Related papers: ProtoSnap: Prototype Alignment for Cuneiform Signs

Despite recent advances in machine learning and explainable AI, a gap remains in personalized preventive healthcare: predictions, interventions, and recommendations should be both understandable and verifiable for all stakeholders in the…

Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel…

Although Simultaneous Localization and Mapping (SLAM) has been an active research topic for decades, current state-of-the-art methods still suffer from instability or inaccuracy due to feature insufficiency or its inherent estimation drift,…

Modeling multi-modal time-series data is critical for capturing system-level dynamics, particularly in biosignals where modalities such as ECG, PPG, EDA, and accelerometry provide complementary perspectives on interconnected physiological…

Sign language recognition is important for natural and convenient communication between deaf community and hearing majority. We take the highly efficient initial step of automatic fingerspelling recognition system using convolutional neural…

Autoencoding has achieved great empirical success as a framework for learning generative models for natural images. Autoencoders often use generic deep networks as the encoder or decoder, which are difficult to interpret, and the learned…

Prompt learning is a new learning paradigm which reformulates downstream tasks as similar pretraining tasks on pretrained models by leveraging textual prompts. Recent works have demonstrated that prompt learning is particularly useful for…

Few-shot Semantic Segmentation (FSS) was proposed to segment unseen classes in a query image, referring to only a few annotated examples named support images. One of the characteristics of FSS is spatial inconsistency between query and…

While deep learning has achieved impressive performance in time series forecasting, it becomes increasingly crucial to understand its decision-making process for building trust in high-stakes scenarios. Existing interpretable models often…

Protoacoustic imaging showed great promise in providing real-time 3D dose verification of proton therapy. However, the limited acquisition angle in protoacoustic imaging induces severe artifacts, which significantly impairs its accuracy for…

Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…

Symbolic regression aims to find interpretable analytical expressions by searching over mathematical formula spaces to capture underlying system behavior, particularly in scientific modeling governed by physical laws. However, traditional…

Prototype-based methods use interpretable representations to address the black-box nature of deep learning models, in contrast to post-hoc explanation methods that only approximate such models. We propose the Neural Prototype Tree…

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…

Accurate image registration is essential in many medical imaging applications, yet most deep registration networks provide little indication of when or where their predictions are unreliable. Existing uncertainty estimation approaches, such…

Automatic, template-free extraction of information from form images is challenging due to the variety of form layouts. This is even more challenging for historical forms due to noise and degradation. A crucial part of the extraction process…

Data scarcity remains a fundamental challenge in robot learning. While human demonstrations benefit from abundant motion capture data and vast internet resources, robotic manipulation suffers from limited training examples. To bridge this…

Abstract--- Exploiting the spatial structure in scene images is a key research direction for scene recognition. Due to the large intra-class structural diversity, building and modeling flexible structural layout to adapt various image…

Recent advances in generative modeling show that pretrained representations can improve generation as conditioning features or alignment targets. Motivated by this, we study protein representations for predicting structures beyond…

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…