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

TL;DR

This paper introduces SCAN-CNN, a novel neural network that learns scale parameters from data for face recognition, improving accuracy especially on blurry images while maintaining efficient one-shot inference.

Contribution

The paper proposes a new scale attention mechanism integrated into CNNs, enabling data-driven scale learning and automatic feature highlighting for face recognition.

Findings

Improved face recognition accuracy, especially on blurry images.

Efficient one-shot inference with no additional cost.

Effective training tools for SCAN-CNN implementation.

Abstract

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 (\textbf{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.