Improving Generalization via Scalable Neighborhood Component Analysis

COMPUTER VISION - ECCV 2018, PT VII(2018)

引用 145|浏览79
暂无评分
摘要
Current major approaches to visual recognition follow an end-to-end formulation that classifies an input image into one of the pre-determined set of semantic categories. Parametric softmax classifiers are a common choice for such a closed world with fixed categories, especially when big labeled data is available during training. However, this becomes problematic for open-set scenarios where new categories are encountered with very few examples for learning a generalizable parametric classifier. We adopt a non-parametric approach for visual recognition by optimizing feature embeddings instead of parametric classifiers. We use a deep neural network to learn the visual feature that preserves the neighborhood structure in the semantic space, based on the Neighborhood Component Analysis (NCA) criterion. Limited by its computational bottlenecks, we devise a mechanism to use augmented memory to scale NCA for large datasets and very deep networks. Our experiments deliver not only remarkable performance on ImageNet classification for such a simple non-parametric method, but most importantly a more generalizable feature representation for sub-category discovery and few-shot recognition.
更多
查看译文
关键词
k-nearest neighbors, Large-scale object recognition, Neighborhood component analysis, Transfer learning, Few-shot learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要