Papers › TINYCD: A (Not So) Deep Learning Model For Change Detection

TINYCD: A (Not So) Deep Learning Model For Change Detection

26 Jul 2022arXiv:2207.13159archive 2025-07-28

Andrea Codegoni, Gabriele Lombardi, Alessandro Ferrari

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

PaperPDFCode

Code

andreacodegoni/tiny_model_4_cd officialmentioned in papermentioned on GitHubpytorch report
likyoo/open-cd pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Building change detection for remote sensing imagesChange DetectionChange detection for remote sensing imagesDeep Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Building change detection for remote sensing images LEVIR-CD TinyCD F1 91.05 #19 of 37 Archive leaderboard report
Building change detection for remote sensing images LEVIR-CD TinyCD IoU 83.57 #19 of 37 Archive leaderboard report
Building change detection for remote sensing images LEVIR-CD TinyCD Params(M) 0.28 #19 of 37 Archive leaderboard report
Building change detection for remote sensing images WHU Building Dataset TinyCD F1 91.74 #2 of 2 Archive leaderboard report
Building change detection for remote sensing images WHU Building Dataset TinyCD IoU 84.74 #2 of 2 Archive leaderboard report
Change Detection WHU-CD Tiny-CD F1 91.05 #18 of 22 Archive leaderboard report
Change Detection WHU-CD Tiny-CD IoU 83.57 #18 of 22 Archive leaderboard report
Change Detection WHU-CD Tiny-CD Overall Accuracy 99.10 #18 of 22 Archive leaderboard report
Change Detection WHU-CD Tiny-CD Precision 92.68 #18 of 22 Archive leaderboard report
Change Detection WHU-CD Tiny-CD Recall 89.47 #18 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Concatenated Skip ConnectionConvolutionMax PoolingReLUSiamese NetworkSiamese U-NetU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections