Low-resolution fine-grained image classification has recently made significant progress, largely thanks to the super-resolution techniques and knowledge distillation methods. However, these approaches ...

STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification (CVPR 2025) Siyi Du, Xinzhe Luo, Declan P. O'Regan, and Chen Qin ...

StreetVision Bittensor Subnet for Image Classification and Object Detection This network is a decentralized subnet designed to inference images to extract information such as construction sites. Built ...

This image serves as input for an enhanced ConvNeXt classification network, producing precise cloud categories based on meteorological standards. Additionally, cloud occlusion feature and cloud factor ...