# Irrelevant Pixels are Everywhere: Find and Exclude Them for More Efficient Computer Vision

arXiv: https://arxiv.org/abs/2207.10741 · HTML: https://mlsanity.com/paper/2207.10741/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 21 Jul 2022.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference](https://mlsanity.com/paper/1912.03203/) (2019)
- [SBNet: Sparse Blocks Network for Fast Inference](https://mlsanity.com/paper/1801.02108/) (2018)

## Built on by (most cited first, 3 of 3)

- [Survey on Computer Vision Techniques for Internet-of-Things Devices](https://mlsanity.com/paper/2308.02553/) (2023)
- [An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions](https://mlsanity.com/paper/2310.07782/) (2023)
- [Synergistic Simplex: Cooperative Runtime Assurance for Safety-Critical Autonomous Systems](https://mlsanity.com/paper/2605.08190/) (2026)

## Abstract (arXiv)

Computer vision is often performed using Convolutional Neural Networks (CNNs). CNNs are compute-intensive and challenging to deploy on power-contrained systems such as mobile and Internet-of-Things (IoT) devices. CNNs are compute-intensive because they indiscriminately compute many features on all pixels of the input image. We observe that, given a computer vision task, images often contain pixels that are irrelevant to the task. For example, if the task is looking for cars, pixels in the sky are not very useful. Therefore, we propose that a CNN be modified to only operate on relevant pixels to save computation and energy. We propose a method to study three popular computer vision datasets, finding that 48% of pixels are irrelevant. We also propose the focused convolution to modify a CNN's convolutional layers to reject the pixels that are marked irrelevant. On an embedded device, we observe no loss in accuracy, while inference latency, energy consumption, and multiply-add count are all reduced by about 45%.