NGC | Catalog
CatalogModelsVisual ChangeNet Segmentation - (Research-only)

Visual ChangeNet Segmentation - (Research-only)

Logo for Visual ChangeNet Segmentation - (Research-only)
Visual ChangeNet-Segmentation (Research-only)
Latest Version
October 16, 2023
134.17 MB

Visual ChangeNet-Segmentation Model Card (Research-only)

Model Overview

The model described in this model card detects building change maps from a pair of co-registered remote sensing images (RSI). The inputs are a pair of co-registered pre-change golden image and a post-change test image of the same area under observation captured using RSI and the output is a binary segmentation change map denoting the change between the two images.

Model Architecture

Visual ChangeNet is a state of the art transformer-based Change Detection model. Visual ChangeNet is based on Siamese Network, which is a class of neural network architectures containing two or more identical subnetworks. The training algorithm works by updating the parameters across all the sub-networks in tandem. In TAO, Visual ChangeNet supports two images as input where the end goal is to either classify or segment the change between the "golden or reference" image and the "test" image. TAO supports the FAN backbone network for both Visual ChangeNet architectures. For more details about training FAN backbones, see the Pre-trained FAN based ImageNet Classification. In TAO, two different types of Change Detection networks are supported:

  • Visual ChangeNet-Segmentation - for segmentation of change between to input images.
  • Visual ChangeNet-Classification - for classification of change between to input images.

Visual ChangeNet-Classification is specifically intended for change classification. In this model card, the Visual ChangeNet-Segmentation model is leveraged to demonstrate building change detection using LEVIR-CD dataset for remote-sensing imagery. The model uses a pretrained FAN backbone, trained on NVImageNet dataset, and then fine-tunes on the LEVIR-CD dataset.


This model was trained using the visual_changenet entrypoint in TAO. The training algorithm optimizes the network to minimize the cross-entropy loss for every pixel of the mask.

Training Data

Visual ChangeNet-Segmentation model was trained on open-source remote sensing (RS) building change detection dataset called LEVIR-CD. The training dataset consists of 10,192 pair-wise co-registered images. LEVIR-CD is a building CD dataset that contains RS image pairs of resolution 1024 × 1024. From these images, we crop non-overlapping patches of size 256 × 256. They are randomly split into three parts to make train, val, and test sets of samples 7120, 1024 and 2048 respectively.

Dataset No. of images
LEVIR-CD 10,192

Following is a sample image showing a changed scenario.


Evaluation Data

The model performance was evaluated on a validation dataset which had a total of 2048 images.

Methodology and KPI

The performance of the Visual ChangeNet-Segmentation model is mainly measured using overall accuracy and precision, recall and IoU score for the change class.

Model Model Architecture Testing Images Precision Recall IoU F1 Overall Accuracy
Visual ChangeNet-Segmentation Siamese Network 2048 93.75 89.78 84.7 91.72 99.17

Real-time Inference Performance

The inference is run on the provided unpruned model at FP16 precision. The inference performance is run using trtexec on Jetson AGX Xavier, Xavier NX, Orin, Orin NX and NVIDIA T4, and Ampere GPUs. The Jetson devices are running at Max-N configuration for maximum GPU frequency. The performance shown here is the inference only performance. The end-to-end performance with streaming video data might vary depending on other bottlenecks in the hardware and software.

Platform BS FPS
Orin Nano 8GB 16 15.19
Orin NX 16GB 16 21.92
AGX Orin 64GB 16 55.07

How to Use this Model

These models need to be used with NVIDIA hardware and software. For hardware, the models can run on any NVIDIA GPU including NVIDIA Jetson devices. These models can only be used with Train Adapt Optimize (TAO) Toolkit, or TensorRT.

The primary use case intended for these models is for Visual ChangeNet-Segmentation using RGB component level images. The model is a Siamese Network which outputs semantic change maps denoting pixel-level change between the two images.

These models are intended for training and fine-tune using TAO Toolkit and user datasets for image comparison. High-fidelity models can be trained to the new use cases. A Jupyter notebook is available as a part of the TAO container and can be used to re-train.

The models are also intended for edge deployment using TensorRT.


Two imput images:

Pre-Change: RGB Image of dimensions: 256 X 256 X 3 (H x W x C)

Post-Change: RGB Image of dimensions: 256 X 256 X 3 (H x W x C)

Channel Ordering of the Input: NCHW, where N = Batch Size, C = number of channels (3), H = Height of images (256), W = Width of the images (256)


Segmentation change map with the same spatial resolution as the input images: 256 X 256 X 2 (H x W x C), where C = number of output change classes.

Input Image

Here is a sample image for a pre and post change images along with ground-truth segmentation change map side-by-side.

Using the model with TAO

To use these models as pretrained weights for transfer learning, please use the snippet below as template for the model and train component of the experiment spec file to train a Siamese Network model. For more information on the experiment spec file, see the TAO Toolkit User Guide - Visual ChangeNet-Segmentation.

    type: "fan_small_12_p4_hybrid"
    pretrained_backbone_path: null
    model_path: "???"


Expecting Co-registered Remote Sensing Imagery

The Visual ChangeNet-Segmentation Network model was trained on pair-wise co-registered RS imagery and might not perform well for mis-aligned image pairs not captured using RSI.

Model Versions

  • changenet_levircd_trainable_v1.0 - FAN-Hybrid Base Visual ChangeNet-Classification model LEVIR-CD trainable.
  • changenet_levircd_deployable_v1.0 - FAN-Hybrid Base Visual ChangeNet-Classification model LEVIR-CD deployable to deepstream.


Using TAO Pre-trained Models

Technical Blogs

Suggested Reading


License to use this model is covered by CC-BY-NC-SA-4.0. By downloading the unpruned or pruned version of the model, you accept the terms and conditions of these licenses.

Ethical Considerations

NVIDIA Visual ChangeNet-Segmentation model detects changes between pair-wise images. NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.