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

TL;DR

TinyCD is a lightweight, fast, and effective change detection model that outperforms larger models in accuracy while being significantly smaller and less computationally demanding, suitable for industrial applications.

Contribution

The paper introduces TinyCD, a novel small-scale change detection model with a unique Siamese U-Net architecture and a new space-semantic attention mechanism, achieving superior performance with reduced complexity.

Findings

TinyCD is 13 to 140 times smaller than existing models.

It outperforms state-of-the-art models by at least 1% on F1 and IoU metrics.

The model reduces computational complexity by at least a third.

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