Deep Learning Face Attributes in the Wild

TL;DR

This paper introduces a deep learning framework with two CNNs, LNet and ANet, for face attribute prediction in unconstrained environments, achieving superior accuracy and revealing new insights into face representation learning.

Contribution

It presents a novel cascaded CNN approach with distinct pre-training strategies, enabling effective face localization and attribute prediction without requiring bounding boxes or landmarks.

Findings

LNet can be trained for face localization using only image-level annotations.

High-level neurons in ANet automatically discover semantic concepts.

The framework outperforms previous state-of-the-art methods significantly.

Abstract

Predicting face attributes in the wild is challenging due to complex face variations. We propose a novel deep learning framework for attribute prediction in the wild. It cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently. LNet is pre-trained by massive general object categories for face localization, while ANet is pre-trained by massive face identities for attribute prediction. This framework not only outperforms the state-of-the-art with a large margin, but also reveals valuable facts on learning face representation. (1) It shows how the performances of face localization (LNet) and attribute prediction (ANet) can be improved by different pre-training strategies. (2) It reveals that although the filters of LNet are fine-tuned only with image-level attribute tags, their response maps over entire images have strong indication of face locations. This fact enables training LNet for face localization with only image-level annotations, but without face bounding boxes or landmarks, which are required by all attribute recognition works. (3) It also demonstrates that the high-level hidden neurons of ANet automatically discover semantic concepts after pre-training with massive face identities, and such concepts are significantly enriched after fine-tuning with attribute tags. Each attribute can be well explained with a sparse linear combination of these concepts.