In the dynamic field of machine learning, foundation models have recently gained prominence, particularly for their application in natural language processing and computer vision. The foundational Segment Anything Model (SAM), known for its interactive image segmentation via prompts, serves as the basis for this study. We introduce ChangeSAM, a tailored adaptation of SAM for street scene image change detection (CD). ChangeSAM utilizes the versatility and vast knowledge of SAM, adapting it to effectively identify semantic changes in image pairs. Two architectural adaptations are introduced - Pre Decoder Fusion (PreDF) and Post Decoder Fusion (PostDF) - enabling ChangeSAM to process dual images. Enhancements through Prompt Tuning and Low-Rank Adaptation (LoRA) are integrated, achieving a balance between reusability, computational efficiency, and accuracy. Our evaluation on the VL-CMU-CD dataset shows that with minimal parameter adjustments, ChangeSAM achieves accuracy on par with fully fine-tuned models. This work contributes to the ongoing development of foundation models in practical applications, illustrating the viability and potential of adaptable, efficient models in scenarios with limited computational resources, such as intelligent vehicles.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    ChangeSAM: Adapting the Segment Anything Model to Street Scene Image Change Detection


    Beteiligte:


    Erscheinungsdatum :

    24.09.2024


    Format / Umfang :

    2962266 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    When segment anything model meets inventorying of roadway assets

    Zhang, Chenyu / Huang, Sam / Qin, Ruwen | Elsevier | 2024

    Freier Zugriff


    Adapting indexing features to scene structures for relevant image retrieval

    Qiu, G. / Sudirman, S. / Institution of Electrical Engineers | British Library Conference Proceedings | 2003


    DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection

    Chen, Shuo / Yang, Kailun / Stiefelhagen, Rainer | IEEE | 2021