ARC Is a Vision Problem!

The article introduces Convolutional Nearest Neighbors (ConvNN), a framework that unifies Convolutional Neural Networks (CNNs) and Transformers by viewing convolution and self-attention as neighbor selection and aggregation methods. ConvNN allows for a systematic exploration of the spectrum between these two architectures, serving as a drop-in replacement for convolutional and attention layers. The framework's effectiveness is validated through classification tasks on CIFAR-10 and CIFAR-100 datasets.

Bladder cancer is a prevalent malignancy with a high recurrence rate of up to 78%, necessitating precise post-operative monitoring. Multi-sequence contrast-enhanced MRI is commonly utilized for recurrence detection, but interpreting these scans is challenging due to post-surgical changes. This study introduces a curated multi-sequence, multi-modal MRI dataset designed for bladder cancer recurrence prediction and proposes H-CNN-ViT, a new model aimed at enhancing prediction accuracy in this critical area.

Accurate modeling of cognitive decline in Alzheimer's disease is crucial for early stratification and personalized management. This study evaluates the predictive contributions of tabular and imaging-based representations, focusing on transformer-derived Magnetic Resonance Imaging (MRI) embeddings. A trajectory-aware labeling strategy based on Dynamic Time Warping clustering is introduced to capture heterogeneous cognitive change patterns. The study trains a 3D Vision Transformer (ViT) on harmonized MRI data to obtain anatomy-preserving embeddings, assessed using traditional and deep learning …

The article presents a systematic comparison of out-of-distribution (OOD) detection methods across different representation paradigms, specifically CNNs and Vision Transformers (ViTs). The study evaluates these methods using metrics such as AURC and AUGRC on datasets including CIFAR-10, CIFAR-100, SuperCIFAR-100, and TinyImageNet. Findings indicate that the learned feature space significantly influences OOD detection efficacy, with probabilistic scores being more effective for CNNs, while geometry-aware scores excel in ViTs under stronger shifts.