# Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation

arXiv: https://arxiv.org/abs/2209.08788 · HTML: https://mlsanity.com/paper/2209.08788/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 19 Sep 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [Attention to Scale: Scale-aware Semantic Image Segmentation](https://mlsanity.com/paper/1511.03339/) (2015)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Learning a Discriminative Feature Network for Semantic Segmentation](https://mlsanity.com/paper/1804.09337/) (2018)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [Multi-Context Attention for Human Pose Estimation](https://mlsanity.com/paper/1702.07432/) (2017)
- [Mis-classified Vector Guided Softmax Loss for Face Recognition](https://mlsanity.com/paper/1912.00833/) (2019)
- [FaceBoxes: A CPU Real-time Face Detector with High Accuracy](https://mlsanity.com/paper/1708.05234/) (2017)
- [Surveillance Face Recognition Challenge](https://mlsanity.com/paper/1804.09691/) (2018)

## Abstract (arXiv)

Human face images usually appear with wide range of visual scales. The existing face representations pursue the bandwidth of handling scale variation via multi-scale scheme that assembles a finite series of predefined scales. Such multi-shot scheme brings inference burden, and the predefined scales inevitably have gap from real data. Instead, learning scale parameters from data, and using them for one-shot feature inference, is a decent solution. To this end, we reform the conv layer by resorting to the scale-space theory, and achieve two-fold facilities: 1) the conv layer learns a set of scales from real data distribution, each of which is fulfilled by a conv kernel; 2) the layer automatically highlights the feature at the proper channel and location corresponding to the input pattern scale and its presence. Then, we accomplish the hierarchical scale attention by stacking the reformed layers, building a novel style named SCale AttentioN Conv Neural Network (SCAN-CNN). We apply SCAN-CNN to the face recognition task and push the frontier of SOTA performance. The accuracy gain is more evident when the face images are blurry. Meanwhile, as a single-shot scheme, the inference is more efficient than multi-shot fusion. A set of tools are made to ensure the fast training of SCAN-CNN and zero increase of inference cost compared with the plain CNN.