Corpus ID: 234336860

Human-Aided Saliency Maps Improve Generalization of Deep Learning

  title={Human-Aided Saliency Maps Improve Generalization of Deep Learning},
  author={Aidan Boyd and K. Bowyer and A. Czajka},
Deep learning has driven remarkable accuracy increases in many computer vision problems. One ongoing challenge is how to achieve the greatest accuracy in cases where training data is limited. A second ongoing challenge is that trained models are sometimes fragile in the sense that the accuracy achieved does not generalize well, even to new data that is subjectively similar to the training set. We address these challenges in a novel way, with the first-ever (to our knowledge) exploration of… Expand

Figures and Tables from this paper


Attention Augmented Convolutional Networks
It is found that Attention Augmentation leads to consistent improvements in image classification on ImageNet and object detection on COCO across many different models and scales, including ResNets and a state-of-the art mobile constrained network, while keeping the number of parameters similar. Expand
AutoAugment: Learning Augmentation Strategies From Data
This paper describes a simple procedure called AutoAugment to automatically search for improved data augmentation policies, which achieves state-of-the-art accuracy on CIFAR-10, CIFar-100, SVHN, and ImageNet (without additional data). Expand
Human Uncertainty Makes Classification More Robust
It is shown that, while contemporary classifiers fail to exhibit human-like uncertainty on their own, explicit training on this dataset closes this gap, supports improved generalization to increasingly out-of-training-distribution test datasets, and confers robustness to adversarial attacks. Expand
A survey on Image Data Augmentation for Deep Learning
This survey will present existing methods for Data Augmentation, promising developments, and meta-level decisions for implementing DataAugmentation, a data-space solution to the problem of limited data. Expand
Visual Psychophysics for Making Face Recognition Algorithms More Explainable
This paper suggests that visual psychophysics is a viable methodology for making face recognition algorithms more explainable, and a comprehensive set of procedures is developed for assessing face recognition algorithm behavior. Expand
Deep Face Recognition: A Survey
A comprehensive review of the recent developments on deep FR, covering broad topics on algorithm designs, databases, protocols, and application scenes, and the technical challenges and several promising directions are highlighted. Expand
A Survey of Image Synthesis Methods for Visual Machine Learning
This survey provides a comprehensive list of the existing image synthesis methods for visual machine learning, categorized in the context of image generation, using a taxonomy based on modelling and rendering, while a classification is made concerning the computer vision applications they are used. Expand
Deep Learning for Generic Object Detection: A Survey
A comprehensive survey of the recent achievements in this field brought about by deep learning techniques, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. Expand
Human Attention in Image Captioning: Dataset and Analysis
By integrating the soft attention model with image saliency, the model can significantly improve the model’s performance on Flickr30k and MSCOCO benchmarks and indicate a large gap between humans and machines in regards to top-down attention. Expand
Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
  • ByungSoo Ko, Geonmo Gu
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
The proposed method generates synthetic points containing augmented information by a combination of feature points and performs hard negative pair mining to learn with the most informative feature representations and can be used for existing metric learning losses without affecting model size, training speed, or optimization difficulty. Expand