Effective Transfer Learning for Identifying Similar Questions Matching User Questions to COVID 19 FAQs

People increasingly search online for answers to their medical questions but the rate at which medical questions are asked online significantly exceeds the capacity of qualified people to answer them . Many of these questions are not unique, and reliable identification of similar questions would enable more efficient and effective question answering Schema .… Read the rest

A Lightweight Music Texture Transfer System

Deep learning researches on the transformation problems for image and text have raised great attention . However, present methods for music feature transfer using neural networks are far from practical application… In this paper, we initiate a novel system for transferring the texture of music, and release it as an open source project .… Read the rest

Overcoming Negative Transfer A Survey

Transfer learning aims to help the target task with little or no training data by leveraging knowledge from one or multi-related auxiliary tasks . Negative transfer is a long-standing problem in transfer learning literature, which has been well recognized within the transfer learning community… How to overcome negative transfer has been studied for a long time and has raised increasing attention in recent years .… Read the rest

Learning to Localize Actions from Moments

Action Herald Networks (AherNet) integrate such design into an one-stage action localization framework . The context of each moment is learnt through the adversarial mechanism to differentiate the generated features from those of background in untrimmed videos . Extensive experiments are conducted on the learning across the learning both across the splits of ActivityNet v1.3 and from THUMOS14 to ActivityNet .… Read the rest

Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces

Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target domain by transferring knowledge from labeled source domain with domain shift . Most of the existing UDA methods try to mitigate the adverse impact induced by the shift via reducing domain discrepancy… However, such approaches easily suffer a notorious mode collapse issue due to the lack of labels in target domain .… Read the rest

All About Knowledge Graphs for Actions

Current action recognition systems require large amounts of training data for recognizing an action . Unlike objects, it is unclear what is the best knowledge representation for actions . In this paper, we intend to gain a better understanding of knowledge graphs (KGs) that can be utilized for zero-shot and few-shot action recognition .… Read the rest

Transfer Learning based Road Damage Detection for Multiple Countries

Many municipalities and road authorities seek to implement automated evaluation of road damage . However, they often lack technology, know-how, and funds to afford state-of-the-art equipment for data collection and analysis of road damages . Some countries, like Japan, have developed less expensive and readily available Smartphone-based methods for automatic road condition monitoring, other countries still struggle to find efficient solutions .… Read the rest

Evaluating Knowledge Transfer In Neural Network for Medical Images

Deep learning and knowledge transfer techniques have permeated the field of medical imaging and are considered as key approaches for revolutionizing diagnostic imaging practices . However, there are still challenges for the successful integration of deep learning into medical imaging tasks due to a lack of large annotated imaging data… To address this issue, we propose a teacher-student learning framework to transfer knowledge from a carefully pre-trained convolutional neural network (CNN) teacher to a student CNN .… Read the rest

A Flexible Selection Scheme for Minimum Effort Transfer Learning

Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task . The orthogonal setting of transferring knowledge from a pretrained network to a visually different yet semantically close source is rarely considered: This commonly happens with real-life data, which is not necessarily as clean as the training source .… Read the rest

A Benchmark for Studying Diabetic Retinopathy Segmentation Grading and Transferability

Computer-aided DR diagnosis is a promising tool for early detection of DR and severity grading, due to the great success of deep learning . Most current DR diagnosis systems do not achieve satisfactory performance or interpretability for ophthalmologists . We construct a large-scale fine-grained annotated annotated DR dataset containing 2,842 images (FGADR) The proposed dataset will enable extensive studies on DR diagnosis .… Read the rest

Self Contained Stylization via Steganography for Reverse and Serial Style Transfer

Style transfer has been widely applied to give real-world images a new artistic look . Attempts to use typical style transfer methods for de-stylization or transferring it again into another style usually lead to artifacts or undesired results . We realize that these issues are originated from the content inconsistency between the original image and its stylized output .… Read the rest

3D for Free Crossmodal Transfer Learning using HD Maps

3D object detection is a core perceptual challenge for robotics and autonomous driving . The class-taxonomies in modern autonomous driving datasets are significantly smaller than many influential 2D detection datasets . We use a collection of 1151 unlabeled, multimodal driving logs from an autonomous vehicle and use the discovered objects to train a LiDAR-based object detector .… Read the rest

Jointly Fine Tuning BERT like Self Supervised Models to Improve Multimodal Speech Emotion Recognition

Multimodal emotion recognition from speech is an important area in affective computing . Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task… In this paper, we explore the use of modality-specific “BERT-like” pretrained Self Supervised Learning (SSL) architectures to represent both speech and text modalities for the task of multimodal speech emotion recognition .… Read the rest

GAN Slimming All in One GAN Compression by A Unified Optimization Framework

Generative adversarial networks (GANs) have gained increasing popularity in various computer vision applications . The study of GAN compression remains in its infancy, so far leveraging individual compression techniques instead of more sophisticated combinations . We observe that due to the notorious instability of training GANs, heuristically stacking different compression techniques will result in unsatisfactory results .… Read the rest

An End to End Attack on Text based CAPTCHAs Based on Cycle Consistent Generative Adversarial Network

As a widely deployed security scheme, text-based CAPTCHAs have become more and more difficult to resist machine learning-based attacks . So far, many researchers have conducted attacking research on CAPTCHA schemes deployed by different companies (such as Microsoft, Amazon, and Apple) However, most of these attacks have some shortcomings, such as poor portability of attack methods .… Read the rest

Predicting Helpfulness of Online Reviews

E-commerce dominates a large part of the world’s economy with many websites dedicated to online selling products . The traditional way of determining the helpfulness of a review is through the feedback from human users . However, such a method does not necessarily cover all reviews .… Read the rest

Few Shot Learning with Intra Class Knowledge Transfer

We consider the few-shot classification task with an unbalanced dataset . Some classes have sufficient training samples while other classes only have limited training samples . We propose to leverage intra-class knowledge from the neighbor many-shot classes with the intuition that neighbor classes share similar statistical information .… Read the rest

Disentangled Adversarial Autoencoder for Subject Invariant Physiological Feature Extraction

Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner . A major challenge of physiological sensing lies in the variability of biosignals across different users and tasks… To address this issue, we propose an adversarial feature extractor for transfer learning to exploit disentangled universal representations .… Read the rest

Laughter Synthesis Combining Seq2seq modeling with Transfer Learning

Despite the growing interest for expressive speech synthesis, synthesis of nonverbal expressions is an under-explored area . We leverage transfer learning by training a deep learning model to learn to generate both speech and laughs from annotations . We evaluate our model with a listening test, comparing its performance to an HMM-based laughter synthesis one and assess that it reaches higher perceived naturalness .… Read the rest

FastSal a Computationally Efficient Network for Visual Saliency Prediction

MobileNetV2 makes an excellent backbone for a visual saliency model and can be effective even without a complex decoder . We also show that knowledge transfer from a more computationally expensive model like DeepGaze II can be achieved via pseudo-labelling an unlabelled dataset, and that this approach gives result on-par with many state-of-the-art algorithms with a fraction of the computational cost and model size .

Graphical Object Detection in Document Images

Graphical Object Detection (GOD) is data-driven and does not require any heuristics or meta-data to locate graphical objects in the document images . The GOD explores the concept of transfer learning and domain adaptation to handle scarcity of labeled training images for graphical object detection task .… Read the rest

Cascade Style Transfer

Recent studies have made tremendous progress in style transfer for specific domains, e.g., artistic, semantic and photo-realistic . But existing approaches have limited flexibility in extending to other domains, as different style representations are often specific to particular domains… This also limits the stylistic quality .… Read the rest

Neural Code Search Revisited Enhancing Code Snippet Retrieval through Natural Language Intent

In this work, we propose and study annotated code search: the retrieval of code snippets paired with brief descriptions of their intent using natural language queries . We find that our model yields significantly more relevant search results (with absolute gains up to 20.6% in mean reciprocal rank) compared to state-of-the-art code retrieval methods that do not use descriptions but attempt to compute the intent of snippets solely from unannotated code .… Read the rest

Learn to Talk via Proactive Knowledge Transfer

Knowledge Transfer has been applied in solving a wide variety of problems . By replacing Forward with Backward in Knowledge Distillation, we observed +0.7-1.1 BLEU gains on the WMT’17 De-En and IWSLT’15 Th-En machine translation tasks . Without loss of generality, we relate knowledge transfer to KL-divergence minimization minimization, i.e.,… Read the rest

Variable Compliance Control for Robotic Peg in Hole Assembly A Deep Reinforcement Learning Approach

Industrial robot manipulators are playing a more significant role in modern manufacturing industries . The main contribution of this work is a learning-based method to solve peg-in-hole tasks with position uncertainty of the hole . We proposed the use of an off-policy model-free reinforcement learning method and bootstrap the training speed by using several transfer learning techniques (sim2real) and domain randomization .… Read the rest

Learning to Transfer Examples for Partial Domain Adaptation

Deep networks can learn disentangled and transferable features that effectively diminish the dataset shift between the source and target domains for knowledge transfer… In the era of Big Data, the ready availability of large-scale labeled datasets has stimulated wide interest in partial domain adaptation (PDA), which transfers a recognizer from a labeled large domain to an unlabeled small domain .… Read the rest

TopicBERT A Transformer transfer learning based memory graph approach for multimodal streaming social media topic detection

Real time nature of social networks with bursty short messages and their respective large data scale spread among vast variety of topics are research interest of many researchers . Many research issues such as noisy sentences that adverse grammar and new online user invented words are challenging maintenance of a good social network topic detection and tracking methodology .… Read the rest

Arbitrary Style Transfer via Multi Adaptation Network

A desired style transfer, given a content image and referenced style painting, would render the content image with the color tone and vivid stroke patterns of the style painting while synchronously maintaining the detailed content structure information . A new disentanglement loss function enables our network to extract main style patterns and exact content structures to adapt to various input images, respectively .… Read the rest

Knowledge Transfer via Dense Cross Layer Mutual Distillation

Knowledge Distillation (KD) based methods adopt the one-way Knowledge Transfer (KT) scheme in which training a lower-capacity student network is guided by a pre-trained high-capacity teacher network . To augment knowledge representation learning, auxiliary classifiers are added to certain hidden layers of both teacher and student networks .… Read the rest

Inducing Language Agnostic Multilingual Representations

Multilingual representations have the potential to make cross-lingual systems available to the vast majority of languages in the world . However they currently require large pretraining corpora, or assume access to typologically similar languages… In this work, we address these obstacles by removing language identity signals from multilingual embeddings .… Read the rest

Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model

Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently . Here, we introduce a transfer learning approach for hate speech detection based on an existing pre-trained language model BERT and evaluate the proposed model on two publicly available datasets that have been annotated for racism, sexism, hate or offensive content on Twitter .… Read the rest