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
arXiv:2605. 15375v2 Announce Type: replace-cross Abstract: Remote sensing change detection (RSCD) localises changes between two images of the same geographic region.
By Bla\v{z} Rolih, Matic Fu\v{c}ka, Filip Wolf, Luka \v{C}ehovin Zajc
arXiv:2606. 31745v1 Announce Type: cross Abstract: Remote sensing change detection (CD) traditionally focuses on pixel-level binary segmentation, which identifies where changes occur but neither what nor why.
By Ziyuan Liu, Ruifei Zhu, Ouqiao Ma, Yuantao Gu
The paper introduces MGRL-RSCC, a multi‑granularity reward reinforcement learning framework for Remote Sensing Change Captioning (RSCC). It uses a CNN with hierarchical self‑attention to extract visual features, a Transformer decoder for visual‑to‑linguistic translation, and a dual‑decoding strategy combined with token‑level supervised learning and self‑critical reinforcement learning. Three reward functions—linguistic fluency, change state consistency, and structural‑semantic relevance—are employed to improve caption quality and reduce exposure bias and conservative generation.
By Futian Wang, Mengqi Wang, Xiao Wang, Wentao Wu, Haowen Wang, Zhicheng Zhao, Jin Tang
arXiv:2606. 28724v1 Announce Type: cross Abstract: Understanding and localizing subtle changes between paired images is critical for tasks such as surveillance and image editing.
By Jinhong Hu, Xiaoping Wang, Shuyin Huang, Guojin Zhong, Kaitai Liu, Kai Lu
arXiv:2611.05570v1 Announce Type: new
Abstract: Remote sensing change detection is typically formulated as Siamese feature comparison, where two images are encoded independently and a decoder determi...
By Buddhi Wijenayake, Dhananjaya Jayasundara, Vishal M. Patel
CoDeRNet is a unified framework for Change Detection & Captioning (CDC) that treats the problem as selective information routing between heterogeneous task branches. It introduces a Confidence‑Decomposed Routing (CoDeR) mechanism that decides when and where to transfer information based on receiver needs and sender reliability. Experiments on LEVIR‑MCI and WHU‑CDC demonstrate that CoDeRNet improves caption generation while maintaining strong change localization, showing that conditional, selective cross‑task communication is key to effective CDC under heterogeneous supervision.
By Eunki Cho, Hyeon Bae Kim, Seong Tae Kim
arXiv:2607. 22705v1 Announce Type: cross Abstract: Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations.
By Anuraag Gadehothur Karnam, Tarunesh Sathish
arXiv:2609.27149v1 Announce Type: new
Abstract: Remote sensing change detection requires both global reasoning across bitemporal images and precise localization of changed regions. However, dense att...
By Anuvab Sen, Maneet Chatterjee, Aparup Ghosh, Udayon Sen, Arnav Aditya, Yixin Zhang
arXiv:2606. 04433v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes.
By Zirui Wang, Junwei Yu, Adam Yala, David M. Chan, Joseph E. Gonzalez, Trevor Darrell
CompoSET is a new vision‑language benchmark that tests compositionality by presenting each image‑caption pair with a foil that differs by only a single controlled edit—such as color, count, spatial relation, or object state—while keeping the overall scene largely unchanged. The dataset contains 1,776 instances across 80 scenes, 16 edit types in four semantic categories, and captions at three verbosity levels, with an average of only 8% pixel change between base and foil images. Evaluation of 22 dual‑encoder VLMs shows that all models perform at or below chance on CompoSET, contrasting with their strong performance on prior benchmarks that conflate global image differences with compositional reasoning.
By Laure Delisle, Pietro Perona
arXiv:2606. 00987v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temporal visual reasoning remains underexplored.
By Bingyu Li, Da Zhang, Tao Huo, Zhiyuan Zhao, Junyu Gao, Xuelong Li