Classifier (UML)
View article: Learning Multiple Layers of Features from Tiny Images
Learning Multiple Layers of Features from Tiny Images Open
April 8, 2009Groups at MIT and NYU have collected a dataset of millions of tiny colour images from the web. It is, in principle, an excellent dataset for unsupervised training of deep generative models, but previous researchers who have tr…
View article
A Simple Framework for Contrastive Learning of Visual Representations Open
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. …
View article
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier Open
Despite widespread adoption in NLP, machine learning models remain mostly black boxes.Understanding the reasons behind predictions is, however, quite important in assessing trust in a model.Trust is fundamental if one plans to take action …
View article
R-FCN: Object Detection via Region-based Fully Convolutional Networks Open
We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our re…
View article
The 30 m annual land cover dataset and its dynamics in China from 1990 to 2019 Open
Land cover (LC) determines the energy exchange, water and carbon cycle between Earth's spheres. Accurate LC information is a fundamental parameter for the environment and climate studies. Considering that the LC in China has been altered d…
View article
Universal Adversarial Perturbations Open
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic…
View article
Automated Hate Speech Detection and the Problem of Offensive Language Open
A key challenge for automatic hate-speech detection on social media is the separation of hate speech from other instances of offensive language. Lexical detection methods tend to have low precision because they classify all messages contai…
View article
Diffusion Models Beat GANs on Image Synthesis Open
We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by finding a better architecture through a series of ablations. For…
View article
Conditional Image Synthesis With Auxiliary Classifier GANs Open
Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We c…
View article
Adversarial Examples in the Physical World Open
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifi…
View article
DSSD : Deconvolutional Single Shot Detector Open
The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection. To achieve this we first combine a state-of-the-art classifier (Residual-101[14]) with a fast detection f…
View article
A Deep Learning Approach to Network Intrusion Detection Open
Software Defined Networking (SDN) has recently emerged to become one of the promising solutions for the future Internet. With the logical centralization of controllers and a global network overview, SDN brings us a chance to strengthen our…
View article
Conditional Adversarial Domain Adaptation Open
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimoda…
View article
Focal Loss for Dense Object Detection Open
The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a reg…
View article
Pruning Convolutional Neural Networks for Resource Efficient Inference Open
We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation - a computationally efficient procedure that m…
View article
A simple framework for contrastive learning of visual representations Open
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. …
View article
Simplifying Graph Convolutional Networks Open
Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, …
View article
Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric Open
Data imbalance is frequently encountered in biomedical applications. Resampling techniques can be used in binary classification to tackle this issue. However such solutions are not desired when the number of samples in the small class is l…
View article
Going deeper in facial expression recognition using deep neural networks Open
Automated Facial Expression Recognition (FER) has remained a challenging and\ninteresting problem. Despite efforts made in developing various methods for\nFER, existing approaches traditionally lack generalizability when applied to\nunseen…
View article
Classification using deep learning neural networks for brain tumors Open
Deep Learning is a new machine learning field that gained a lot of interest over the past few years. It was widely applied to several applications and proven to be a powerful machine learning tool for many of the complex problems. In this …
View article
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks Open
Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation o…
View article
Unsupervised Domain Adaptation with Residual Transfer Networks Open
The recent success of deep neural networks relies on massive amounts of labeled data. For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. In this paper, we propose a…
View article
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain Open
Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation o…
View article
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models Open
Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional imag…
View article
Classification of breast cancer histology images using Convolutional Neural Networks Open
Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis syst…
View article
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks Open
Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep n…
View article
SINTAX: a simple non-Bayesian taxonomy classifier for 16S and ITS sequences Open
Metagenomics experiments often characterize microbial communities by sequencing the ribosomal 16S and ITS regions. Taxonomy prediction is a fundamental step in such studies. The SINTAX algorithm predicts taxonomy by using k -mer similarity…
View article
MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites Open
Quality control of MRI is essential for excluding problematic acquisitions and avoiding bias in subsequent image processing and analysis. Visual inspection is subjective and impractical for large scale datasets. Although automated quality …
View article
Optimal Transport for Domain Adaptation Open
Domain adaptation is one of the most challenging tasks of modern data analytics. If the adaptation is done correctly, models built on a specific data representation become more robust when confronted to data depicting the same classes, but…
View article
Robust Loss Functions under Label Noise for Deep Neural Networks Open
In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learnin…