← Back to all news
arXiv Computer Vision By Jiyoung Park, InJae Oh, Jung Uk Kim

Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning

Read the original on arXiv Computer Vision →

The paper introduces MEDIC, a framework for change captioning that explicitly models different change types such as color shifts and object additions. MEDIC uses type‑specialized memory experts that dynamically retrieve relevant visual patterns and softly route inputs across these experts, enabling each to focus on the most informative cues for its change category. Experiments show that MEDIC consistently outperforms existing methods on diverse and challenging datasets.

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 AI
Aug 26

Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing

The paper introduces KnowChange, a framework that uses pretrained vision‑language models to guide the synthesis of change data for remote sensing. By reasoning about plausible change locations and class transitions, KnowChange flexibly generates diverse change types within a unified pipeline. Experiments show that data produced by KnowChange outperforms existing synthetic datasets in both synthetic‑to‑real transfer and data augmentation scenarios, even at a compact scale.

By Yaoyi Qi, Xingxing Weng, Chao Pang, Yongkang Cui, Xiangyu Hao, Xiaokang Zhang, Guibo Zhu, Gui-Song Xia
llmsmultimodal
More like this →
arXiv Computer Vision
Sep 24

From Change Captions to Change Detection: Semantic-Appearance Agreement Framework for Remote Sensing Change Detection

The paper proposes a weakly supervised remote sensing change detection method that uses change captions as the sole supervision signal, eliminating the need for pixel‑level change masks. It introduces a caption‑driven generation pipeline to create bi‑temporal image pairs with controlled changes and a Semantic‑Appearance Agreement Framework (SAAF) that fuses caption‑grounded semantic responses with RGB differences for accurate change localization. Experiments on the Flair‑RSGen and WHU‑CDC datasets demonstrate that SAAF outperforms existing limited‑supervision baselines in macro‑averaged IoU and F1 metrics.

By Yuan Qian, Jie Ma
More like this →