Related papers: Interpreting Medical Image Classifiers by Optimiza…

Aesthetic image cropping is a practical but challenging task which aims at finding the best crops with the highest aesthetic quality in an image. Recently, many deep learning methods have been proposed to address this problem, but they did…

Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the…

Various types of saliency methods have been proposed for explaining black-box classification. In image applications, this means highlighting the part of the image that is most relevant for the current decision. Unfortunately, the different…

The human visual system employs a selective attention mechanism to understand the visual world in an eficient manner. In this paper, we show how computational models of this mechanism can be exploited for the computer vision application of…

Recent progress in brain-guided image generation has improved the quality of fMRI-based reconstructions; however, fundamental challenges remain in preserving object-level structure and semantic fidelity. Many existing approaches overlook…

The deployment of automated systems to diagnose diseases from medical images is challenged by the requirement to localise the diagnosed diseases to justify or explain the classification decision. This requirement is hard to fulfil because…

The widespread use of black-box AI models has raised the need for algorithms and methods that explain the decisions made by these models. In recent years, the AI research community is increasingly interested in models' explainability since…

In this work we develop a fast saliency detection method that can be applied to any differentiable image classifier. We train a masking model to manipulate the scores of the classifier by masking salient parts of the input image. Our model…

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of…

Spurious features associated with class labels can lead image classifiers to rely on shortcuts that don't generalize well to new domains. This is especially problematic in medical settings, where biased models fail when applied to different…

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…

Supervised learning method requires a large volume of annotated datasets. Collecting such datasets is time-consuming and expensive. Until now, very few annotated COVID-19 imaging datasets are available. Although self-supervised learning…

It is difficult to accurately label ambiguous and complex shaped targets manually by binary masks. The weakness of binary mask under-expression is highlighted in medical image segmentation, where blurring is prevalent. In the case of…

Almost all previous works on saliency detection have been dedicated to conventional images, however, with the outbreak of panoramic images due to the rapid development of VR or AR technology, it is becoming more challenging, meanwhile…

Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data…

Deep learning models are now used in many different industries, while in certain domains safety is not a critical issue in the medical field it is a huge concern. Not only, we want the models to generalize well but we also want to know the…

An integrated approach is proposed across visual and textual data to both determine and justify a medical diagnosis by a neural network. As deep learning techniques improve, interest grows to apply them in medical applications. To enable a…

Image retargeting is the task of making images capable of being displayed on screens with different sizes. This work should be done so that high-level visual information and low-level features such as texture remain as intact as possible to…

Medical images differ from natural images in significantly higher resolutions and smaller regions of interest. Because of these differences, neural network architectures that work well for natural images might not be applicable to medical…

In recent years, several Weakly Supervised Semantic Segmentation (WS3) methods have been proposed that use class activation maps (CAMs) generated by a classifier to produce pseudo-ground truths for training segmentation models. While CAMs…