Jiacheng Xu, Caiming Xiong, Silvio Savarese, Yingbo Zhou. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
Query autocompletion is an essential feature in search engines that predicts and suggests query completions to a user's incomplete prefix input, a critical feature to enhance the user experience. While a generic lookup-based system can provide completions with great efficiency, it is unable to address prefixes not seen in the past. On the other hand, a generative system can complete unseen queries with superior accuracy but requires substantial computational overhead at runtime, making it costly for a large-scale system. Here, we present an efficient, fully-generative query autocompletion framework. Our framework employs an n-gram language model at a subword-level and exploits the n-gram model's inherent data structure to precompute completions prior to runtime. Evaluation results on public dataset show that our framework is not only as effective as previous systems with neural language models, but also reduces computational overhead at runtime, expediting the speed by more than two orders of magnitude. The goal of this work is to showcase a generative query completion system that is an attractive choice for large-scale deployments.
While Generative Adversarial Networks (GANs) have shown promising performance in image generation, they suffer from numerous issues such as mode collapse and training instability. To stabilize GAN training and improve image synthesis quality with diversity, we propose a simple yet effective approach as Contrastive Distance Learning GAN (CDL-GAN) in this paper. Specifically, we add Consistent Contrastive Distance (CoCD) and Characteristic Contrastive Distance (ChCD) into a principled framework to improve GAN performance. The CoCD explicitly maximizes the ratio of the distance between generated images and the increment between noise vectors to strengthen image feature learning for the generator. The ChCD measures the sampling distance of the encoded images in Euler space to boost feature representations for the discriminator. We model the framework by employing Siamese Network as a module into GANs without any modification on the backbone. Both qualitative and quantitative experiments conducted on three public datasets demonstrate the effectiveness of our method.
Heterogeneous face recognition (HFR) has aroused significant interest in recent years, with some challenging tasks such as misalignment problems and limited HFR data. Misalignment occurs among different modalities’ images mainly because of misaligned semantics. Although recent methods have attempted to settle the low-shot problem, they suffer from the misalignment problem between paired near infrared (NIR) and visible (VIS) images. Misalignment can bring performance degradation to most image-to-image translation networks. In this work, we propose a self-aligned dual generation (SADG) architecture for generating semantics-aligned pairwise NIR-VIS images with the same identity, but without the additional guidance of external information learning. Specifically, we propose a self-aligned generator to align the data distributions between two modalities. Then, we present a multiscale patch discriminator to get high quality images. Furthermore, we raise the mean landmark distance (MLD) to test the alignment performance between NIR and VIS images with the same identity. Extensive experiments and an ablation study of SADG on three public datasets show significant alignment performance and recognition results. Specifically, the Rank1 accuracy achieved was close to 99.9% for the CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS and BUAA VIS-NIR datasets, respectively.