Deep Learning Face Attributes in the Wild
Top Cited Papers
- 1 December 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3730-3738
- https://doi.org/10.1109/iccv.2015.425
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.Keywords
Other Versions
This publication has 20 references indexed in Scilit:
- Pedestrian detection aided by deep learning semantic tasksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- PANDA: Pose Aligned Networks for Deep Attribute ModelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Edge Boxes: Locating Object Proposals from EdgesLecture Notes in Computer Science, 2014
- Part-Based R-CNNs for Fine-Grained Category DetectionLecture Notes in Computer Science, 2014
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionLecture Notes in Computer Science, 2014
- A Deep Sum-Product Architecture for Robust Facial Attributes AnalysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Learning SURF Cascade for Fast and Accurate Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Attribute and simile classifiers for face verificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- FaceTracer: A Search Engine for Large Collections of Images with FacesLecture Notes in Computer Science, 2008
- Dimensionality Reduction by Learning an Invariant MappingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006