Related papers: Data-Adaptive Discriminative Feature Localization …

While previous distribution shift detection approaches can identify if a shift has occurred, these approaches cannot localize which specific features have caused a distribution shift -- a critical step in diagnosing or fixing any underlying…

The recent developments of complex deep learning models have led to unprecedented ability to accurately predict across multiple data representation types. Conformal prediction for uncertainty quantification of these models has risen in…

Regarding image forensics, researchers have proposed various approaches to detect and/or localize manipulations, such as splices. Recent best performing image-forensics algorithms greatly benefit from the application of deep learning, but…

Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the prediction logits due to its inefficiency in distilling the localization information. In this paper, we investigate…

Planet-scale photo geolocalization is the complex task of estimating the location depicted in an image solely based on its visual content. Due to the success of convolutional neural networks (CNNs), current approaches achieve super-human…

Unsupervised machine learning, and in particular data clustering, is a powerful approach for the analysis of datasets and identification of characteristic features occurring throughout a dataset. It is gaining popularity across scientific…

Feature selection methods have an important role on the readability of data and the reduction of complexity of learning algorithms. In recent years, a variety of efforts are investigated on feature selection problems based on unsupervised…

This manuscript proposes a novel methodology for developing an interpretable prediction model for irregular Electrocardiogram (ECG) classification, using features extracted by a 1-D Deconvolutional Neural Network (1-D DNN). Given the…

Adversarial sample attacks perturb benign inputs to induce DNN misbehaviors. Recent research has demonstrated the widespread presence and the devastating consequences of such attacks. Existing defense techniques either assume prior…

Unsupervised Re-ID methods aim at learning robust and discriminative features from unlabeled data. However, existing methods often ignore the relationship between module parameters of Re-ID framework and feature distributions, which may…

Interpretability and small labelled datasets are key issues in the practical application of deep learning, particularly in areas such as medicine. In this paper, we present a semi-supervised technique that addresses both these issues by…

This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input. When classifying images, the method highlights areas in a given input image that provide evidence for…

Dense prediction tasks such as segmentation and detection of pathological entities hold crucial clinical value in computational pathology workflows. However, obtaining dense annotations on large cohorts is usually tedious and expensive.…

The classification of electrocardiogram (ECG) plays a crucial role in the development of an automatic cardiovascular diagnostic system. However, considerable variances in ECG signals between individuals is a significant challenge. Changes…

Deep neural networks are state-of-the-art models for understanding the content of images, video and raw input data. However, implementing a deep neural network in embedded systems is a challenging task, because a typical deep neural…

Deep learning has significantly advanced electrocardiogram (ECG) analysis, enabling automatic annotation, disease screening, and prognosis beyond traditional clinical capabilities. However, understanding these models remains a challenge,…

Robot localization is a fundamental component of autonomous navigation in unknown environments. Among various sensing modalities, visual input from cameras plays a central role, enabling robots to estimate their position by tracking point…

In a typical supervised machine learning setting, the predictions on all test instances are based on a common subset of features discovered during model training. However, using a different subset of features that is most informative for…

Electrocardiogram (ECG) is the most widely used diagnostic tool to monitor the condition of the cardiovascular system. Deep neural networks (DNNs), have been developed in many research labs for automatic interpretation of ECG signals to…

Although deep neural networks have shown promising performances on various tasks, they are susceptible to incorrect predictions induced by imperceptibly small perturbations in inputs. A large number of previous works proposed to detect…