research
∙
05/17/2023
FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks
With the continue development of Convolutional Neural Networks (CNNs), t...
share
research
∙
05/09/2023
Towards the Characterization of Representations Learned via Capsule-based Network Architectures
Capsule Networks (CapsNets) have been re-introduced as a more compact an...
research
∙
02/22/2023
Considering Layerwise Importance in the Lottery Ticket Hypothesis
The Lottery Ticket Hypothesis (LTH) showed that by iteratively training ...
research
∙
01/17/2023
Training Methods of Multi-label Prediction Classifiers for Hyperspectral Remote Sensing Images
With their combined spectral depth and geometric resolution, hyperspectr...
research
∙
12/21/2022
Deep set conditioned latent representations for action recognition
In recent years multi-label, multi-class video action recognition has ga...
research
∙
04/29/2021
MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization
One of the most common problems of weakly supervised object localization...
research
∙
04/16/2021
Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed
Explainable AI (XAI) methods focus on explaining what a neural network h...
research
∙
10/29/2020
Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?
We present a method for adversarial attack detection based on the inspec...
research
∙
09/16/2020
Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing
Given a really low-resolution input image of a face (say 16x16 or 8x8 pi...
research
∙
01/23/2020
Information Compensation for Deep Conditional Generative Networks
In recent years, unsupervised/weakly-supervised conditional generative a...
research
∙
09/11/2019
An Iterative Approach for Multiple Instance Learning Problems
Multiple Instance learning (MIL) algorithms are tasked with learning how...
research
∙
12/05/2018
Integrated unpaired appearance-preserving shape translation across domains
We address the problem of un-supervised geometric image-to-image transla...
research
∙
12/18/2017
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks
Learning-based representations have become the defacto means to address ...
research
∙
07/10/2017
An Analysis of Human-centered Geolocation
Online social networks contain a constantly increasing amount of images ...
research
∙
03/31/2016
Modeling Visual Compatibility through Hierarchical Mid-level Elements
In this paper we present a hierarchical method to discover mid-level ele...
research
∙
12/06/2015