Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed two shortcomings: illogical synthetic SQL queries from independent column sampling and arbitrary table joins. To address these issues, we propose a novel synthesis framework that incorporates key relationships from schema, imposes strong typing, and conducts schema-distance-weighted column sampling. We also adopt an intermediate representation (IR) for the SQL-to-text task to further improve the quality of the generated natural language questions. When existing powerful semantic parsers are pre-finetuned on our high-quality synthesized data, our experiments show that these models have significant accuracy boosts on popular benchmarks, including new state-of-the-art performance on Spider.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Talking face generation aims at generating photo-realistic video portraits of a target person driven by input audio. Due to its nature of one-to-many mapping from the input audio to the output video (e.g., one speech content may have multiple feasible visual appearances), learning a deterministic mapping like previous works brings ambiguity during training, and thus causes inferior visual results. Although this one-to-many mapping could be alleviated in part by a two-stage framework (i.e., an audio-to-expression model followed by a neural-rendering model), it is still insufficient since the prediction is produced without enough information (e.g., emotions, wrinkles, etc.). In this paper, we propose MemFace to complement the missing information with an implicit memory and an explicit memory that follow the sense of the two stages respectively. More specifically, the implicit memory is employed in the audio-to-expression model to capture high-level semantics in the audio-expression shared space, while the explicit memory is employed in the neural-rendering model to help synthesize pixel-level details. Our experimental results show that our proposed MemFace surpasses all the state-of-the-art results across multiple scenarios consistently and significantly.

Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate answers. Retrievers and readers are usually modeled separately, which necessitates a cumbersome implementation and is hard to train and adapt in an end-to-end fashion. In this paper, we revisit this design and eschew the separate architecture and training in favor of a single Transformer that performs Retrieval as Attention (ReAtt), and end-to-end training solely based on supervision from the end QA task. We demonstrate for the first time that a single model trained end-to-end can achieve both competitive retrieval and QA performance, matching or slightly outperforming state-of-the-art separately trained retrievers and readers. Moreover, end-to-end adaptation significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings, making our model a simple and adaptable solution for knowledge-intensive tasks. Code and models are available at https://github.com/jzbjyb/ReAtt.

High-definition (HD) semantic map generation of the environment is an essential component of autonomous driving. Existing methods have achieved good performance in this task by fusing different sensor modalities, such as LiDAR and camera. However, current works are based on raw data or network feature-level fusion and only consider short-range HD map generation, limiting their deployment to realistic autonomous driving applications. In this paper, we focus on the task of building the HD maps in both short ranges, i.e., within 30 m, and also predicting long-range HD maps up to 90 m, which is required by downstream path planning and control tasks to improve the smoothness and safety of autonomous driving. To this end, we propose a novel network named SuperFusion, exploiting the fusion of LiDAR and camera data at multiple levels. We benchmark our SuperFusion on the nuScenes dataset and a self-recorded dataset and show that it outperforms the state-of-the-art baseline methods with large margins. Furthermore, we propose a new metric to evaluate the long-range HD map prediction and apply the generated HD map to a downstream path planning task. The results show that by using the long-range HD maps predicted by our method, we can make better path planning for autonomous vehicles. The code will be available at https://github.com/haomo-ai/SuperFusion.

关于文本到SQL语义解析的最新研究取决于解析器本身或基于简单的启发式方法来理解自然语言查询（NLQ）。合成SQL查询时，没有可用的NLQ的明确语义信息，从而导致不良的概括性能。此外，如果没有词汇级的细粒度查询理解，查询与数据库之间的链接只能依赖模糊的字符串匹配，这会导致实际应用中的次优性能。考虑到这一点，在本文中，我们提出了一个基于令牌级的细粒度查询理解的通用，模块化的神经语义解析框架。我们的框架由三个模块组成：命名实体识别器（NER），神经实体接头（NEL）和神经语义解析器（NSP）。通过共同建模查询和数据库，NER模型可以分析用户意图并确定查询中的实体。 NEL模型将类型的实体链接到数据库中的模式和单元格值。解析器模型利用可用的语义信息并链接结果并根据动态生成的语法合成树结构的SQL查询。新发布的语义解析数据集的Squall实验表明，我们可以在WikiableQuestions（WTQ）测试集上实现56.8％的执行精度，这使最先进的模型的表现优于2.7％。

域适应是神经机器翻译的重要挑战。但是，传统的微调解决方案需要多次额外的培训，并产生高昂的成本。在本文中，我们提出了一种非调节范式，通过基于及时的方法解决域的适应性。具体来说，我们构建了双语短语级数据库，并从中检索相关对作为输入句子的提示。通过利用检索到的短语级提示（REPP），我们有效地提高了翻译质量。实验表明，我们的方法改善了域特异性的机器翻译，可用于6.2 BLEU分数，并改善了在没有额外训练的情况下，精度为11.5％的翻译约束。

随着移动平台上对计算摄影和成像的需求不断增长，在相机系统中开发和集成了高级图像传感器与新型算法的发展。但是，缺乏用于研究的高质量数据以及从行业和学术界进行深入交流的难得的机会限制了移动智能摄影和成像（MIPI）的发展。为了弥合差距，我们介绍了第一个MIPI挑战，包括五个曲目，这些曲目着重于新型图像传感器和成像算法。在本文中，引入了RGBW关节Remosaic和Denoise，这是五个曲目之一，在全面分辨率上进行了RGBW CFA插值的插值。为参与者提供了一个新的数据集，其中包括70（培训）和15个（验证）高质量RGBW和拜耳对的场景。此外，对于每个场景，在0dB，24dB和42dB上提供了不同噪声水平的RGBW。所有数据均在室外和室内条件下使用RGBW传感器捕获。最终结果是使用PSNR，SSIM，LPIPS和KLD在内的客观指标评估的。本文提供了此挑战中所有模型的详细描述。有关此挑战的更多详细信息以及数据集的链接，请访问https://github.com/mipi-challenge/mipi2022。

随着移动平台上对计算摄影和成像的需求不断增长，在相机系统中开发和集成了高级图像传感器与新型算法的发展。但是，缺乏用于研究的高质量数据以及从行业和学术界进行深入交流的难得的机会限制了移动智能摄影和成像（MIPI）的发展。为了弥合差距，我们引入了第一个MIPI挑战，其中包括五个专注于新型图像传感器和成像算法的曲目。在本文中，引入了RGBW关节融合和Denoise，这是五个曲目之一，其中一条致力于将Binning模式RGBW融合到拜耳。为参与者提供了一个新的数据集，其中包括70（培训）和15个（验证）高质量RGBW和拜耳对的场景。此外，对于每个场景，在24dB和42dB处提供不同噪声水平的RGBW。所有数据均在室外和室内条件下使用RGBW传感器捕获。最终结果使用客观指标，包括PSNR，SSIM}，LPIPS和KLD评估。本文提供了此挑战中所有模型的详细描述。有关此挑战的更多详细信息以及数据集的链接，请访问https://github.com/mipi-challenge/mipi2022。

随着移动平台上对计算摄影和成像的需求不断增长，在相机系统中开发和集成了高级图像传感器与新型算法的发展。但是，缺乏用于研究的高质量数据以及从行业和学术界进行深入交流的难得的机会限制了移动智能摄影和成像（MIPI）的发展。为了弥合差距，我们引入了第一个MIPI挑战，其中包括五个专注于新型图像传感器和成像算法的曲目。在本文中，引入了QUAD Remosaic和Denoise，这是五个曲目之一，在完全分辨率上进行了四QFA插值向拜耳进行插值。为参与者提供了一个新的数据集，包括70（培训）和15个（验证）高品质四边形和拜耳对的场景。此外，对于每个场景，在0dB，24dB和42dB上提供了不同噪声水平的四边形。所有数据均在室外和室内条件下使用四边形传感器捕获。最终结果使用客观指标，包括PSNR，SSIM，LPIPS和KLD。本文提供了此挑战中所有模型的详细描述。有关此挑战的更多详细信息以及数据集的链接，请访问https://github.com/mipi-challenge/mipi2022。