← Back to all news
arXiv Computer Vision By Eftychios Protopapadakis, Konstantinos Makantasis, Konstantinos M. Giannoutakis

Prototype-Rule Neurosymbolic Regularization for Rank-Constrained Tensor Neural Networks under Label Scarcity

Read the original on arXiv Computer Vision →

The paper proposes a neurosymbolic regularization framework that adds a differentiable prototype‑rule to rank‑constrained tensor neural networks, aiming to improve class geometry under limited supervision. Experiments on four hyperspectral datasets with various Rank‑R settings and spatially separated folds show that training‑time prototype regularization yields the majority of performance gains, while inference fusion of prototype evidence with neural logits has a smaller, dataset‑dependent effect. The method achieves notable Macro‑F1 improvements, especially on the Botswana and Indian Pines benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Machine Learning
Aug 18

Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks

arXiv:2608. 16241v1 Announce Type: cross Abstract: Feature extraction for hyperspectral image classification is conventionally addressed using rigid tensor decompositions that fail to capture complex spatio-spectral interdependencies, or heavily parameterized convolutional neural networks that are computationally expensive.

By S\"uha Tuna, \"Ulker Ba\c{s}ar
computer-visionbenchmarks
More like this →
arXiv Computer Vision
3d ago

Hyperspectral Image Models: Technical Report

The technical report introduces Hyperspectral Image Models, a modular framework that unifies 55 deep‑learning models across six paradigms for hyperspectral remote sensing. It standardizes tensor conventions, evaluation protocols, and dataset handling, integrating 24 benchmark scenes from various sensors and providing tools to avoid train‑test overlap. Experiments across 1,320 model‑scene combinations show that scene difficulty outweighs architecture, with no single paradigm dominating and small models achieving performance comparable to much larger ones.

By Tanishq Rachamalla, Aryan Das, Srishti Kaushik, Swalpa Kumar Roy
llmsbenchmarks
More like this →
arXiv Computer Vision
4d ago

HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing

HyperSAM is a promptable foundation model for hyperspectral remote sensing that integrates a data‑centric synthesis pipeline with a spectral adaptation architecture based on Segment Anything Model 3 (SAM3). The model generates full‑spectrum hyperspectral cubes from high‑resolution multispectral imagery using a physics‑informed abundance‑transfer generator, and employs SAM3‑derived pseudo‑masks for object‑centric supervision. With a frozen SAM3 RGB branch, a trainable hyperspectral encoder, ControlNet‑style feature injection, and a mixture‑of‑experts mask refiner, HyperSAM demonstrates strong generalization across diverse hyperspectral tasks such as classification, anomaly detection, change detection, target detection, and airborne oil‑spill mapping.

By Li Pang, Xinqiao Wu, Jing Yao, Pedram Ghamisi, Jun Zhou, Zhengchao Chen, Deyu Meng, Xiangyong Cao
llmscomputer-visionmultimodal
More like this →