Sorry, you need to enable JavaScript to visit this website.

Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization, inspiring many compression-based regularization methods. In this paper, we introduce REVE, a new regularization scheme. Noting that compressing the representation can be sub-optimal, our first contribution is to identify a variable that is directly responsible for the final prediction. Our method aims at compressing the class conditioned entropy of this latter variable.

Categories:
33 Views

This paper proposed a modified YOLOv3 which has an extra object depth prediction module for obstacle detection and avoidance. We use a pre-processed KITTI dataset to train the proposed, unified model for (i) object detection and (ii) depth prediction and use the AirSim flight simulator to generate synthetic aerial images to verify that our model can be applied in different data domains.

Categories:
296 Views

The notorious incident of sudden infant death syndrome (SIDS) can easily happen to a newborn due to many environmental factors. To prevent such tragic incidents from happening, we propose a multi-task deep learning framework that detects different facial traits and two life-threatening indicators, i.e. which facial parts are occluded or covered, by analyzing the infant head image. Furthermore, we extend and adapt the recently developed models that capture data-dependent uncertainty from noisy observations for our application.

Categories:
17 Views

This work exploits the basic denoising autoencoding (DAE) as enhanced priori for color image restoration (IR). The proposed method consists of two steps: enhanced DAE network learning and iterative restoration. To be special, at the training phase, a denoising network taking 6-dimensional variable as input is trained. Then, the network-driven high-dimensional prior information embedded DAE priori is utilized in the iterative restoration procedure. We first map the intermediate color image to be 6 dimensional and employ the higher-dimensional network to handle its corrupted version.

Categories:
59 Views

Insufficient reasoning for their predictions has for long been a major drawback of neural networks and has proved to be a major obstacle for their adoption by several fields of application. This paper presents a framework for discriminative localization, which helps shed some light into the decision-making of Convolutional Neural Networks (CNN). Our framework generates robust, refined and high-quality Class Activation Maps, without impacting the CNN’s performance.

Categories:
126 Views

The goal of endoscopic analysis is to find abnormal lesions and determine further therapy from the obtained information. However, the procedure produces a variety of non-informative frames and lesions can be missed due to poor video quality. Especially when analyzing entire endoscopic videos made by non-expert endoscopists, informative frame classification is crucial to e.g. video quality grading. This work concentrates on the design of an automated indication of informativeness of video frames.

Categories:
60 Views

Pages