本次学术沙龙教师发展中心邀请到澳大利亚阿德莱德大学博士后王鹏，与我校师生分享Deep Neural Network for Few-shot Learning的研究及进展。具体安排如下，欢迎感兴趣的师生参加。
一、主 题：Deep Neural Network for Few-shot Learning
五、主持人：未来媒体研究中心 姬艳丽 副教授
Few-shot learning is a challenging problem where the aim is to recognize a class identified by a single or few training images. Given the practical importance of few-shot learning, it seems surprising that the rich information present in the class tag itself has largely been ignored. Most existing approaches restrict the use of the class tag to finding similar classes and transferring classifiers or metrics learned thereon. We demonstrate in the first work, in contrast, that the class tag can inform few-shot learning as a guide to visual attention on the training image for creating the image representation. This is motivated by the fact that human beings can better interpret a training image if the class tag of the image is understood.
Humans are capable of learning a new fine-grained concept with very little supervision, e.g., few exemplary images for a species of bird, yet our best deep learning systems need hundreds or thousands of labeled examples. In the second work, we try to reduce this gap by studying the fine-grained image recognition problem in a challenging few-shot learning setting, termed few-shot fine-grained recognition (FSFG). The task of FSFG requires the learning systems to build classifiers for novel fine-grained categories from few examples. To solve this problem, we propose an end-to-end trainable deep network which is inspired by the state-of-the-art fine-grained recognition model and is tailored for the FSFG task.
王鹏，现于澳大利亚阿德莱德大学开展博士后研究，于2017年获得澳大利亚昆士兰大学计算机科学博士学位。目前主要从事计算机视觉和机器学习的研究，在TPAMI/TMM/ TIP/TCSVT/CVPR/AAAI/ACM MM等顶级期刊和会议发表多篇论文，曾担任TKDE/TCSVT/ACM MM等多个国际顶级期刊或会议论文审稿人。
编辑：林坤 / 审核：罗莎 / 发布者：一戈