Current audio-visual separation methods share a standard architecture design where an audio encoder-decoder network is fused with visual encoding features at the encoder bottleneck. This design confounds the learning of multi-modal feature encoding with robust sound decoding for audio separation. To generalize to a new instrument: one must finetune the entire visual and audio network for all musical instruments. We re-formulate visual-sound separation task and propose Instrument as Query (iQuery) with a flexible query expansion mechanism. Our approach ensures cross-modal consistency and cross-instrument disentanglement. We utilize "visually named" queries to initiate the learning of audio queries and use cross-modal attention to remove potential sound source interference at the estimated waveforms. To generalize to a new instrument or event class, drawing inspiration from the text-prompt design, we insert an additional query as an audio prompt while freezing the attention mechanism. Experimental results on three benchmarks demonstrate that our iQuery improves audio-visual sound source separation performance.

Geometry problem solving is a well-recognized testbed for evaluating the high-level multi-modal reasoning capability of deep models. In most existing works, two main geometry problems: calculation and proving, are usually treated as two specific tasks, hindering a deep model to unify its reasoning capability on multiple math tasks. However, in essence, these two tasks have similar problem representations and overlapped math knowledge which can improve the understanding and reasoning ability of a deep model on both two tasks. Therefore, we construct a large-scale Unified Geometry problem benchmark, UniGeo, which contains 4,998 calculation problems and 9,543 proving problems. Each proving problem is annotated with a multi-step proof with reasons and mathematical expressions. The proof can be easily reformulated as a proving sequence that shares the same formats with the annotated program sequence for calculation problems. Naturally, we also present a unified multi-task Geometric Transformer framework, Geoformer, to tackle calculation and proving problems simultaneously in the form of sequence generation, which finally shows the reasoning ability can be improved on both two tasks by unifying formulation. Furthermore, we propose a Mathematical Expression Pretraining (MEP) method that aims to predict the mathematical expressions in the problem solution, thus improving the Geoformer model. Experiments on the UniGeo demonstrate that our proposed Geoformer obtains state-of-the-art performance by outperforming task-specific model NGS with over 5.6% and 3.2% accuracies on calculation and proving problems, respectively.

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper.

We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenario where the data contains multiple or even many subgroups, each with limited number of samples. As a result, we present a principled method for learning a fair predictor for all subgroups via formulating it as a bilevel objective. Specifically, the subgroup specific predictors are learned in the lower-level through a small amount of data and the fair predictor. In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors. We further prove that such a bilevel objective can effectively control the group sufficiency and generalization error. We evaluate the proposed framework on real-world datasets. Empirical evidence suggests the consistently improved fair predictions, as well as the comparable accuracy to the baselines.

在没有解密的情况下对加密数据进行神经网络推断是一种流行的方法，可以使隐私神经网络（PNET）作为服务。与用于机器学习的常规神经网络相比，PNET需要额外的编码，例如量化精确数字和多项式激活。加密输入还引入了新颖的挑战，例如对抗性鲁棒性和安全性。据我们所知，我们是第一个研究问题，包括（i）PNET是否比常规神经网络对对抗性输入更强大？ （ii）如何在没有解密的情况下设计强大的PNET？我们建议使用PNET攻击来生成黑框对抗示例，这些示例可以成功攻击目标和非目标方式。攻击结果表明，需要改进针对对抗输入的PNET鲁棒性。这不是一项琐碎的任务，因为PNET模型所有者无法访问输入值的明文，这阻止了现有检测和防御方法的应用，例如输入调整，模型归一化和对抗性培训。为了应对这一挑战，我们提出了一种新的快速准确的噪声插入方法，称为RPNET，以设计强大的私人神经网络。我们的综合实验表明，PNET-ITSTACK比先前的工作减少了至少$ 2.5 \ times $的查询。我们从理论上分析了我们的RPNET方法，并证明RPNET可以降低$ \ sim 91.88 \％$ $攻击成功率。

光学计算是一种新兴技术，用于下一代高效人工智能（AI），其速度和效率超高。电磁场模拟对于光子设备和电路的设计，优化和验证至关重要。但是，昂贵的数值模拟显着阻碍了光子电路设计循环中的可扩展性和转环。最近，已经提出了物理信息的神经网络来预测具有预定义参数的部分微分方程（PDE）的单个实例的光场解。它们复杂的PDE公式和缺乏有效的参数化机制限制了其在实际模拟方案中的灵活性和概括。在这项工作中，首次提出了一个被称为Neurolight的物理敏捷神经操作员框架，以学习一个频率域的麦克斯韦PDE家族，以进行超快速的参数光子设备模拟。我们通过几种新技术来平衡神经照明的效率和概括。具体而言，我们将不同的设备离散到统一域中，代表具有紧凑型波的参数PDE，并通过掩盖的源建模编码入射光。我们使用参数效率高的跨形神经块设计模型，并采用基于叠加的增强来进行数据效率学习。通过这些协同方法，神经亮像可以概括为大量的看不见的模拟设置，比数值求解器显示了2个磁性的模拟速度，并且比先前的神经网络模型优于降低54％的预测误差，而降低了约44％的参数。 。我们的代码可在https://github.com/jeremiemelo/neurolight上找到。

现有的最佳3D对象检测器通常依赖于多模式融合策略。但是，由于忽略了特定于模式的有用信息，因此从根本上限制了该设计，并最终阻碍了模型性能。为了解决这一局限性，在这项工作中，我们介绍了一种新型的模式相互作用策略，在该策略中，在整个过程中学习和维护单个单模式表示，以使其在物体检测过程中被利用其独特特征。为了实现这一建议的策略，我们设计了一个深层互动体系结构，其特征是多模式代表性交互编码器和多模式预测交互解码器。大规模Nuscenes数据集的实验表明，我们所提出的方法经常超过所有先前的艺术。至关重要的是，我们的方法在竞争激烈的Nuscenes对象检测排行榜上排名第一。

我们提出了CrossHuman，这是一种新颖的方法，该方法从参数人类模型和多帧RGB图像中学习了交叉指导，以实现高质量的3D人类重建。为了恢复几何细节和纹理，即使在无形区域中，我们设计了一个重建管道，结合了基于跟踪的方法和无跟踪方法。给定一个单眼RGB序列，我们在整个序列中跟踪参数人模型，与目标框架相对应的点（体素）被参数体运动扭曲为参考框架。在参数体的几何学先验和RGB序列的空间对齐特征的指导下，稳健隐式表面被融合。此外，将多帧变压器（MFT）和一个自我监管的经过修补模块集成到框架中，以放宽参数主体的要求并帮助处理非常松散的布。与以前的作品相比，我们的十字人类可以在可见的和无形区域启用高保真的几何细节和纹理，并提高人类重建的准确性，即使在估计的不准确的参数人类模型下也是如此。实验表明我们的方法达到了最新的（SOTA）性能。

事件摄像机最近在高动力或具有挑战性的照明情况下具有强大的常规摄像头的潜力，因此摄影机最近变得越来越受欢迎。通过同时定位和映射（SLAM）给出了可能受益于事件摄像机的重要问题。但是，为了确保在包含事件的多传感器大满贯上进展，需要新颖的基准序列。我们的贡献是使用包含基于事件的立体声摄像机，常规立体声摄像机，多个深度传感器和惯性测量单元的多传感器设置捕获的第一组基准数据集。该设置是完全硬件同步的，并且经过了准确的外部校准。所有序列都均均均均由高度准确的外部参考设备（例如运动捕获系统）捕获的地面真相数据。各个序列都包括小型和大型环境，并涵盖动态视觉传感器针对的特定挑战。

通用事件边界检测（GEBD）是视频理解中的一项重要但挑战性的任务，该任务旨在检测人类自然感知事件边界的时刻。在本文中，我们为GEBD任务提供了本地上下文建模和全局边界解码方法。提出了局部上下文建模子网络来感知通用事件边界的各种模式，并生成强大的视频表示和可靠的边界信心。基于它们，全局边界解码子网络被利用为从全局视图解码事件边界。我们提出的方法在动力学-GEBD测试集上达到了85.13％的F1得分，与基线方法相比，它实现了22％以上的F1得分增强。该代码可从https://github.com/jackytown/gebd_challenge_cvpr2022获得。