Deep model compression has been extensively studied, and state-of-the-art methods can now achieve high compression ratios with minimal accuracy loss.

Neural Information Processing Systems http://nips.cc/

Real-world learning systems have practical limitations on the quality and quantity of the training datasets that they can collect and consider. How should a system go about choosing a subset of the possible training examples that still allows for learning accurate, generalizable models? To help address this question, we draw inspiration from a highly efficient practical learning system: the human child. Using head-mounted cameras, eye gaze trackers, and a model of foveated vision, we collected first-person (egocentric) images that represent a highly accurate approximation of the "training data" that toddlers' visual systems collect in everyday, naturalistic learning contexts. We used state-of-the-art computer vision learning models (convolutional neural networks) to help characterize the structure of these data, and found that child data produce significantly better object models than egocentric data experienced by adults in exactly the same environment. By using the CNNs as a modeling tool to investigate the properties of the child data that may enable this rapid learning, we found that child data exhibit a unique combination of quality and diversity, with not only many similar large, high-quality object views but also a greater number and diversity of rare views. This novel methodology of analyzing the visual "training data" used by children may not only reveal insights to improve machine learning, but also may suggest new experimental tools to better understand infant learning in developmental psychology.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Due to the foveated nature of the human vision system, people can focus their visual attention on only a small region of their visual field at a time, which usually contains a single object. Estimating this object of attention in first-person (egocentric) videos is useful for many human-centered real-world applications such as augmented reality and driver assistance systems. A straightforward solution for this problem is to first estimate the gaze with a traditional gaze estimator and generate object candidates from an off-the-shelf object detector, and then pick the object that the estimated gaze falls in. However, such an approach can fail because it addresses the where and the what problems separately, despite that they are highly related, chicken-and-egg problems. In this paper, we propose a novel unified model that incorporates both spatial and temporal evidence in identifying as well as locating the attended object in first-person videos. It introduces a novel Self Validation Module that enforces and leverages consistency of the where and the what concepts. We evaluate on two public datasets, demonstrating that the Self Validation Module significantly benefits both training and testing and that our model outperforms the state-of-the-art.