# Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognition

Source: [Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognition](<https://www.sota2.com/research/paper/68fa6ad81e209131cea2ab8d>)

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

Data updated: 2025-10-28T13:56:49.911Z

Authors: Alan Preciado-Grijalva, Venkata Santosh Sai Ramireddy Muthireddy

Published: 2021-09-28T01:22:12.000Z

## Abstract

It has been well proved that deep networks are efficient at extracting features from a given (source) labeled dataset. However, it is not always the case that they can generalize well to other (target) datasets which very often have a different underlying distribution. In this report, we evaluate four different domain adaptation techniques for image classification tasks: DeepCORAL, DeepDomainConfusion, CDAN and CDAN+E. These techniques are unsupervised given that the target dataset dopes not carry any labels during training phase. We evaluate model performance on the office-31 dataset. A link to the github repository of this report can be found here: https://github.com/agrija9/Deep-Unsupervised-Domain-Adaptation.

## 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/2109.13420>)

[PDF](<https://arxiv.org/pdf/2109.13420.pdf>)