# DIME: Scaling Facial Representation Learning via Differential Masked Autoencoding

arXiv: https://arxiv.org/abs/2610.17015 · HTML: https://mlsanity.com/paper/2610.17015/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 73 of its 103 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 30 of 73)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Beyond neural scaling laws: beating power law scaling via data pruning](https://mlsanity.com/paper/2206.14486/) (2022)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Rotary Position Embedding for Vision Transformer](https://mlsanity.com/paper/2403.13298/) (2024)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [What Should Not Be Contrastive in Contrastive Learning](https://mlsanity.com/paper/2008.05659/) (2020)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [Face Alignment in Full Pose Range: A 3D Total Solution](https://mlsanity.com/paper/1804.01005/) (2018)
- [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](https://mlsanity.com/paper/1805.10483/) (2018)
- [Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition](https://mlsanity.com/paper/2205.01782/) (2022)
- [Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification](https://mlsanity.com/paper/1912.07872/) (2019)

## Abstract (arXiv)

Scaling up data and model capacity has driven substantial progress in visual representation learning. However, conventional pretext tasks exhibit diminishing returns on fine-grained facial analysis. We attribute this to a scaling bottleneck: these tasks model each image's appearance and are dominated by identity, pose, and illumination, so subtle within-identity facial differences contribute little to the training signal. We introduce DIME, a differential masked autoencoder for large-scale facial representation learning. DIME builds on a simple observation: two images of the same person share identity-specific appearance, so their difference exposes facial changes. DIME reconstructs both masked images in an identity-matched pair and, through an Explicit Differential Direction Supervision (EDDS) objective, aligns the direction of their reconstructed difference with the true difference, while source isolation makes each reconstruction depend only on its own image. Shared appearance cancels in this difference, and because EDDS ignores magnitude, subtle facial changes count as much as large pose or illumination changes. DIME uses identity labels only to form pretraining pairs, requires no dense annotations, and learns dense facial representations with emergent part-level semantics. We pretrain DIME on 20 million high-resolution facial images consolidated from existing face datasets. DIME's AU detection performance continues to improve as pretraining data scales from 6M to 20M images, with its BP4D F1 increasing by 5.9 points, while MAE gains only 0.5 points on the same subsets. DIME also outperforms specialized facial methods on AU detection, AU intensity estimation, cross-domain anti-spoofing, landmark localization, head pose estimation, face parsing, and face generation.