# Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective

arXiv: https://arxiv.org/abs/2509.00859 · HTML: https://mlsanity.com/paper/2509.00859/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 51 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Surrogate Gap Minimization Improves Sharpness-Aware Training](https://mlsanity.com/paper/2203.08065/) (2022)
- [Domain Generalization via Conditional Invariant Representation](https://mlsanity.com/paper/1807.08479/) (2018)
- [Overcoming Oscillations in Quantization-Aware Training](https://mlsanity.com/paper/2203.11086/) (2022)
- [Domain Agnostic Learning with Disentangled Representations](https://mlsanity.com/paper/1904.12347/) (2019)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Network Quantization with Element-wise Gradient Scaling](https://mlsanity.com/paper/2104.00903/) (2021)
- [Oscillation-free Quantization for Low-bit Vision Transformers](https://mlsanity.com/paper/2302.02210/) (2023)

## Built on by (most cited first, 2 of 2)

- [Neural Network Quantization by Learning Low-Loss Subspaces](https://mlsanity.com/paper/2606.25087/) (2026)
- [Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models](https://mlsanity.com/paper/2607.11359/) (2026)

## Abstract (arXiv)

Current quantization-aware training (QAT) methods primarily focus on enhancing the performance of quantized models on in-distribution (I.D) data, while overlooking the potential performance degradation on out-of-distribution (OOD) data. In this paper, we first substantiate this problem through rigorous experiment, showing that QAT can lead to a significant OOD generalization performance degradation. Further, we find the contradiction between the perspective that flatness of loss landscape gives rise to superior OOD generalization and the phenomenon that QAT lead to a sharp loss landscape, can cause the above problem. Therefore, we propose a flatness-oriented QAT method, FQAT, to achieve generalizable QAT. Specifically, i) FQAT introduces a layer-wise freezing mechanism to mitigate the gradient conflict issue between dual optimization objectives (i.e., vanilla QAT and flatness). ii) FQAT proposes an disorder-guided adaptive freezing algorithm to dynamically determines which layers to freeze at each training step, effectively addressing the challenges caused by interference between layers. A gradient disorder metric is designed to help the algorithm identify unstable layers during training. Extensive experiments on influential OOD benchmark demonstrate the superiority of our method over state-of-the-art baselines under both I.D and OOD image classification tasks.