth v2
T5 for Hate Speech, Augmented Data and Ensemble
Our motivation is to determine which of the recent SoTA models is best for automatic hate speech detection and what advantage methods like data augmentation and ensemble may have on the best model, if any.
Identifying and Mitigating Flaws of Deep Perceptual Similarity Metrics
This work investigates the most common DPS metric, where deep features are compared by spatial position, along with metrics comparing the averaged and sorted deep features.
Vector Representations of Idioms in Conversational Systems
We experiment with three instances of the SoTA dialogue model, Dialogue Generative Pre-trained Transformer (DialoGPT), for conversation generation.
Deep Neural Network approaches for Analysing Videos of Music Performances
While this idea was proposed in a previous study, this paper introduces several novelties: (i) Presents a novel method to overcome the class imbalance challenge and make learning possible for co-existent gestures by batch balancing approach and spatial-temporal representations of gestures.
State-of-the-art in Open-domain Conversational AI: A Survey
Results of the survey show that progress has been made with recent SoTA conversational AI, but there are still persistent challenges that need to be solved, and the female gender is more common than the male for conversational AI.
SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion
Depth completion involves recovering a dense depth map from a sparse map and an RGB image.
Ranked #1 on
Depth Completion
on KITTI Depth Completion
AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages
The language with the most transferable properties is the Nigerian Pidgin English, with a human-likeness score of 78. 1%, of which 34. 4% are unanimous.
ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language
This paper describes the system used by the Machine Learning Group of LTU in subtask 1 of the SemEval-2022 Task 4: Patronizing and Condescending Language (PCL) Detection.
A Survey of Historical Document Image Datasets
However, because of the very large variety of the actual data (e. g., scripts, tasks, dates, support systems, and amount of deterioration), the different formats for data and label representation, and the different evaluation processes and benchmarks, finding appropriate datasets is a difficult task.
Magnification Prior: A Self-Supervised Method for Learning Representations on Breast Cancer Histopathological Images
This work presents a novel self-supervised pre-training method to learn efficient representations without labels on histopathology medical images utilizing magnification factors.
Ranked #1 on
Breast Cancer Histology Image Classification
on BreakHis
(Accuracy (Inter-Patient) metric)
Breast Cancer Histology Image Classification (20% labels)
Classification Of Breast Cancer Histology Images
+2
HaT5: Hate Language Identification using Text-to-Text Transfer Transformer
We investigate the performance of a state-of-the art (SoTA) architecture T5 (available on the SuperGLUE) and compare with it 3 other previous SoTA architectures across 5 different tasks from 2 relatively diverse datasets.
Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry
In the process industry, condition monitoring systems with automated fault diagnosis methods assist human experts and thereby improve maintenance efficiency, process sustainability, and workplace safety.
Sharing to learn and learning to share -- Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review
Integrating knowledge across different domains is an essential feature of human learning.
Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning
Perplexity score (an automated intrinsic language model metric) and surveys by human evaluation were used to assess the performances of the fine-tuned models, with results that indicate that the capacity for transfer learning can be exploited with considerable success.
Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks
Table understanding has substantially benefited from the recent breakthroughs in deep neural networks.
Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms
The challenges with NLP systems with regards to tasks such as Machine Translation (MT), word sense disambiguation (WSD) and information retrieval make it imperative to have a labelled idioms dataset with classes such as it is in this work.
Guided Table Structure Recognition through Anchor Optimization
Subsequently, these anchors are exploited to locate the rows and columns in tabular images.
The Challenge of Diacritics in Yoruba Embeddings
The major contributions of this work include the empirical establishment of a better performance for Yoruba embeddings from undiacritized (normalized) dataset and provision of new analogy sets for evaluation.
Corpora Compared: The Case of the Swedish Gigaword & Wikipedia Corpora
In this work, we show that the difference in performance of embeddings from differently sourced data for a given language can be due to other factors besides data size.
Exploring Swedish & English fastText Embeddings for NER with the Transformer
To achieve a good network performance in natural language processing (NLP) downstream tasks, several factors play important roles: dataset size, the right hyper-parameters, and well-trained embeddings.
Word2Vec: Optimal Hyper-Parameters and Their Impact on NLP Downstream Tasks
However, wrong combination of hyper-parameters can produce poor quality vectors.
Pretraining Image Encoders without Reconstruction via Feature Prediction Loss
To evaluate this method we perform experiments on three standard publicly available datasets (LunarLander-v2, STL-10, and SVHN) and compare six different procedures for training image encoders (pixel-wise, perceptual similarity, and feature prediction losses; combined with two variations of image and feature encoding/decoding).
HyperEmbed: Tradeoffs Between Resources and Performance in NLP Tasks with Hyperdimensional Computing enabled Embedding of n-gram Statistics
The embedding achieved on par F1 scores while decreasing the time and memory requirements by several times compared to the conventional n-gram statistics, e. g., for one of the classifiers on a small dataset, the memory reduction was 6. 18 times; while train and test speed-ups were 4. 62 and 3. 84 times, respectively.
Improving Image Autoencoder Embeddings with Perceptual Loss
Autoencoders are trained to embed images from three different computer vision datasets using perceptual loss based on a pretrained model as well as pixel-wise loss.
Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks
In this work, we investigate the application of trainable and spectrally initializable matrix transformations on the feature maps produced by convolution operations.
Survey of Artificial Intelligence for Card Games and Its Application to the Swiss Game Jass
Jass is a very popular card game in Switzerland and is closely connected with Swiss culture.
Improving Reproducible Deep Learning Workflows with DeepDIVA
The field of deep learning is experiencing a trend towards producing reproducible research.
Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts
We measured the performance of our method on a recent dataset of challenging medieval manuscripts and surpassed state-of-the-art results by reducing the error by 80. 7%.
Ranked #1 on
Text-Line Extraction
on DIVA-HisDB
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis
Automatic analysis of scanned historical documents comprises a wide range of image analysis tasks, which are often challenging for machine learning due to a lack of human-annotated learning samples.
Ranked #7 on
Image Classification
on Kuzushiji-MNIST
ICDAR 2019 Historical Document Reading Challenge on Large Structured Chinese Family Records
We propose a Historical Document Reading Challenge on Large Chinese Structured Family Records, in short ICDAR2019 HDRC CHINESE.
Using Deep Object Features for Image Descriptions
The decoder model learns to extract descriptions for the image from scratch by decoding the joint representation of the object visual features and their object classes conditioned by the encoder component.
A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
In this paper, Bayesian Convolutional Neural Network (BayesCNN) using Variational Inference is proposed, that introduces probability distribution over the weights.
Leveraging Random Label Memorization for Unsupervised Pre-Training
We present a novel approach to leverage large unlabeled datasets by pre-training state-of-the-art deep neural networks on randomly-labeled datasets.
Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks
Biometric authentication by means of handwritten signatures is a challenging pattern recognition task, which aims to infer a writer model from only a handful of genuine signatures.
Subword Semantic Hashing for Intent Classification on Small Datasets
In this paper, we introduce the use of Semantic Hashing as embedding for the task of Intent Classification and achieve state-of-the-art performance on three frequently used benchmarks.
Are You Tampering With My Data?
We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models.
Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference
On multiple datasets in supervised learning settings (MNIST, CIFAR-10, CIFAR-100), this variational inference method achieves performances equivalent to frequentist inference in identical architectures, while the two desiderata, a measure for uncertainty and regularization are incorporated naturally.
Bidirectional Learning for Robust Neural Networks
A multilayer perceptron can behave as a generative classifier by applying bidirectional learning (BL).
DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments
We introduce DeepDIVA: an infrastructure designed to enable quick and intuitive setup of reproducible experiments with a large range of useful analysis functionality.
Identifying Cross-Depicted Historical Motifs
Cross-depiction is the problem of identifying the same object even when it is depicted in a variety of manners.
Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks
This paper introduces a very challenging dataset of historic German documents and evaluates Fully Convolutional Neural Network (FCNN) based methods to locate handwritten annotations of any kind in these documents.
A Pitfall of Unsupervised Pre-Training
Experimental results suggest that in fact, there is no correlation between the reconstruction score and the quality of features for a classification task.
Open Evaluation Tool for Layout Analysis of Document Images
This paper presents an open tool for standardizing the evaluation process of the layout analysis task of document images at pixel level.
Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines
This paper presents an approach for real-time training and testing for document image classification.
Historical Document Image Segmentation with LDA-Initialized Deep Neural Networks
In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA).
Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification
We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half.
Ranked #27 on
Document Image Classification
on RVL-CDIP
Multilevel Context Representation for Improving Object Recognition
In this work, we propose the combined usage of low- and high-level blocks of convolutional neural networks (CNNs) for improving object recognition.
TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
In this work, we present the Text Conditioned Auxiliary Classifier Generative Adversarial Network, (TAC-GAN) a text to image Generative Adversarial Network (GAN) for synthesizing images from their text descriptions.
A Pitfall of Unsupervised Pre-Training
Experimental results suggest that in fact, there is no correlation between the reconstruction score and the quality of features for a classification task.
PCA-Initialized Deep Neural Networks Applied To Document Image Analysis
In this paper, we present a novel approach for initializing deep neural networks, i. e., by turning PCA into neural layers.
Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection
Convolutional Neural Networks (CNNs) have become the state-of-the-art in various computer vision tasks, but they are still premature for most sensor data, especially in pervasive and wearable computing.
DIVA-HisDB: A Precisely Annotated Large Dataset of Challenging Medieval Manuscripts
Layout analysis results of several representative baseline technologies are also presented in order to help researchers evaluate their methods and advance the frontiers of complex historical manuscripts analysis.
A Generic Method for Automatic Ground Truth Generation of Camera-captured Documents
The method is generic, language independent and can be used for generation of labeled documents datasets (both scanned and cameracaptured) in any cursive and non-cursive language, e. g., English, Russian, Arabic, Urdu, etc.
Symbol Grounding Association in Multimodal Sequences with Missing Elements
We evaluated the proposed extension in the following scenarios: missing elements in one modality (visual or audio) and missing elements in both modalities (visual and sound).
DeXpression: Deep Convolutional Neural Network for Expression Recognition
The proposed architecture achieves 99. 6% for CKP and 98. 63% for MMI, therefore performing better than the state of the art using CNNs.
Ranked #1 on
Facial Expression Recognition (FER)
on MMI
Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
In contrast, Multi-Dimensional Recurrent NNs (MD-RNNs) can perceive the entire spatio-temporal context of each pixel in a few sweeps through all pixels, especially when the RNN is a Long Short-Term Memory (LSTM).
Scene Labeling With LSTM Recurrent Neural Networks
This paper addresses the problem of pixel-level segmentation and classification of scene images with an entirely learning-based approach using Long Short Term Memory (LSTM) recurrent neural networks, which are commonly used for sequence classification.
Sparse Radial Sampling LBP for Writer Identification
In this paper we present the use of Sparse Radial Sampling Local Binary Patterns, a variant of Local Binary Patterns (LBP) for text-as-texture classification.
Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks
On-line handwriting recognition is unusual among sequence labelling tasks in that the underlying generator of the observed data, i. e. the movement of the pen, is recorded directly.
