A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this paper, we provide a general weighting framework for understanding recent pair-based loss functions. Our contributions are three-fold: (1) we establish a General Pair Weighting (GPW) framework, which casts the sampling problem of deep metric learning into a unified view of pair weighting through gradient analysis, providing a powerful tool for understanding recent pair-based loss functions; (2) we show that with GPW, various existing pair-based methods can be compared and discussed comprehensively, with clear differences and key limitations identified; (3) we propose a new loss called multi-similarity loss (MS loss) under the GPW, which is implemented in two iterative steps (i.e., mining and weighting). This allows it to fully consider three similarities for pair weighting, providing a more principled approach for collecting and weighting informative pairs. Finally, the proposed MS loss obtains new state-of-the-art performance on four image retrieval benchmarks, where it outperforms the most recent approaches, such as ABE [14] and HTL [4], by a large margin, e.g., , and 80.9% → 88.0% on In-Shop Clothes Retrieval dataset at Recall@1. Code is available at https://github. com/MalongTech/research-ms-loss arXiv:1904.06627v3 [cs.CV]

Abstract. We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image. The CTPN detects a text line in a sequence of fine-scale text proposals directly in convolutional feature maps. We develop a vertical anchor mechanism that jointly predicts location and text/non-text score of each fixed-width proposal, considerably improving localization accuracy. The sequential proposals are naturally connected by a recurrent neural network, which is seamlessly incorporated into the convolutional network, resulting in an end-to-end trainable model. This allows the CTPN to explore rich context information of image, making it powerful to detect extremely ambiguous text. The CTPN works reliably on multi-scale and multilanguage text without further post-processing, departing from previous bottom-up methods requiring multi-step post filtering. It achieves 0.88 and 0.61 F-measure on the ICDAR 2013 and 2015 benchmarks, surpassing recent results [8,35] by a large margin. The CTPN is computationally efficient with 0.14s/image, by using the very deep VGG16 model [27]. Online demo is available at: http://textdet.com/.

We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global context information. This allows us to cope with the main limitation of random sampling in training a conventional triplet loss, which is a central issue for deep metric learning. Our main contributions are two-fold. (i) we construct a hierarchical class-level tree where neighboring classes are merged recursively. The hierarchical structure naturally captures the intrinsic data distribution over the whole dataset. (ii) we formulate the problem of triplet collection by introducing a new violate margin, which is computed dynamically based on the designed hierarchical tree. This allows it to automatically select meaningful hard samples with the guide of global context. It encourages the model to learn more discriminative features from visual similar classes, leading to faster convergence and better performance. Our method is evaluated on the tasks of image retrieval and face recognition, where it outperforms the standard triplet loss substantially by 1%18%. It achieves new state-of-the-art performance on a number of benchmarks, with much fewer learning iterations.

Abstract. Maximally Stable Extremal Regions (MSERs) have achieved great success in scene text detection. However, this low-level pixel operation inherently limits its capability for handling complex text information efficiently (e. g. connections between text or background components), leading to the difficulty in distinguishing texts from background components. In this paper, we propose a novel framework to tackle this problem by leveraging the high capability of convolutional neural network (CNN). In contrast to recent methods using a set of low-level heuristic features, the CNN network is capable of learning high-level features to robustly identify text components from text-like outliers (e.g. bikes, windows, or leaves). Our approach takes advantages of both MSERs and slidingwindow based methods. The MSERs operator dramatically reduces the number of windows scanned and enhances detection of the low-quality texts. While the sliding-window with CNN is applied to correctly separate the connections of multiple characters in components. The proposed system achieved strong robustness against a number of extreme text variations and serious real-world problems. It was evaluated on the ICDAR 2011 benchmark dataset, and achieved over 78% in F-measure, which is significantly higher than previous methods.