# Slim-CNN: A Light-Weight CNN for Face Attribute Prediction

arXiv: https://arxiv.org/abs/1907.02157 · HTML: https://mlsanity.com/paper/1907.02157/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis](https://mlsanity.com/paper/2103.05630/) (2021)
- [Self-Supervised Facial Representation Learning with Facial Region Awareness](https://mlsanity.com/paper/2403.02138/) (2024)
- [15M Multimodal Facial Image-Text Dataset](https://mlsanity.com/paper/2407.08515/) (2024)
- [Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction](https://mlsanity.com/paper/2108.04353/) (2021)
- [Privacy-preserving Generative Framework Against Membership Inference Attacks](https://mlsanity.com/paper/2202.05469/) (2022)
- [Enhancing Fairness of Visual Attribute Predictors](https://mlsanity.com/paper/2207.05727/) (2022)
- [ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation](https://mlsanity.com/paper/2311.01929/) (2023)
- [Signal Quality Assessment of Photoplethysmogram Signals using Quantum Pattern Recognition and lightweight CNN Architecture](https://mlsanity.com/paper/2202.00606/) (2022)
- [ASD: Towards Attribute Spatial Decomposition for Prior-Free Facial Attribute Recognition](https://mlsanity.com/paper/2210.13716/) (2022)
- [FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition](https://mlsanity.com/paper/2601.01537/) (2026)

## Abstract (arXiv)

We introduce a computationally-efficient CNN micro-architecture Slim Module to design a lightweight deep neural network Slim-Net for face attribute prediction. Slim Modules are constructed by assembling depthwise separable convolutions with pointwise convolution to produce a computationally efficient module. The problem of facial attribute prediction is challenging because of the large variations in pose, background, illumination, and dataset imbalance. We stack these Slim Modules to devise a compact CNN which still maintains very high accuracy. Additionally, the neural network has a very low memory footprint which makes it suitable for mobile and embedded applications. Experiments on the CelebA dataset show that Slim-Net achieves an accuracy of 91.24% with at least 25 times fewer parameters than comparably performing methods, which reduces the memory storage requirement of Slim-net by at least 87%.