SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data

Abstract

State-of-the-art techniques of artificial intelligence, in particular deep learning, are mostly data-driven. However, collecting and manually labeling a large scale dataset is both difficult and expensive. A promising alternative is to introduce synthesized training data, so that the dataset size can be significantly enlarged with little human labor. But, this raises an important problem in active vision: given an {\bf infinite} data space, how to effectively sample a {\bf finite} subset to train a visual classifier? This paper presents an approach for learning from synthesized data effectively. The motivation is straightforward -- increasing the probability of seeing difficult training data. We introduce a module named {\bf SampleAhead} to formulate the learning process into an online communication between a {\em classifier} and a {\em sampler}, and update them iteratively. In each round, we adjust the sampling distribution according to the classification results, and train the classifier using the data sampled from the updated distribution. Experiments are performed by introducing synthesized images rendered from ShapeNet models to assist PASCAL3D+ classification. Our approach enjoys higher classification accuracy, especially in the scenario of a limited number of training samples. This demonstrates its efficiency in exploring the infinite data space.

arXiv commentBMVC 2018 Oral

References in corpus (11)

• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition
• Learning from Synthetic Humans
• Unsupervised Learning of Visual Representations using Videos
• Online Batch Selection for Faster Training of Neural Networks
• Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
• 3D ShapeNets: A Deep Representation for Volumetric Shapes
• Synthesizing Training Images for Boosting Human 3D Pose Estimation
• Fracking Deep Convolutional Image Descriptors
• Crafting a multi-task CNN for viewpoint estimation
• UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision

Cited by in corpus (4)

• UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
• Identifying Model Weakness with Adversarial Examiner
• Generalized Coarse-to-Fine Visual Recognition with Progressive Training
• A stepped sampling method for video detection using LSTM