# From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning

arXiv: https://arxiv.org/abs/2303.08414 · HTML: https://mlsanity.com/paper/2303.08414/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 57 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing](https://mlsanity.com/paper/2011.02062/) (2020)
- [Dual-Cross Central Difference Network for Face Anti-Spoofing](https://mlsanity.com/paper/2105.01290/) (2021)
- [NTIRE 2022 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2206.11695/) (2022)
- [Local Binary Convolutional Neural Networks](https://mlsanity.com/paper/1608.06049/) (2016)
- [Multi-Modal Face Anti-Spoofing Based on Central Difference Networks](https://mlsanity.com/paper/2004.08388/) (2020)
- [Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition](https://mlsanity.com/paper/2008.09412/) (2020)
- [Semantic Diffusion Network for Semantic Segmentation](https://mlsanity.com/paper/2302.02057/) (2023)
- [Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer](https://mlsanity.com/paper/2108.07520/) (2021)
- [Dynamic Binary Neural Network by learning channel-wise thresholds](https://mlsanity.com/paper/2110.05185/) (2021)
- [SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation](https://mlsanity.com/paper/2209.05924/) (2022)
- [Local Motion and Contrast Priors Driven Deep Network for Infrared Small Target Super-Resolution](https://mlsanity.com/paper/2201.01014/) (2022)
- [A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2111.06995/) (2021)
- [Median Pixel Difference Convolutional Network for Robust Face Recognition](https://mlsanity.com/paper/2205.15867/) (2022)
- [A Compact Deep Architecture for Real-time Saliency Prediction](https://mlsanity.com/paper/2008.13227/) (2020)
- [Image Quality Assessment with Gradient Siamese Network](https://mlsanity.com/paper/2208.04081/) (2022)
- [FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond](https://mlsanity.com/paper/2010.09294/) (2020)

## Built on by (most cited first, 1 of 1)

- [A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling](https://mlsanity.com/paper/2407.02283/) (2024)

## Abstract (arXiv)

LBP is a successful hand-crafted feature descriptor in computer vision. However, in the deep learning era, deep neural networks, especially convolutional neural networks (CNNs) can automatically learn powerful task-aware features that are more discriminative and of higher representational capacity. To some extent, such hand-crafted features can be safely ignored when designing deep computer vision models. Nevertheless, due to LBP's preferable properties in visual representation learning, an interesting topic has arisen to explore the value of LBP in enhancing modern deep models in terms of efficiency, memory consumption, and predictive performance. In this paper, we provide a comprehensive review on such efforts which aims to incorporate the LBP mechanism into the design of CNN modules to make deep models stronger. In retrospect of what has been achieved so far, the paper discusses open challenges and directions for future research.