SyncAI.news, a Varaisys broadcasting
Anchoring with Visual Evidence: Explicit Semantic Anchors for Joint Change Detection and Captioning
KZ

Kai Zheng, Hang-Cheng Dong, Puyi Fang, Junjia Pan, Zhenkai Wu, Wei Zhang

· 1 min read

ResearcharXiv cs.CV

Anchoring with Visual Evidence: Explicit Semantic Anchors for Joint Change Detection and Captioning

arXiv:2611.24462v1 Announce Type: new Abstract: Joint change detection and captioning seeks to localize changes and describe them from bi-temporal remote sensing images. A key challenge is translating dense visual evidence into the semantic conditions that guide description generation. We propose Explicit Semantic Anchors (ESA), a supervised interface that exposes entity presence, temporal appearance variation, and spatial extent. A prediction-guided readout combines visual features and predicted change probabilities, and three factor heads estimate the corresponding anchor activations. These activations guide generation through two complementary routes. The context route maps the three factor activations to three separate memory tokens, one per factor, and appends them to the dense visual memory, while the lexicon route produces an additive vocabulary bias at each decoding step. Dense visual memory remains available for spatial detail and information beyond the explicit factors. Anchor targets are derived from existing images and change annotations, requiring no additional anchor-level language annotation. At inference, all conditions are computed from the input image pair and the model's own predictions. Experiments on LEVIR-MCI and WHU-CDC show strong joint detection and captioning performance, supporting the use of supervised visual attributes as explicit conditions for change description generation.

Original source

This story was published by arXiv cs.CV and written by Kai Zheng, Hang-Cheng Dong, Puyi Fang, Junjia Pan, Zhenkai Wu, Wei Zhang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News