# DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised

Source: [DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised](<https://www.sota2.com/research/paper/68fa71b61e209131cea52aff>)

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

Data updated: 2026-07-09T05:00:01.225Z

Authors: Abanoub Ghobrial, Kerstin Eder

Published: 2023-11-13T16:44:29.000Z

## Abstract

Autonomous systems (AS) often rely on Deep Neural Network (DNN) classifiers to operate in complex and dynamically changing environments. However, during operation, these classifiers may encounter domains that differ from those seen during development, causing performance degradation under distribution shift. Removing systems from operation for labelled data collection and retraining is often impractical, particularly when adaptation must occur quickly and at scale. This paper introduces DIRA-SS, a self-supervised extension of Dynamic Incremental Regularised Adaptation (DIRA) that enables online domain adaptation using only a small number of unlabelled target-domain samples. DIRA-SS augments an existing classifier with an auxiliary retraining branch and adapts the shared feature representation through a rotation-prediction task, while elastic weight consolidation regularises important source-domain parameters to reduce destructive updates. This allows the model to benefit from transfer learning without requiring classification labels during operation. We evaluate DIRA-SS on CIFAR-10C, CIFAR-100C, and ImageNet-C using ResNet architectures under severe common corruptions. The results show that DIRA-SS substantially improves performance over the non-adapted source model, achieves accuracy close to the supervised DIRA method, and outperforms existing unsupervised test-time adaptation baselines on ImageNet-C when using only 100 target-domain samples.

## 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.

- [Image Classification on ImageNet-C (level 5)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-level-5.md>): Image Classification; ImageNet-C level 5; Avg Top-1 Acc (ImageNet-C L5): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2311.07461>)

[PDF](<https://arxiv.org/pdf/2311.07461.pdf>)