We explore the task of sentiment analysis on Hinglish (code-mixed Hindi-English) tweets as participants of Task 9 of the SemEval-2020 competition . We had two main approaches: 1) applying transfer learning by fine-tuning pre-trained BERT models and 2) training feedforward neural networks on bag-of-words representations… We obtained an F-score of 71.3% with our best model, […]

The shape adaptor is a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution . The module allows for a learnable reshaping factor… Our implementation enables shape adaptors to be trained end-to-end without any additional supervision . The source code is available at: GitHub.com/lorenmt/shape-adaptor . We performed […]

A self-supervised approach to incorporate semantic guidance into a GAN based stain normalization framework and preserve detailed structural information . Our method does not require manual segmentation maps which is a significant advantage over existing methods . The proposed scheme outperforms other color normalization methods leading to better classification and segmentation performance . It does […]

Transfer learning considers a learning process where a new task is solved by transferring relevant knowledge from known solutions to related tasks . While this has been studied experimentally, there lacks a foundational description of the transfer learning problem that exposes what related tasks are, and how they can be exploited… In this work, we […]

This paper considers the estimation and prediction of a high-dimensional linear regression in the setting of transfer learning, using samples from the target model as well as auxiliary samples from different but possibly related regression models . When the set of “informative” auxiliary samples is known, an estimator and a predictor are proposed and their […]

Image-to-image translation approaches with disentangled representations have been shown effective for style transfer between two image categories… However, previous methods often assume a shared domain-invariant content space, which could compromise the content representation power . The proposed method outperforms previous style transfer methods, particularly on challenging scenarios that would require semantic correspondences between images . […]

Convolutional neural networks have witnessed remarkable improvements in computational efficiency in recent years . The price of the efficiency is the sub-optimal flow of information across space and channels in the network . To overcome this limitation, we present MUXConv, a layer that is designed to increase the flow of . information by progressively multiplexing […]

In this paper, a Federated Learning (FL) simulation platform is introduced . The target scenario is Acoustic Model training based on this platform… To our knowledge, this is the first attempt to apply FL techniques to Speech Recognition tasks due to the inherent complexity . The proposed FL platform can support different tasks based on […]

The well-known technique outlined in the paper of Leon A. Gatys et al., A Neural Algorithm of Artistic Style, has become a trending topic both in academic literature and industrial applications . The purpose of this study is to present a method for creating artistic maps from satellite images, based on the NST algorithm . […]

The proposed DCNet was compared against a comparable 3D UNet segmentation in terms of sensitivity, specificity, precision, accuracy, and Dice overlap . Fast (5-7seconds) and reliable adipose tissue segmentation can be obtained with high Dice overlap (0.94), sensitivity (96.6%), specificity (95.1%), precision (92.1%) and accuracy (98.4%) from 3D whole-body MR datasets (field of view coverage […]

Neural networks are highly effective tools for pose estimation . But robustness to outof-domain data remains a challenge, especially for small training sets that are common for real world applications… Here, we probe the generalization ability with three architecture classes (MobileNetV2s, ResNets, and EfficientNets) We developed a novel dataset of 30 horses that allowed for […]

Global Forecasting Models (GFM) have shown promising results in forecasting competitions and real-world applications, outperforming many state-of-the-art univariate forecasting techniques . GFMs are implemented using deep neural networks, which require a sufficient amount of time series to estimate their model parameters . In this study, we propose a novel, data augmentation based forecasting framework that […]

Class-incremental learning (CIL) usually suffers from the “catastrophic forgetting” problem when updating the joint classification model on the arrival of newly added classes . To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer . To alleviate this problem, we […]

This paper describes our approach to the task of identifying offensive languages in a multilingual setting . We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection . Our multilingual systems achieved competitive results in Greek, Danish, and Turkish at OffensEval 2020 . We propose a […]

The SOEL learning system uses a combination of transfer learning and principles of computa-tional neuroscience and deep learning… We show that partiallytrained deep Spiking Neural Networks (SNNs) implemented onneuromorphic hardware can rapidly adapt online to new classes of data within a domain . SOEL updates trigger when an error occurs, enabling faster learning with fewer […]

Prompt Agnostic Essay Scorer (PAES) for cross-prompt AES is a single-stage approach . PAES is easy to apply in practice and achieves state-of-the-art performance on the Automated Student Assessment Prize (ASAP) dataset . Our method requires no access to labelled or unlabelled target-Prompt data during training and is a one-step approach . It is easy-to-apply […]

Designing logos, typefaces, and other decorated shapes can require professional skills . In this paper, we aim to produce new and unique decorated shapes by stylizing ordinary shapes with machine learning . Specifically, we combined parametric and non-parametric neural style transfer algorithms to transfer both local and global features . Furthermore, we introduced a distance-based […]

Laprop decouples momentum and adaptivity in Adam-style optimizers . The coupling leads to instability and divergence when the parameters are mismatched . The decoupling leads to greater flexibility in the hyperparameters and allows for a straightforward interpolation between the signed gradient methods and the adaptive gradient methods . We experimentally show that Laprop has consistently […]

Active Learning Strategies have shown promising results in the Persian language . LDA sampling, which is an efficient Active Learning strategy using Topic Modeling, is proposed in this research . MirasOpinion, which to our knowledge is the largest Persian sentiment analysis dataset, is crawled from a Persian e-commerce website and annotated using a crowd-sourcing policy […]

Zero-shot hyperparameter optimization (HPO) is a simple yet effective use of transfer learning for constructing a small list of hyperparameters (HP) configurations that complement each other . Current techniques for obtaining this list are computationally expensive as they rely on running training jobs on a diverse collection of datasets and a large collection of randomly […]

Underwater robots in shallow waters usually suffer from strong wave forces, which may frequently exceed robot’s control constraints . A transfer reinforcement learning algorithm using Transition Mismatch Compensation (TMC) is developed based on the modular architecture, that learns an additional compensatory policy through minimizing mismatch of transitions predicted by the two dynamics models of the […]

Music FaderNets is inspired by the fact that low-level attributes can be continuously manipulated by separate “sliding faders” through feature disentanglement and latent regularization techniques . High-level features are then inferred from the low level representations through semi-supervised clustering using Gaussian Mixture Variational Autoencoders (GM-VAEs) Using arousal as an example of a high-level feature, we […]

We explore the task of sentiment analysis on Hinglish (code-mixed Hindi-English) tweets as participants of Task 9 of the SemEval-2020 competition . We had two main approaches: 1) applying transfer learning by fine-tuning pre-trained BERT models and 2) training feedforward neural networks on bag-of-words representations… We obtained an F-score of 71.3% with our best model, […]

Deep neural networks have provided state-of-the-art solutions for problems such as denoising, which implicitly rely on a prior probability model of natural images… Here, we develop a robust and general methodology for making use of this implicit prior . A generalization of this algorithm to constrained sampling provides a method for using the implicit prior […]

This article proposes a transfer reinforcement learning (RL) based adaptive energy managing approach for a hybrid electric vehicle (HEV) with parallel topology . This approach is bi-level… The up-level characterizes how to transform the Q-value tables in the RL framework via driving cycle transformation (DCT) The lower-level determines how to set the corresponding control strategies […]

Computational histopathology image diagnosis becomes increasingly popular and important, where images are segmented or classified for disease diagnosis by computers . While pathologists do not struggle with color variations in slides, computational solutions usually suffer from this critical issue . Study proposes two stain style transfer models, SSIM-GAN and DSCSI-GAN, based on the generative adversarial […]

Mix-StAGE is a new model that trains a single model for multiple speakers while learning unique style embeddings for each speaker’s gestures in an end-to-end manner . The new model significantly outperforms the previous state-of-the-art approach for gesture generation and provides a path towards performing gesture style transfer across multiple speakers . The researchers also […]

We reveal incoherence between the widely-adopted empirical domain adversarial training and its generally-assumed theoretical counterpart based on $\mathcal{H}$-divergence . Concretely, we find that $H-Divergence is not equivalent to Jensen-Shannon divergence . We establish a new theoretical framework by directly proving the upper and lower target risk bounds . We employ algorithms for each principle and […]

Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion . One common limitation of many existing methods is that they often train a model directly on all available training data without validation due to the nature of continual learning, thus suffering poor generalization at test time… In […]

Parametric models of humans, faces, hands and animals have been widely used for a range of tasks such as image-based reconstruction, shape correspondence estimation, and animation . Learning such models requires lots of expert knowledge and hand-defined object-specific constraints, making the learning approach unscalable to novel objects . In this paper, we present a simple […]

Blood pressure monitoring is an essential component of hypertension management and in the prediction of associated comorbidities . Capturing blood pressure remotely and frequently has traditionally been achieved by measuring blood pressure at discrete intervals using an inflatable cuff . There is growing interest in developing a cuffless ambulatory blood pressure monitoring system to measure […]

Smartphones, wearables, and Internet of Things (IoT) devices produce a wealth of data that cannot be accumulated in a centralized repository for learning supervised models due to privacy, bandwidth limitations, and the prohibitive cost of annotations . To address these issues, we propose a self-supervised approach termed \textit{scalogram-signal correspondence learning} based on wavelet transform to […]

Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks to new domains . This approach is particularly useful when only limited or weakly labelled data are available for the new task . We show that adversarially-trained models transfer better across new domains than naturally-trained ones . This behavior results from […]

Tiny-Transfer-Learning (TinyTL) can reduce training memory cost by order of magnitude (up to 13.3x) without sacrificing accuracy compared to fine-tuning the full network . TinyTL pre-trains a large super-net that contains many weight-shared sub-nets that can individually operate . Different from using the same feature extractor to fit different target datasets, TinyTL adapts the architecture […]

A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition . The proposed method first extracts features from both modalities using a convolutional feature extractor . These features are then fused using a two-layer attention mechanism . The training database is preprocessed and augmented through […]

A single Named Entity Recognition model that is trained jointly on many languages simultaneously is able to decode these languages with better accuracy than models trained only on one language . The model could be used to make zero-shot predictions on a new language, even ones for which training data is not available, out of […]


Enjoy this blog? Please spread the word :)