Related papers: ProtoryNet - Interpretable Text Classification Via…

Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity…

We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered high-level sequence from a whole word…

High-dimensional policies, such as those represented by neural networks, cannot be reasonably interpreted by humans. This lack of interpretability reduces the trust users have in policy behavior, limiting their use to low-impact tasks such…

The lack of explainability of deep learning models limits the adoption of such models in clinical practice. Prototype-based models can provide inherent explainable predictions, but these have predominantly been designed for classification…

Prototype-based neural networks offer interpretable predictions by comparing inputs to learned, representative signal patterns anchored in training data. While such models have shown promise in the classification of physiological data, it…

Studies of image captioning are shifting towards a trend of a fully end-to-end paradigm by leveraging powerful visual pre-trained models and transformer-based generation architecture for more flexible model training and faster inference…

Despite their success and widespread adoption, the opaque nature of deep neural networks (DNNs) continues to hinder trust, especially in critical applications. Current interpretability solutions often yield inconsistent or oversimplified…

Interpretability is essential for deploying object detection systems in critical applications, especially under low-quality imaging conditions that degrade visual information and increase prediction uncertainty. Existing methods either…

Deep neural networks (DNNs) have demonstrated remarkable performance across various domains, but their inherent complexity makes them challenging to interpret. This is especially true for temporal graph regression tasks due to the complex…

Prediction accuracy and model explainability are the two most important objectives when developing machine learning algorithms to solve real-world problems. The neural networks are known to possess good prediction performance, but lack of…

Recognizing relations between entities is a pivotal task of relational learning. Learning relation representations from distantly-labeled datasets is difficult because of the abundant label noise and complicated expressions in human…

Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box transformers. We present a middle ground…

Uncovering the opacity of diffusion-based generative models is urgently needed, as their applications continue to expand while their underlying procedures largely remain a black box. With a critical question -- how can the diffusion…

This paper is concerned with paraphrase detection. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship…

Transformer architectures have achieved great success in solving natural language tasks, which learn strong language representations from large-scale unlabeled texts. In this paper, we seek to go further beyond and explore a new logical…

Mode decomposition is a prototypical pattern recognition problem that can be addressed from the (a priori distinct) perspectives of numerical approximation, statistical inference and deep learning. Could its analysis through these combined…

Explaining predictions of black-box neural networks is crucial when applied to decision-critical tasks. Thus, attribution maps are commonly used to identify important image regions, despite prior work showing that humans prefer explanations…

In this paper, we study a novel inference paradigm, termed as schema inference, that learns to deductively infer the explainable predictions by rebuilding the prior deep neural network (DNN) forwarding scheme, guided by the prevalent…

In this paper we propose a novel human-centered approach for detecting forgery in face images, using dynamic prototypes as a form of visual explanations. Currently, most state-of-the-art deepfake detections are based on black-box models…

Interpretability research often adopts a neuron-centric lens, treating individual neurons as the fundamental units of explanation. However, neuron-level explanations can be undermined by superposition, where single units respond to mixtures…