Zero-Shot Scene Change Detection

Authors: Kyusik Cho, Dong Yeop Kim, Euntai Kim

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We compare our approach and baseline through various experiments. While existing train-based baseline tend to specialize only in the trained domain, our method shows consistent performance across various domains, proving the competitiveness of our approach. We conducted extensive ablation experiments and more analyses in the supplementary materials to validate the efficacy and robustness of our proposed methods.
Researcher Affiliation Collaboration 1Yonsei University, Seoul, Republic of Korea 2Korea Electronics Technology Institute, Seoul, Republic of Korea
Pseudocode No The paper describes the methodology using prose and illustrative figures (Figure 1 and Figure 3), but it does not contain a clearly labeled pseudocode or algorithm block.
Open Source Code Yes Code https://github.com/kyusik-cho/ZSSCD
Open Datasets Yes Change Sim (Park et al. 2021) is a synthetic dataset with an industrial indoor environment. VL-CMU-CD (Alcantarilla et al. 2018) is a dataset that includes information on urban street view changes over a long period. PCD (Sakurada and Okatani 2015) is a dataset consisting of panoramic images.
Dataset Splits No The paper mentions using specific image sizes for predictions and evaluating on 'in-domain' and 'cross-domain' test sets, and states, 'We trained the baseline model on each subset and tested it across all subsets.' However, it does not provide explicit details on the training, validation, and test splits (e.g., percentages or sample counts) for reproducibility.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU models, or memory specifications used for running the experiments.
Software Dependencies No The paper mentions using 'Segment Anything Model (SAM)' and 'DEVA' as foundational models but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup No The paper states, 'Comprehensive details about parameters for F and G, and details about the mask generation process are provided in the supplementary materials.' It also mentions, 'For our experiments, we set Tmax to 60.' However, it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) or detailed training configurations in the main text.