Deep Learning F… (2014-11-27T00:00:00.000000Z)

TL;DR

A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently.

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.

Authors

Ziwei Liu

27 papers

Ping Luo

22 papers

Xiaogang Wang

21 papers

References44 items

Clustering by Fast Search and Find of Density Peaks

Is object localization for free? - Weakly-supervised learning with convolutional neural networks

Object Detectors Emerge in Deep Scene CNNs

Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations

Pedestrian detection aided by deep learning semantic tasks

Abstract

References44 items

TL;DR

Abstract

Authors

References44 items

Clustering by Fast Search and Find of Density Peaks

Is object localization for free? - Weakly-supervised learning with convolutional neural networks

Object Detectors Emerge in Deep Scene CNNs

Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations

Pedestrian detection aided by deep learning semantic tasks

TL;DR

Abstract

Authors

References44 items

Clustering by Fast Search and Find of Density Peaks

Is object localization for free? - Weakly-supervised learning with convolutional neural networks

Object Detectors Emerge in Deep Scene CNNs

Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations

Pedestrian detection aided by deep learning semantic tasks

Fully convolutional networks for semantic segmentation

Self-taught object localization with deep networks

Face Detection without Bells and Whistles

Edge Boxes: Locating Object Proposals from Edges

Aggregate channel features for multi-view face detection

Part-Based R-CNNs for Fine-Grained Category Detection

Clustering by fast search and find of density peaks

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Deep Learning Face Representation by Joint Identification-Verification

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

Exploiting relationship between attributes for improved face verification

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

A Deep Sum-Product Architecture for Robust Facial Attributes Analysis

PANDA: Pose Aligned Networks for Deep Attribute Modeling

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation

Learning SURF Cascade for Fast and Accurate Object Detection

Deep Convolutional Network Cascade for Facial Point Detection

ImageNet classification with deep convolutional neural networks

Deep Attribute Networks

Hierarchical face parsing via deep learning

Describing people: A poselet-based approach to attribute classification

Relative attributes

Two faces are better than one: Face recognition in group photographs

SUN database: Large-scale scene recognition from abbey to zoo

Attribute and simile classifiers for face verification

ImageNet: A large-scale hierarchical image database

Describing objects by their attributes

FaceTracer: A Search Engine for Large Collections of Images with Faces

Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments

LIBLINEAR: A Library for Large Linear Classification

Dimensionality Reduction by Learning an Invariant Mapping

Vector boosting for rotation invariant multi-view face detection

Histograms of oriented gradients for human detection

Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

Handwritten Digit Recognition with a Back-Propagation Network

Figure 14. More examples of face localization by LNet

Figure 14 More results of LNet averaged response maps. (Best viewed in color)

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names