# Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification

arXiv: https://arxiv.org/abs/2410.04492 · HTML: https://mlsanity.com/paper/2410.04492/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 63 references that are in the map.
- First posted on arXiv 6 Oct 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 10 of 10)

- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [The Herbarium Challenge 2019 Dataset](https://mlsanity.com/paper/1906.05372/) (2019)
- [When can transformers reason with abstract symbols?](https://mlsanity.com/paper/2310.09753/) (2023)
- [On Provable Length and Compositional Generalization](https://mlsanity.com/paper/2402.04875/) (2024)
- [A Theory for Length Generalization in Learning to Reason](https://mlsanity.com/paper/2404.00560/) (2024)
- [Improving Interpretability via Regularization of Neural Activation Sensitivity](https://mlsanity.com/paper/2211.08686/) (2022)

## Built on by (most cited first, 5 of 5)

- [Ordinal-Aware Calibration for Ordinal Classification](https://mlsanity.com/paper/2410.15658/) (2024)
- [Covariance-based Space Regularization for Few-shot Class Incremental Learning](https://mlsanity.com/paper/2411.01172/) (2024)
- [Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization](https://mlsanity.com/paper/2509.15791/) (2025)
- [Fourier Self-Supervision for Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2608.08963/) (2026)
- [PatchGen: Learning Soft Intra-Image Predictive Subsets for Visual Generalization](https://mlsanity.com/paper/2608.12766/) (2026)

## Abstract (arXiv)

Vision models excel in image classification but struggle to generalize to unseen data, such as classifying images from unseen domains or discovering novel categories. In this paper, we explore the relationship between logical reasoning and deep learning generalization in visual classification. A logical regularization termed L-Reg is derived which bridges a logical analysis framework to image classification. Our work reveals that L-Reg reduces the complexity of the model in terms of the feature distribution and classifier weights. Specifically, we unveil the interpretability brought by L-Reg, as it enables the model to extract the salient features, such as faces to persons, for classification. Theoretical analysis and experiments demonstrate that L-Reg enhances generalization across various scenarios, including multi-domain generalization and generalized category discovery. In complex real-world scenarios where images span unknown classes and unseen domains, L-Reg consistently improves generalization, highlighting its practical efficacy.