Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity. In contrast, the latter class enables fast and reliable convergence, but cannot consider the rich datato-data relations. This paper presents a new proxy-based loss that takes advantages of both pair-and proxy-based methods and overcomes their limitations. Thanks to the use of proxies, our loss boosts the speed of convergence and is robust against noisy labels and outliers. At the same time, it allows embedding vectors of data to interact with each other through its gradients to exploit data-to-data relations. Our method is evaluated on four public benchmarks, where a standard network trained with our loss achieves state-ofthe-art performance and most quickly converges.

No abstract

Metric Learning for visual similarity has mostly adopted binary supervision indicating whether a pair of images are of the same class or not. Such a binary indicator covers only a limited subset of image relations, and is not sufficient to represent semantic similarity between images described by continuous and/or structured labels such as object poses, image captions, and scene graphs. Motivated by this, we present a novel method for deep metric learning using continuous labels. First, we propose a new triplet loss that allows distance ratios in the label space to be preserved in the learned metric space. The proposed loss thus enables our model to learn the degree of similarity rather than just the order. Furthermore, we design a triplet mining strategy adapted to metric learning with continuous labels. We address three different image retrieval tasks with continuous labels in terms of human poses, room layouts and image captions, and demonstrate the superior performance of our approach compared to previous methods.

This study examined whether foreign language learner anxiety and motivational goal orientations remained stable across two different classroom contexts: a reading course and a conversation course. The researcher measured anxiety and four types of motivational goal orientations by surveying 59 Korean college students learning English in both courses. A repeated‐measures MANCOVA was used to analyze the responses. The findings indicated that levels of anxiety can vary according to instructional contexts. The study found a significant difference for anxiety, with the students reporting higher levels of anxiety in the conversation course than in the reading course. By contrast, for goal orientation, students exhibited similar patterns across contexts. These Korean students displayed a high tendency toward a utilitarian goal regardless of context. The article also suggests teaching implications for reducing anxiety and enhancing motivation.

No abstract