Fully Convolutional Networks for Diabetic Foot Ulcer Segmentation

Diabetic Foot Ulcer (DFU) is a major complication of Diabetes, which if not managed properly can lead to amputation . DFU can appear anywhere on the foot and can vary in size, colour, and contrast depending on various pathologies… Current clinical approaches to DFU treatment rely on patients and clinician vigilance, which has significant limitations such as the high cost involved in the diagnosis, treatment and lengthy care of the DFU .…

Gaussian Process Classification with Privileged Information by Soft to Hard Labeling Transfer

A state-of-the-art method of Gaussian process classification (GPC) with privileged information is GPC+. A drawback of GPC+ is that it requires numerical quadrature to calculate the posterior distribution of the latent function, which is extremely time-consuming . To overcome this limitation, we propose a novel classification method based on Gaussian processes, called “soft-label-transferred Gauss process (SLT-GP) Our basic idea is that we construct another learning task of predicting soft labels (continuous values) obtained from privileged information .…

Gaussian Process Models for Link Analysis and Transfer Learning

In this paper we develop a Gaussian process (GP) framework to model a collection of reciprocal random variables defined on the \emph{edges} of a network . We show how to construct GP priors, i.e.,~covariance functions, on the edges of directed, undirected, and bipartite graphs… The model suggests an intimate connection between .link…

GeoGAN A Conditional GAN with Reconstruction and Style Loss to Generate Standard Layer of Maps from Satellite Images

We created a database of pairs of satellite images and the corresponding map of the area . Our model translates the satellite image to the corresponding standard layer map image using three main model architectures: (i) a conditional Generative Adversarial Network (GAN) which compresses the images down to a learned embedding, (ii) a generator which is trained as a normalizing flow (RealNVP) model, (iii) A conditional GAN where the generator translates via a series of convolutions to the standard layer of a map and the discriminator input is the concatenation of the real and generated map .…

MERL Multi Head Reinforcement Learning

A common challenge in reinforcement learning is how to convert the agent’s interactions with an environment into fast and robust learning . While promising, previously acquired knowledge is often costly and challenging to scale up . Instead, we decide to consider problem knowledge with signals from quantities relevant to solve any task, e.g.,…

Humpty Dumpty Controlling Word Meanings via Corpus Poisoning

Word embeddings are typically trained on large public corpora such as Wikipedia or Twitter . An attack on the embedding can affect diverse downstream tasks, demonstrating for the first time the power of data poisoning in transfer learning scenarios . We use this attack to manipulate query expansion in information retrieval systems such as resume search, make certain names more or less visible to named entity recognition models, and cause new words to be translated to a particular target word regardless of the language .…

Improved Multi Stage Training of Online Attention based Encoder Decoder Models

In this paper, we propose a refined multi-stage multi-task training strategy to improve the performance of online attention-based encoder-decoder (AED) models . We explore different pre-training strategies for the encoders including transfer learning from a bidirectional encoder . Our models achieve a word error rate (WER) of 5.04% and 4.48% on the Librispeech test-clean data for the smaller and bigger models respectively after fusion with long short-term memory (LSTM) based external language model (LM) The models with online attention show 35% and 10% relative improvement over their baselines .…

Interactive dimensionality reduction using similarity projections

Recent advances in machine learning allow us to analyze and describe content of high-dimensional data . In order to visualize that data in 2D or 3D, usually Dimensionality Reduction (DR) techniques are employed… Most of these techniques produce static projections without taking into account corrections from humans or other data exploration scenarios .…

Is Discriminator a Good Feature Extractor

The discriminator from generative adversarial nets (GAN) has been used by researchers as a feature extractor in transfer learning and appeared worked well . We found that the connection between the task of the discriminator and the feature is not as strong as was thought, for that the main factor restricting the feature learned by the discrimator is not the task, but is the need to prevent the entire GAN model from mode collapse during the training .…

Accelerated Bayesian Optimization throughWeight Prior Tuning

Bayesian optimization (BO) is a widely-used method for optimizing expensive (to evaluate) problems . At the core of most BO methods is the modeling of the objective function using a Gaussian Process . In many practical applications there is data available that has a similar (covariance) structure to the objective, but which, having different form, cannot be used directly in transfer learning .…

ADMM SOFTMAX An ADMM Approach for Multinomial Logistic Regression

ADMM-Softmax is geared toward supervised classification tasks with many examples and features . It decouples the nonlinear optimization problem in MLR into three steps that can be solved efficiently . Each iteration consists of a linear least-squares problem, a set of independent small-scale smooth, convex problems and a trivial dual variable update .…

Latent User Linking for Collaborative Cross Domain Recommendation

Collaborative filtering is a popular approach in implementing recommender systems… Yet, collaborative filtering methods are highly dependent on user feedback, which is often highly sparse and hard to obtain . We propose a Variational Autoencoder based network model for cross-domain linking with added contextualization to handle sparse data .…

Learning a Deep Compact Image Representation for Visual Tracking

In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background . In contrast to most existing trackers which only learn the appearance of the tracked object online, we take a different approach, inspired by recent advances in deep learning architectures, by putting more emphasis on the (unsupervised) feature learning problem .…

Learning to Progressively Recognize New Named Entities with Sequence to Sequence Models

In this paper, we propose to use a sequence to sequence model for Named Entity Recognition (NER) and explore the effectiveness of such model in a progressive NER setting . We train an initial model on source data and transfer it to a model that can recognize new NE categories in the target data during a subsequent step, when the source data is no longer available… Our solution consists in: (i) to reshape and re-parametrize the output layer of the first learned model to enable the recognition of new NEs .…

Learning to Select Pre Trained Deep Representations with Bayesian Evidence Framework

We propose a Bayesian evidence framework to facilitate transfer learning from pre-trained deep convolutional neural networks (CNNs) Our framework is formulated on top of a least squares SVM (LS-SVM) classifier, which is simple and fast in both training and testing, and achieves competitive performance in practice… The regularization parameters in LS-Svm is estimated automatically without grid search and cross-validation by maximizing evidence .…

Liver Steatosis Segmentation with Deep Learning Methods

An accurate quantification of steatosis area within the liver histopathological microscopy images plays an important role in liver disease diagnosis and trans-plantation assessment . A deep learning model Mask-RCNN can predict object masks in addition to bounding box detection . With transfer learning, the resulting model is able to segment overlapped areas at 75.87% by Average Precision, 60.66% by Recall, 65.88% by F1-score, and 76.97% by Jaccard index .…

LSTD A Low Shot Transfer Detector for Object Detection

Recent advances in object detection are mainly driven by deep learning with large-scale detection benchmarks . However, the fully-annotated training set is often limited for a target detection task, which may deteriorate the performance of deep detectors… To address this challenge, we propose a novel low-shot transfer detector (LSTD) in this paper, where we leverage rich source-domain knowledge to construct an effective target-domain detector with very few training examples .…

Mind2Mind transfer learning for GANs

Transfer learning enables deep networks for classification tasks to be trained with limited computing and data resources… However a similar approach is missing in the specific context of generative tasks . This is partly due to the fact that the extremal layers of the two networks of a GAN, which should be learned during transfer, are on two opposite sides .…

Motion Blur removal via Coupled Autoencoder

In this paper a joint optimization technique has been proposed for coupled autoencoder . The proposed technique can operate on-the-fly, since it does not require solving any costly inverse problem . The technique is applicable to any transfer learning problem… In this work, we propose a new formulation that recasts deblurring as a transfer learning .…

Multi Module Recurrent Neural Networks with Transfer Learning

This paper describes multiple solutions designed and tested for the problem of word-level metaphor detection . The proposed systems are all based on variants of recurrent neural network architectures… Specifically, we explore multiple sources of information: pre-trained word embeddings (Glove), a dictionary of language concreteness and a transfer learning scenario based on the states of an encoder network from neural network machine translation system .…

Multiple Text Style Transfer by using Word level Conditional Generative Adversarial Network with Two Phase Training

Non-parallel text style transfer, or controllable text generation, is to alter specific attributes (e.g. mood, mood, tense, politeness, etc) of a given text while preserving its remaining attributes and content . By using a style-related condition architecture before generating a word, our model is able to maintain style-unrelated words while changing the others .…

Neural Subgraph Isomorphism Counting

In this paper, we study a new graph learning problem: learning to count subgraph isomorphisms . Different from other traditional graph learning problems such as node classification and link prediction . Subgraph isomorphicism counting is NP-complete and requires more global inference to oversee the whole graph .…

NULI at SemEval 2019 Task 6 Transfer Learning for Offensive Language Detection using Bidirectional Transformers

Transfer learning and domain adaptive learning have been applied to various fields including computer vision and natural language processing . One of the benefits of transfer learning is to learn effectively and efficiently from limited labeled data with a pre-trained model… In the shared task of identifying and categorizing offensive language in social media, we preprocess the dataset according to the language behaviors on social media .…

Object Recognition from very few Training Examples for Enhancing Bicycle Maps

In recent years, data-driven methods have shown great success for extracting information about infrastructure in urban areas . But for cyclists very few labeled data is available although appearance, point of view, and positioning of even relevant objects differ . The aim is to recognize particular traffic signs in crowdsourced data to collect information which is of interest to cyclists .…

OMNIA Faster R CNN Detection in the wild through dataset merging and soft distillation

Object detectors tend to perform poorly in new or open domains, and require exhaustive yet costly annotations from fully labeled datasets . We aim at benefiting from several datasets with different categories but without additional labelling, not only to increase the number of categories detected, but also to take advantage from transfer learning and to enhance domain independence .…

Optimal Transport for Deep Joint Transfer Learning

Joint Transfer Learning Network (JTLN) can effectively learn useful knowledge for target classification from source data . JTLN can incorporate different prior knowledge about the relatedness between target categories and source categories . This Joint Transfer learning with OT loss is general and can also be applied to other kind of Neural Networks .…

Overcoming Small Minirhizotron Datasets Using Transfer Learning

Minirhizotron technology is widely used for studying the development of roots . Automated analysis of root systems could facilitate new scientific discoveries that would be critical to address the world’s pressing food, resource, and climate issues . Supervised learning techniques appear to be an appropriate tool for the challenge due to varying local soil and root conditions, however, lack of enough annotated training data is a major limitation due to the error-prone and time-consuming manually labeling process .…

Personalized Risk Scoring for Critical Care Patients using Mixtures of Gaussian Process Experts

The proposed algorithm aims to discover the number of latent classes in the patients population, and train a mixture of Gaussian Process (GP) experts, where each expert models the physiological data streams associated with a specific class . Self-taught transfer learning is used to transfer the knowledge of latent class learning to the domain of clinically stable patients .…

Planning from Images with Deep Latent Gaussian Process Dynamics

Planning is a powerful approach to control problems with known environment dynamics . This is particularly challenging when the underlying states are only indirectly observable through images . We propose to learn a deep latent Gaussian process dynamics (DLGPD) model that learns low-dimensional system dynamics from environment interactions with visual observations .…

Posture recognition using an RGB D camera exploring 3D body modeling and deep learning approaches

The emergence of RGB-D sensors offered new possibilities for addressing complex artificial vision problems efficiently . Human posture recognition is among these computer vision problems, with a wide range of applications such as ambient assisted living and intelligent health care systems… In this context, our paper presents novel methods and ideas to design automatic posture recognition systems using an RGB-d camera .…

PROPS Probabilistic personalization of black box sequence models

PROPS is a lightweight transfer learning mechanism for sequential data . PROPS learns probabilistic perturbations around the predictions of one or more arbitrarily complex, pre-trained black box models . The technique pins the black-box prediction functions to “source nodes” of a hidden Markov model (HMM) and uses the remaining nodes as “perturbation nodes” for learning customized perturbation .…

Revisit Multinomial Logistic Regression in Deep Learning Data Dependent Model Initialization for Image Recognition

Logistic regression is widely known not having a closed-form solution, it is usually randomly initialized, leading to several deficiencies . The deficiencies include slow convergence speed, possibility of stuck in local minimum, and the risk of over-fitting . The approach can reduce the training time by 10 times and achieve 3.2% gain in accuracy for Flickr-style classification .…

SEALion a Framework for Neural Network Inference on Encrypted Data

SEALion is an extensible framework for privacy-preserving machine learning with homomorphic encryption . It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data… The framework consists of two layers: the first is built upon TensorFlow and SEAL and exposes standard algebra and deep learning primitives .…