# Structured Output Regularization: a framework for few-shot transfer learning

arXiv: https://arxiv.org/abs/2510.08728 · HTML: https://mlsanity.com/paper/2510.08728/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 15 of 15)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [On the Challenges and Perspectives of Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2306.05705/) (2023)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting](https://mlsanity.com/paper/2007.03260/) (2020)
- [Only Train Once: A One-Shot Neural Network Training And Pruning Framework](https://mlsanity.com/paper/2107.07467/) (2021)
- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification](https://mlsanity.com/paper/2306.09579/) (2023)
- [Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?](https://mlsanity.com/paper/2401.12902/) (2024)
- [Targeted Self Supervision for Classification on a Small COVID-19 CT Scan Dataset](https://mlsanity.com/paper/2011.10188/) (2020)
- [Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization](https://mlsanity.com/paper/1611.05527/) (2016)
- [A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks](https://mlsanity.com/paper/2201.08652/) (2022)

## Abstract (arXiv)

Traditional transfer learning typically reuses large pre-trained networks by freezing some of their weights and adding task-specific layers. While this approach is computationally efficient, it limits the model's ability to adapt to domain-specific features and can still lead to overfitting with very limited data. To address these limitations, we propose Structured Output Regularization (SOR), a simple yet effective framework that freezes the internal network structures (e.g., convolutional filters) while using a combination of group lasso and L1 penalties. This framework tailors the model to specific data with minimal additional parameters and is easily applicable to various network components, such as convolutional filters or various blocks in neural networks enabling broad applicability for transfer learning tasks. We evaluate SOR on three few shot medical imaging classification tasks and we achieve competitive results using DenseNet121, and EfficientNetB4 bases compared to established benchmarks.