Deep metric learning aims to learn an embedding space, where semantically similar samples are close together and dissimilar ones are repelled against. To explore more hard and informative training signals for augmentation and generalization, recent methods focus on generating synthetic samples to boost metric learning losses. However, these methods just use the deterministic and class-independent generations (e.g., simple linear interpolation), which only can cover the limited part of distribution spaces around original samples. They have overlooked the wide characteristic changes of different classes and can not model abundant intra-class variations for generations. Therefore, generated samples not only lack rich semantics within the certain class, but also might be noisy signals to disturb training. In this paper, we propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining and boost metric learning losses. Further, for most datasets that have a few samples within the class, we propose the neighbor correction to revise the inaccurate estimations, according to our correlation discovery where similar classes generally have similar variation distributions. Extensive experiments on five benchmarks show our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%. Our code is available at https://github.com/darkpromise98/IAA

To handle this information overload and to help users in efficient decision making, recommender systems (RS) have been designed. The goal of RSs is to recommend personalized items for online users when they need to choose among several items. Typical problems include recommendations for which movie to watch, which jokes/books/news to read, which hotel to stay at, or which songs to listen to. One of the most popular approaches in the field of recommender systems is collaborative filtering (CF). The underlying idea of CF is very simple: Users generally express their tastes in an explicit way by rating the items. CF tries to estimate the users' preferences based on the ratings they have already made on items and based on the ratings of other, similar users. For a recent review on recommender systems and collaborative filtering, see e.g., [1]. Novel advances on CF show that dictionary learning based approaches can be efficient for making predictions about users' preferences [2]. The dictionary learning based approach assumes that (i) there is a latent, unstructured feature space (hidden representation) behind the users' ratings, and (ii) a rating of an item is equal to the product of the item and the user's feature.