Related papers: Transforming Feature Space to Interpret Machine Le…

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

The use of machine learning to predict wave dynamics is a topic of growing interest, but commonly-used deep learning approaches suffer from a lack of interpretability of the trained models. Here we present an interpretable machine learning…

Exploring search spaces is one of the most unpredictable challenges that has attracted the interest of researchers for decades. One way to handle unpredictability is to characterise the search spaces and take actions accordingly. A…

Semantic image parsing, which refers to the process of decomposing images into semantic regions and constructing the structure representation of the input, has recently aroused widespread interest in the field of computer vision. The recent…

Face attribute evaluation plays an important role in video surveillance and face analysis. Although methods based on convolution neural networks have made great progress, they inevitably only deal with one local neighborhood with…

Fine-grained remote sensing image segmentation is essential for accurately identifying detailed objects in remote sensing images. Recently, vision transformer models (VTMs) pre-trained on large-scale datasets have demonstrated strong…

With increasing interest in explaining machine learning (ML) models, the first part of this two-part study synthesizes recent research on methods for explaining global and local aspects of ML models. This study distinguishes explainability…

SHAP is a popular method for measuring variable importance in machine learning models. In this paper, we study the algorithm used to estimate SHAP scores and outline its connection to the functional ANOVA decomposition. We use this…

Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically…

Vehicle Re-identification is attracting more and more attention in recent years. One of the most challenging problems is to learn an efficient representation for a vehicle from its multi-viewpoint images. Existing methods tend to derive…

Image understanding is an important research domain in the computer vision due to its wide real-world applications. For an image understanding framework that uses the Bag-of-Words model representation, the visual codebook is an essential…

Deep learning has achieved remarkable success in processing and managing unstructured data. However, its "black box" nature imposes significant limitations, particularly in sensitive application domains. While existing interpretable machine…

As data-driven methods rise in popularity in materials science applications, a key question is how these machine learning models can be used to understand microstructure. Given the importance of process-structure-property relations…

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to…

Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth…

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained…

How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question. Traditionally, this has been done with carefully engineered…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

The representations of the Earth's surface vary from one geographic region to another. For instance, the appearance of urban areas differs between continents, and seasonality influences the appearance of vegetation. To capture the diversity…

In the domain of scientific imaging, interpreting visual data often demands an intricate combination of human expertise and deep comprehension of the subject materials. This study presents a novel methodology to linguistically emulate and…