# Exploration of Optimized Semantic Segmentation Architectures for edge-Deployment on Drones

Source: [Exploration of Optimized Semantic Segmentation Architectures for edge-Deployment on Drones](<https://www.sota2.com/research/paper/68fa67ec1e209131cea19280>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:25:00.051Z

Authors: Vivek Parmar, Narayani Bhatia, Shubham Negi, Manan Suri

Published: 2020-07-06T15:49:18.000Z

## Abstract

In this paper, we present an analysis on the impact of network parameters for semantic segmentation architectures in context of UAV data processing. We present the analysis on the DroneDeploy Segmentation benchmark. Based on the comparative analysis we identify the optimal network architecture to be FPN-EfficientNetB3 with pretrained encoder backbones based on Imagenet Dataset. The network achieves IoU score of 0.65 and F1-score of 0.71 over the validation dataset. We also compare the various architectures in terms of their memory footprint and inference latency with further exploration of the impact of TensorRT based optimizations. We achieve memory savings of ~4.1x and latency improvement of 10% compared to Model: FPN and Backbone: InceptionResnetV2.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.02839>)

[PDF](<https://arxiv.org/pdf/2007.02839.pdf>)