# Saliency Assisted Quantization for Neural Networks

arXiv: https://arxiv.org/abs/2411.05858 · HTML: https://mlsanity.com/paper/2411.05858/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 12 of 12)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Stochastic Gradient Descent as Approximate Bayesian Inference](https://mlsanity.com/paper/1704.04289/) (2017)
- [Tell Me Where to Look: Guided Attention Inference Network](https://mlsanity.com/paper/1802.10171/) (2018)
- [Investigating the influence of noise and distractors on the interpretation of neural networks](https://mlsanity.com/paper/1611.07270/) (2016)
- [Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image Segmentation](https://mlsanity.com/paper/2402.14611/) (2024)
- [Novel Saliency Analysis for the Forward Forward Algorithm](https://mlsanity.com/paper/2409.15365/) (2024)

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

- [Interpreting the Effects of Quantization on LLMs](https://mlsanity.com/paper/2508.16785/) (2025)
- [Resource-efficient medical image classification for edge devices](https://mlsanity.com/paper/2512.17515/) (2025)
- [NetworkFF: Unified Layer Optimization in Forward-Only Neural Networks](https://mlsanity.com/paper/2512.17531/) (2025)
- [Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning](https://mlsanity.com/paper/2605.18804/) (2026)
- [Detecting Unreliable Classifications from Quantized Models](https://mlsanity.com/paper/2610.18575/) (2026)

## Abstract (arXiv)

Deep learning methods have established a significant place in image classification. While prior research has focused on enhancing final outcomes, the opaque nature of the decision-making process in these models remains a concern for experts. Additionally, the deployment of these methods can be problematic in resource-limited environments. This paper tackles the inherent black-box nature of these models by providing real-time explanations during the training phase, compelling the model to concentrate on the most distinctive and crucial aspects of the input. Furthermore, we employ established quantization techniques to address resource constraints. To assess the effectiveness of our approach, we explore how quantization influences the interpretability and accuracy of Convolutional Neural Networks through a comparative analysis of saliency maps from standard and quantized models. Quantization is implemented during the training phase using the Parameterized Clipping Activation method, with a focus on the MNIST and FashionMNIST benchmark datasets. We evaluated three bit-width configurations (2-bit, 4-bit, and mixed 4/2-bit) to explore the trade-off between efficiency and interpretability, with each configuration designed to highlight varying impacts on saliency map clarity and model accuracy. The results indicate that while quantization is crucial for implementing models on resource-limited devices, it necessitates a trade-off between accuracy and interpretability. Lower bit-widths result in more pronounced reductions in both metrics, highlighting the necessity of meticulous quantization parameter selection in applications where model transparency is paramount. The study underscores the importance of achieving a balance between efficiency and interpretability in the deployment of neural networks.