Purifying Real Images with an Attention-guided Style Transfer Network for Gaze Estimation
arXiv:2002.06145
Abstract
Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images compared to real images, the desired performance cannot be achieved. Real images consist of multiple forms of light orientation, while synthetic images consist of a uniform light orientation. These features are considered to be characteristic of outdoor and indoor scenes, respectively. To solve this problem, the previous method learned a model to improve the realism of the synthetic image. Different from the previous methods, this paper try to purify real image by extracting discriminative and robust features to convert outdoor real images to indoor synthetic images. In this paper, we first introduce the segmentation masks to construct RGB-mask pairs as inputs, then we design a attention-guided style transfer network to learn style features separately from the attention and bkgd(background) region , learn content features from full and attention region. Moreover, we propose a novel region-level task-guided loss to restrain the features learnt from style and content. Experiments were performed using mixed studies (qualitative and quantitative) methods to demonstrate the possibility of purifying real images in complex directions. We evaluate the proposed method on three public datasets, including LPW, COCO and MPIIGaze. Extensive experimental results show that the proposed method is effective and achieves the state-of-the-art results.
arXiv commentarXiv admin note: substantial text overlap with arXiv:1903.05820, arXiv:1903.08152; and text overlap with arXiv:1603.08155 by other authors
References in corpus (7)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Multi-View Spectral Clustering via Structured Low-Rank Matrix Factorization
- Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
- Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval
- Iterative Views Agreement: An Iterative Low-Rank based Structured Optimization Method to Multi-View Spectral Clustering
- 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
- Deep Manifold Traversal: Changing Labels with Convolutional Features