# LogicNet: A Logical Consistency Embedded Face Attribute Learning Network

arXiv: https://arxiv.org/abs/2311.11208 · HTML: https://mlsanity.com/paper/2311.11208/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 60 references that are in the map.
- First posted on arXiv 19 Nov 2023.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [A Semantic Loss Function for Deep Learning with Symbolic Knowledge](https://mlsanity.com/paper/1711.11157/) (2017)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization](https://mlsanity.com/paper/2104.05833/) (2021)
- [STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing](https://mlsanity.com/paper/1904.09709/) (2019)
- [Deep Imbalanced Learning for Face Recognition and Attribute Prediction](https://mlsanity.com/paper/1806.00194/) (2018)
- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach](https://mlsanity.com/paper/1706.00906/) (2017)
- [Unsupervised Multi-hop Question Answering by Question Generation](https://mlsanity.com/paper/2010.12623/) (2020)
- [MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes](https://mlsanity.com/paper/1603.07027/) (2016)
- [ROAD-R: The Autonomous Driving Dataset with Logical Requirements](https://mlsanity.com/paper/2210.01597/) (2022)
- [MAAD-Face: A Massively Annotated Attribute Dataset for Face Images](https://mlsanity.com/paper/2012.01030/) (2020)
- [Critical Thinking for Language Models](https://mlsanity.com/paper/2009.07185/) (2020)
- [Controllable Inversion of Black-Box Face Recognition Models via Diffusion](https://mlsanity.com/paper/2303.13006/) (2023)
- [Deep Attributes Driven Multi-Camera Person Re-identification](https://mlsanity.com/paper/1605.03259/) (2016)
- [The Gender Gap in Face Recognition Accuracy Is a Hairy Problem](https://mlsanity.com/paper/2206.04867/) (2022)
- [Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation](https://mlsanity.com/paper/2207.14000/) (2022)
- [Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning](https://mlsanity.com/paper/2302.11102/) (2023)
- [What Should Be Balanced in a "Balanced" Face Recognition Dataset?](https://mlsanity.com/paper/2304.09818/) (2023)
- [A Deep Cascade Network for Unaligned Face Attribute Classification](https://mlsanity.com/paper/1709.03851/) (2017)

## Built on by (most cited first, 4 of 4)

- [Goldilocks Test Sets for Face Verification](https://mlsanity.com/paper/2405.15965/) (2024)
- [Impact of Sunglasses on One-to-Many Facial Identification Accuracy](https://mlsanity.com/paper/2412.05721/) (2024)
- [FaceInsight: A Multimodal Large Language Model for Face Perception](https://mlsanity.com/paper/2504.15624/) (2025)
- [Vec2Face+ for Face Dataset Generation](https://mlsanity.com/paper/2507.17192/) (2025)

## Abstract (arXiv)

Ensuring logical consistency in predictions is a crucial yet overlooked aspect in multi-attribute classification. We explore the potential reasons for this oversight and introduce two pressing challenges to the field: 1) How can we ensure that a model, when trained with data checked for logical consistency, yields predictions that are logically consistent? 2) How can we achieve the same with data that hasn't undergone logical consistency checks? Minimizing manual effort is also essential for enhancing automation. To address these challenges, we introduce two datasets, FH41K and CelebA-logic, and propose LogicNet, an adversarial training framework that learns the logical relationships between attributes. Accuracy of LogicNet surpasses that of the next-best approach by 23.05%, 9.96%, and 1.71% on FH37K, FH41K, and CelebA-logic, respectively. In real-world case analysis, our approach can achieve a reduction of more than 50% in the average number of failed cases compared to other methods.