A Contrastive Learning Framework Empowered by Attention-based Feature Adaptation for Street-View Image Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: You, Qi, Cheng, Yitai, Zeng, Zichao, Haworth, James
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914337530052608
author You, Qi
Cheng, Yitai
Zeng, Zichao
Haworth, James
author_facet You, Qi
Cheng, Yitai
Zeng, Zichao
Haworth, James
contents Street-view image attribute classification is a vital downstream task of image classification, enabling applications such as autonomous driving, urban analytics, and high-definition map construction. It remains computationally demanding whether training from scratch, initialising from pre-trained weights, or fine-tuning large models. Although pre-trained vision-language models such as CLIP offer rich image representations, existing adaptation or fine-tuning methods often rely on their global image embeddings, limiting their ability to capture fine-grained, localised attributes essential in complex, cluttered street scenes. To address this, we propose CLIP-MHAdapter, a variant of the current lightweight CLIP adaptation paradigm that appends a bottleneck MLP equipped with multi-head self-attention operating on patch tokens to model inter-patch dependencies. With approximately 1.4 million trainable parameters, CLIP-MHAdapter achieves superior or competitive accuracy across eight attribute classification tasks on the Global StreetScapes dataset, attaining new state-of-the-art results while maintaining low computational cost. The code is available at https://github.com/SpaceTimeLab/CLIP-MHAdapter.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16590
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Contrastive Learning Framework Empowered by Attention-based Feature Adaptation for Street-View Image Classification
You, Qi
Cheng, Yitai
Zeng, Zichao
Haworth, James
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Street-view image attribute classification is a vital downstream task of image classification, enabling applications such as autonomous driving, urban analytics, and high-definition map construction. It remains computationally demanding whether training from scratch, initialising from pre-trained weights, or fine-tuning large models. Although pre-trained vision-language models such as CLIP offer rich image representations, existing adaptation or fine-tuning methods often rely on their global image embeddings, limiting their ability to capture fine-grained, localised attributes essential in complex, cluttered street scenes. To address this, we propose CLIP-MHAdapter, a variant of the current lightweight CLIP adaptation paradigm that appends a bottleneck MLP equipped with multi-head self-attention operating on patch tokens to model inter-patch dependencies. With approximately 1.4 million trainable parameters, CLIP-MHAdapter achieves superior or competitive accuracy across eight attribute classification tasks on the Global StreetScapes dataset, attaining new state-of-the-art results while maintaining low computational cost. The code is available at https://github.com/SpaceTimeLab/CLIP-MHAdapter.
title A Contrastive Learning Framework Empowered by Attention-based Feature Adaptation for Street-View Image Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.16590