Skip to search formSkip to main contentSkip to account menu
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
TLDR
This work introduces SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples and shows how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE.
View PDF on arXiv
Shallow and Deep Convolutional Networks for Saliency Prediction
TLDR
This paper addresses the problem with a completely data-driven approach by training a convolutional neural network (convnet) and proposes two designs: a shallow convnet trained from scratch, and a another deeper solution whose first three layers are adapted from another network trained for classification.
View on IEEE
Unsupervised label noise modeling and loss correction
TLDR
A suitable two-component mixture model is suggested as an unsupervised generative model of sample loss values during training to allow online estimation of the probability that a sample is mislabelled and correct the loss by relying on the network prediction.
View PDF on arXiv
A comparative evaluation of interactive segmentation algorithms
View via Publisher
A multiscale representation method for nonrigid shapes with a single closed contour
TLDR
The criteria that should be satisfied by a descriptor for nonrigid shapes with a single closed contour are discussed and a shape representation method that fulfills these criteria is proposed that is very efficient and invariant to several kinds of transformations.
View on IEEE
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
TLDR
This work shows that a naive pseudo-labeling overfits to incorrect pseudo-labels due to the so-called confirmation bias and demonstrates that mixup augmentation and setting a minimum number of labeled samples per mini-batch are effective regularization techniques for reducing it.
View on IEEE
Bags of Local Convolutional Features for Scalable Instance Search
TLDR
This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW), demonstrating the suitability of the BoW representation based on local CNN features for instance retrieval.
View on ACM
Fully Convolutional Crowd Counting on Highly Congested Scenes
TLDR
The state-of-the-art for crowd counting in high density scenes is advanced by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016), and a training set augmentation scheme that minimises redundancy among training samples to improve model generalisation and overall counting performance is developed.
View PDF on arXiv
Event detection in field sports video using audio-visual features and a support vector Machine
TLDR
A novel audio-visual feature-based framework for event detection in broadcast video of multiple different field sports and the results suggest that high event retrieval and content rejection statistics are achievable.
View on IEEE
Touch Screens for the Older User
It has been 20 years since Ben Schneiderman predicted that there would be an increase in the use of touch screen applications yet it has been only in recent years that this prediction has come to…
View PDF
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License