# Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation Source: [Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:40:08.455Z Authors: Wenyu Zhang, Li Shen, Chuan-Sheng Foo Published: 2022-12-15T02:25:22.000Z ## Abstract Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to an unlabeled target domain. Large-data pre-trained networks are used to initialize source models during source training, and subsequently discarded. However, source training can cause the model to overfit to source data distribution and lose applicable target domain knowledge. We propose to integrate the pre-trained network into the target adaptation process as it has diversified features important for generalization and provides an alternate view of features and classification decisions different from the source model. We propose to distil useful target domain information through a co-learning strategy to improve target pseudolabel quality for finetuning the source model. Evaluation on 4 benchmark datasets show that our proposed strategy improves adaptation performance and can be successfully integrated with existing SFDA methods. Leveraging modern pre-trained networks that have stronger representation learning ability in the co-learning strategy further boosts performance. ## 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. - [Fundus Image Classification on ODIR to FIVES (target)](): Fundus Image Classification; ODIR to FIVES (target); Average Score: 75.3. - [Fundus Image Classification on ODIR to VietAI (target)](): Fundus Image Classification; ODIR to VietAI (target); Avg Score: 76. ## Original sources and implementation [Original paper]() [PDF]()