{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tinycd-a-not-so-deep-learning-model-for","title":"TINYCD: A (Not So) Deep Learning Model For Change Detection","arxiv_id":"2207.13159","date":"2022-07-26","proceeding":null,"authors":["Andrea Codegoni","Gabriele Lombardi","Alessandro Ferrari"],"abstract":"In this paper, we present a lightweight and effective change detection model, called TinyCD. This model has been designed to be faster and smaller than current state-of-the-art change detection models due to industrial needs. Despite being from 13 to 140 times smaller than the compared change detection models, and exposing at least a third of the computational complexity, our model outperforms the current state-of-the-art models by at least $1\\%$ on both F1 score and IoU on the LEVIR-CD dataset, and more than $8\\%$ on the WHU-CD dataset. To reach these results, TinyCD uses a Siamese U-Net architecture exploiting low-level features in a globally temporal and locally spatial way. In addition, it adopts a new strategy to mix features in the space-time domain both to merge the embeddings obtained from the Siamese backbones, and, coupled with an MLP block, it forms a novel space-semantic attention mechanism, the Mix and Attention Mask Block (MAMB). Source code, models and results are available here: https://github.com/AndreaCodegoni/Tiny_model_4_CD","url_abs":"https://arxiv.org/abs/2207.13159v2","url_pdf":"https://arxiv.org/pdf/2207.13159v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tinycd-a-not-so-deep-learning-model-for","repo_url":"https://github.com/andreacodegoni/tiny_model_4_cd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tinycd-a-not-so-deep-learning-model-for","repo_url":"https://github.com/likyoo/open-cd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"building-change-detection-for-remote-sensing","task_name":"Building change detection for remote sensing images"},{"task_slug":"change-detection","task_name":"Change Detection"},{"task_slug":"change-detection-for-remote-sensing-images","task_name":"Change detection for remote sensing images"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"siamese-network","method_name":"Siamese Network"},{"method_slug":"siamese-u-net","method_name":"Siamese U-Net"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/building-change-detection-for-remote-sensing","task":"Building change detection for remote sensing images","dataset":"LEVIR-CD","model":"TinyCD","rank_in_archive_order":19,"of":37,"metrics":{"F1":"91.05","IoU":"83.57","Params(M)":"0.28"},"uses_additional_data":true},{"leaderboard":"/sota/building-change-detection-for-remote-sensing-1","task":"Building change detection for remote sensing images","dataset":"WHU Building Dataset","model":"TinyCD","rank_in_archive_order":2,"of":2,"metrics":{"F1":"91.74","IoU":"84.74"},"uses_additional_data":false},{"leaderboard":"/sota/change-detection-on-whu-cd","task":"Change Detection","dataset":"WHU-CD","model":"Tiny-CD","rank_in_archive_order":18,"of":22,"metrics":{"F1":"91.05","IoU":"83.57","Overall Accuracy":"99.10","Precision":"92.68","Recall":"89.47"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}