Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
arXiv:1907.03030
Abstract
This paper targets the problem of image set-based face verification and identification. Unlike traditional single media (an image or video) setting, we encounter a set of heterogeneous contents containing orderless images and videos. The importance of each image is usually considered either equal or based on their independent quality assessment. How to model the relationship of orderless images within a set remains a challenge. We address this problem by formulating it as a Markov Decision Process (MDP) in the latent space. Specifically, we first present a dependency-aware attention control (DAC) network, which resorts to actor-critic reinforcement learning for sequential attention decision of each image embedding to fully exploit the rich correlation cues among the unordered images. Moreover, we introduce its sample-efficient variant with off-policy experience replay to speed up the learning process. The pose-guided representation scheme can further boost the performance at the extremes of the pose variation.
Fixed the unreadable code in CVF version. arXiv admin note: text overlap with arXiv:1707.00130 by other authors
References in corpus (15)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Continuous control with deep reinforcement learning
- A Brief Survey of Deep Reinforcement Learning
- Trust Region Policy Optimization
- Recurrent Models of Visual Attention
- Deep Reinforcement Learning: An Overview
- Sample Efficient Actor-Critic with Experience Replay
- Order Matters: Sequence to sequence for sets
- A Riemannian Network for SPD Matrix Learning
- Face Search at Scale: 80 Million Gallery
- Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
- Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
- Learning Policies for Adaptive Tracking with Deep Feature Cascades
- Deep Reinforcement Learning Attention Selection for Person Re-Identification
- Multi-shot Pedestrian Re-identification via Sequential Decision Making