# Faster gaze prediction with dense networks and Fisher pruning

arXiv: https://arxiv.org/abs/1801.05787 · HTML: https://mlsanity.com/paper/1801.05787/

## Key facts

- Cited by 94 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2018.

## Built on by (most cited first, 30 of 94)

- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Training Neural Networks with Fixed Sparse Masks](https://mlsanity.com/paper/2111.09839/) (2021)
- [Zero-Cost Proxies for Lightweight NAS](https://mlsanity.com/paper/2101.08134/) (2021)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [A Fast Post-Training Pruning Framework for Transformers](https://mlsanity.com/paper/2204.09656/) (2022)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Group Fisher Pruning for Practical Network Compression](https://mlsanity.com/paper/2108.00708/) (2021)
- [How Powerful are Performance Predictors in Neural Architecture Search?](https://mlsanity.com/paper/2104.01177/) (2021)
- [Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach](https://mlsanity.com/paper/2210.05177/) (2022)
- [A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification](https://mlsanity.com/paper/2205.07877/) (2022)
- [Parameter-Efficient Fine-Tuning without Introducing New Latency](https://mlsanity.com/paper/2305.16742/) (2023)
- [M-FAC: Efficient Matrix-Free Approximations of Second-Order Information](https://mlsanity.com/paper/2107.03356/) (2021)
- [Differentiable Subset Pruning of Transformer Heads](https://mlsanity.com/paper/2108.04657/) (2021)
- [MQBench: Towards Reproducible and Deployable Model Quantization Benchmark](https://mlsanity.com/paper/2111.03759/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance](https://mlsanity.com/paper/2505.07004/) (2025)
- [SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning](https://mlsanity.com/paper/2110.11395/) (2021)
- [DECORE: Deep Compression with Reinforcement Learning](https://mlsanity.com/paper/2106.06091/) (2021)
- [HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers](https://mlsanity.com/paper/2302.09632/) (2023)
- [Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency](https://mlsanity.com/paper/2105.08667/) (2021)
- [ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies](https://mlsanity.com/paper/2110.10423/) (2021)
- [EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization](https://mlsanity.com/paper/2307.10554/) (2023)
- [Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities](https://mlsanity.com/paper/2307.01998/) (2023)
- [Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning](https://mlsanity.com/paper/2311.03748/) (2023)
- [GradSign: Model Performance Inference with Theoretical Insights](https://mlsanity.com/paper/2110.08616/) (2021)
- [Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively](https://mlsanity.com/paper/2211.01642/) (2022)
- [TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge](https://mlsanity.com/paper/2307.09988/) (2023)
- [Differentiable Network Pruning for Microcontrollers](https://mlsanity.com/paper/2110.08350/) (2021)
- [Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning](https://mlsanity.com/paper/2301.05219/) (2023)
- [No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models](https://mlsanity.com/paper/2202.02664/) (2022)

## Abstract (arXiv)

Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition. However, as we show in this paper, these networks are highly overparameterized for the task of fixation prediction. We first present a simple yet principled greedy pruning method which we call Fisher pruning. Through a combination of knowledge distillation and Fisher pruning, we obtain much more runtime-efficient architectures for saliency prediction, achieving a 10x speedup for the same AUC performance as a state of the art network on the CAT2000 dataset. Speeding up single-image gaze prediction is important for many real-world applications, but it is also a crucial step in the development of video saliency models, where the amount of data to be processed is substantially larger.