# Fault Localization for Buggy Deep Learning Framework Conversions in Image Recognition

arXiv: https://arxiv.org/abs/2306.06157 · HTML: https://mlsanity.com/paper/2306.06157/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 10 Jun 2023.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [DeepLocalize: Fault Localization for Deep Neural Networks](https://mlsanity.com/paper/2103.03376/) (2021)
- [DeepFault: Fault Localization for Deep Neural Networks](https://mlsanity.com/paper/1902.05974/) (2019)
- [An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications](https://mlsanity.com/paper/2101.04930/) (2021)
- [An Empirical Study of Challenges in Converting Deep Learning Models](https://mlsanity.com/paper/2206.14322/) (2022)
- [Using Machine Learning to Generate Test Oracles: A Systematic Literature Review](https://mlsanity.com/paper/2107.00906/) (2021)
- [Learning to Encode and Classify Test Executions](https://mlsanity.com/paper/2001.02444/) (2020)
- [M3: Semantic API Migrations](https://mlsanity.com/paper/2008.12118/) (2020)
- [Exploring Effects of Computational Parameter Changes to Image Recognition Systems](https://mlsanity.com/paper/2211.00471/) (2022)
- [Explaining Image Classifiers using Statistical Fault Localization](https://mlsanity.com/paper/1908.02374/) (2019)

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

- [FetaFix: Automatic Fault Localization and Repair of Deep Learning Model Conversions](https://mlsanity.com/paper/2312.15101/) (2023)
- [Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them](https://mlsanity.com/paper/2609.05881/) (2026)

## Abstract (arXiv)

When deploying Deep Neural Networks (DNNs), developers often convert models from one deep learning framework to another (e.g., TensorFlow to PyTorch). However, this process is error-prone and can impact target model accuracy. To identify the extent of such impact, we perform and briefly present a differential analysis against three DNNs widely used for image recognition (MobileNetV2, ResNet101, and InceptionV3) converted across four well-known deep learning frameworks (PyTorch, Keras, TensorFlow (TF), and TFLite), which revealed numerous model crashes and output label discrepancies of up to 100%. To mitigate such errors, we present a novel approach towards fault localization and repair of buggy deep learning framework conversions, focusing on pre-trained image recognition models. Our technique consists of four stages of analysis: 1) conversion tools, 2) model parameters, 3) model hyperparameters, and 4) graph representation. In addition, we propose various strategies towards fault repair of the faults detected. We implement our technique on top of the Apache TVM deep learning compiler, and we test it by conducting a preliminary fault localization analysis for the conversion of InceptionV3 from TF to TFLite. Our approach detected a fault in a common DNN converter tool, which introduced precision errors in weights, reducing model accuracy. After our fault localization, we repaired the issue, reducing our conversion error to zero.