Leveraging unstructured conversations for detecting early dementia may be possible through information transfer from more systematically constrained representations.To explore whether cross-domain (from semi-structured to unstructured) transfer learning improves dementia classification from conversational speech, we fine-tuned a BERT-family model using semi-structured narratives.We further fine-tuned on naturalistic conversations recorded in the home, but found that direct transfer from BERT to conversations was more effective for improving generalization.These findings show scope to directly leverage unstructured language samples for in-the-wild dementia detection.

Class imbalance poses a significant challenge in classification tasks, where traditional approaches often lead to biased models and unreliable predictions. Undersampling and oversampling techniques have been commonly employed to address this issue, yet they suffer from inherent limitations stemming from their simplistic approach such as loss of information and additional biases respectively. In this paper, we propose a novel framework that leverages learning theory and concentration inequalities to overcome the shortcomings of traditional solutions. We focus on understanding the uncertainty in a class-dependent manner, as captured by confidence bounds that we directly embed into the learning process. By incorporating class-dependent estimates, our method can effectively adapt to the varying degrees of imbalance across different classes, resulting in more robust and reliable classification outcomes. We empirically show how our framework provides a promising direction for handling imbalanced data in classification tasks, offering practitioners a valuable tool for building more accurate and trustworthy models.

Transparency in AI models is crucial to designing, auditing, and deploying AI systems. However, 'black box' models are still used in practice for their predictive power despite their lack of transparency. This has led to a demand for post-hoc, model-agnostic surrogate explainers which provide explanations for decisions of any model by approximating its behaviour close to a query point with a surrogate model. However, it is often overlooked how the location of the query point in the decision surface of the black box model affects the faithfulness of the surrogate explainer. Here, we show that when using standard techniques, there is a decrease in agreement between the black box and the surrogate model for query points towards the edge of the test dataset and when moving away from the decision boundary. This originates from a mismatch between the data distributions used to train and evaluate surrogate explainers. We address this by leveraging knowledge about the test data distribution captured in the class labels of the black box model. By addressing this and encouraging users to take care in understanding the alignment of training and evaluation objectives, we empower them to construct more faithful surrogate explainers.

In this paper we present an extension of rotation-based iterative Gaussianization (RBIG). Although RBIG has been successfully applied to many tasks, it is limited to medium dimensionality data (on the order of a thousand dimensions). In images its application has been restricted to small image patches or isolated pixels, because the rotation operation in RBIG is based on principal or independent component analysis and these transformations are difficult to learn and scale. Here we present Convolutional RBIG: an extension that alleviates this issue by imposing that the rotation in RBIG is a convolution. We propose to learn convolutional rotations (i.e. orthonormal convolutions) by optimising for the reconstruction loss between the input and an approximate inverse of the transformation using the transposed convolution operation. Additionally, we suggest different regularizers in learning orthonormal convolutions. For example, imposing sparsity in the activations leads to a transformation that extends convolutional independent component analysis to multilayer architectures. We also highlight how statistical properties of the data, such as multivariate mutual information, can be obtained. We illustrate the behavior of the transform with a simple example of texture synthesis, and analyze its properties by visualizing the stimuli that maximize the response in certain feature and layer.

Explaining the decisions of models is becoming pervasive in the image processing domain, whether it is by using posthoc methods or by creating inherently interpretable models. While the widespread use of surrogate explainers is a welcome addition to inspect and understand black-box models, assessing the robustness and reliability of the explanations is key for their success. Additionally, whilst existing work in the explainability field proposes various strategies to address this problem, the challenges of working with data in the wild is often overlooked. For instance, in image classification, distortions to images can not only affect the predictions assigned by the model, but also the explanation. Given a clean and a distorted version of an image, even if the prediction probabilities are similar, the explanation may still be different. In this paper we propose a methodology to evaluate the effect of distortions in explanations by embedding perceptual distances that tailor the neighbourhoods used to training surrogate explainers. We also show that by operating in this way, we can make the explanations more robust to distortions. We generate explanations for images in the Imagenet-C dataset and demonstrate how using a perceptual distances in the surrogate explainer creates more coherent explanations for the distorted and reference images.

Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was usually taken from the human visual perceptual system and how the system processes different perturbations in order to replicate to what extent it determines our ability to judge image quality. While recent works have presented deep neural networks trained to predict human perceptual quality, very few borrow any intuitions from the human visual system. To address this, we present PerceptNet, a convolutional neural network where the architecture has been chosen to reflect the structure and various stages in the human visual system. We evaluate PerceptNet on various traditional perception datasets and note strong performance on a number of them as compared with traditional image quality metrics. We also show that including a nonlinearity inspired by the human visual system in classical deep neural networks architectures can increase their ability to judge perceptual similarity. Compared to similar deep learning methods, the performance is similar, although our network has a number of parameters that is several orders of magnitude less.