stp2y

[Submitted on 7 Aug 2024] View a PDF of the paper titled PushPull-Net: Inhibition-driven ResNet robust to image corruptions, by Guru Swaroop Bennabhaktula and 2 other authors View PDF HTML (experimental) Abstract:We introduce a novel computational unit, termed PushPull-Conv, in the first layer of a ResNet architecture, inspired by the anti-phase inhibition phenomenon observed in the primary visual cortex. This unit redefines the traditional convolutional layer by implementing a pair of complementary filters: a trainable push kernel and its counterpart, the pull kernel. The push kernel (analogous to traditional convolution) learns to respond to specific stimuli, while the pull kernel…

arXiv:2408.04114v1 Announce Type: new Abstract: This work addresses the challenge of factual consistency in text generation systems. We unify the tasks of Natural Language Inference, Summarization Evaluation, Factuality Verification and Factual Consistency Evaluation to train models capable of evaluating the factual consistency of source-target pairs across diverse domains. We rigorously evaluate these against eight baselines on a comprehensive benchmark suite comprising 22 datasets that span various tasks, domains, and document lengths. Results demonstrate that our method achieves state-of-the-art performance on this heterogeneous benchmark while addressing efficiency concerns and attaining cross-domain generalization. Source link lol

[Submitted on 7 Aug 2024] View a PDF of the paper titled Deep Generative Models for Subgraph Prediction, by Erfaneh Mahmoudzadeh and 3 other authors View PDF HTML (experimental) Abstract:Graph Neural Networks (GNNs) are important across different domains, such as social network analysis and recommendation systems, due to their ability to model complex relational data. This paper introduces subgraph queries as a new task for deep graph learning. Unlike traditional graph prediction tasks that focus on individual components like link prediction or node classification, subgraph queries jointly predict the components of a target subgraph based on evidence that is represented…

[Submitted on 7 Aug 2024] View a PDF of the paper titled AEye: A Visualization Tool for Image Datasets, by Florian Gr"otschla and 3 other authors View PDF HTML (experimental) Abstract:Image datasets serve as the foundation for machine learning models in computer vision, significantly influencing model capabilities, performance, and biases alongside architectural considerations. Therefore, understanding the composition and distribution of these datasets has become increasingly crucial. To address the need for intuitive exploration of these datasets, we propose AEye, an extensible and scalable visualization tool tailored to image datasets. AEye utilizes a contrastively trained model to embed images into semantically…