paper-with-me

Scene Classification

2개 벤치마크 · 논문 496편 · 이 태스크의 논문 보기 →

Benchmarks

Places365-Standard

결과 2개

Most implemented

Papers

Semi-Supervised Adaptation of Vision-Language Models for Image Classification

2026-08-26 · Mohamed L. Mekhalfi, Mohamad M. Al Rahhal, Yakoub Bazi, Salah E. Khenfer 외 arxiv

Vision-language models like CLIP have shown sig- nificant potential in handling natural images, yet their perfor- mance is often limited by the distinct characteristics of satellite imagery. While parameter-efficient ada…

Scene ClassificationImage Classification

Label-Decoupled Style Augmentation for Domain Generalization in Multi-Label Remote Sensing Scene Classification

2026-07-14 · Alaa Almouradi, Erchan Aptoula arxiv

Multi-label classification assigns several co-occurring labels to each aerial scene, yet deployed models often encounter data distributions different from their training. Feature-statistics augmentation such as MixStyle,…

Multi-Label ClassificationDomain GeneralizationScene Classification

Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing

2026-07-10 · Mohammad Dabaja, Turgay Celik arxiv

The deployment of large-scale foundation models, such as the Segment Anything Model 3 (SAM 3), promises a transition toward open-vocabulary, training-free computer vision. However, their capacity to generalize out-of-dis…

Instance SegmentationScene ClassificationObject Detection

TerraDiT-$Ω$: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive

2026-06-30 · Brian Wei, Srikumar Sastry, Daniel Cher, Eric Xing 외 hf

Generative models have achieved remarkable progress, yet applying them to satellite imagery remains challenging. Unlike natural imagery, satellite scenes are structured by spatially complex and semantically distinct geom…

Scene ClassificationData AugmentationObject Detection

MSNN-LINet: Cross-Modal Learning via Continuous Linear Integration

2026-06-30 · Gabriel Clinger arxiv

We present LINet (Linear Integration Network), a Multi-Stream Neural Network (MSNN) for RGB-D scene classification. Current multi-modal architectures treat feature fusion as a discrete, ad-hoc event: early fusion entangl…

Scene Classification

WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization

2026-06-18 · Qian Liang, Xiaomin Li, Ying Zhang, Jia Xu 외 arxiv

Recent text-to-image generation models have demonstrated remarkable capabilities in synthesizing highly realistic images from text inputs alone. Although existing benchmarks can evaluate the generation capabilities of va…

Text-to-Image GenerationScene Classification

전체 496편 보기 →