Papers › Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks

Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks

31 Dec 2019ECCV 2020 8arXiv:1912.13503archive 2025-07-28

Jeffrey O. Zhang, Alexander Sax, Amir Zamir, Leonidas Guibas, Jitendra Malik

When training a neural network for a desired task, one may prefer to adapt a pre-trained network rather than starting from randomly initialized weights. Adaptation can be useful in cases when training data is scarce, when a single learner needs to perform multiple tasks, or when one wishes to encode priors in the network. The most commonly employed approaches for network adaptation are fine-tuning and using the pre-trained network as a fixed feature extractor, among others. In this paper, we propose a straightforward alternative: side-tuning. Side-tuning adapts a pre-trained network by training a lightweight "side" network that is fused with the (unchanged) pre-trained network via summation. This simple method works as well as or better than existing solutions and it resolves some of the basic issues with fine-tuning, fixed features, and other common approaches. In particular, side-tuning is less prone to overfitting, is asymptotically consistent, and does not suffer from catastrophic forgetting in incremental learning. We demonstrate the performance of side-tuning under a diverse set of scenarios, including incremental learning (iCIFAR, iTaskonomy), reinforcement learning, imitation learning (visual navigation in Habitat), NLP question-answering (SQuAD v2), and single-task transfer learning (Taskonomy), with consistently promising results.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jozhang97/side-tuning mentioned on GitHubpytorchMIT report
thezingaro/multimodal-side-tuning mentioned on GitHubpytorchGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Imitation LearningIncremental LearningQuestion AnsweringReinforcement LearningTransfer LearningVisual Navigation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections