Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP). The images can then be used for photography or visual computing tasks in a variety of applications, such as public safety surveillance and autonomous driving. One can argue that since RAW images contain all the captured information, the conversion of RAW to RGB using an ISP is not necessary for visual computing. In this paper, we propose a novel $\rho$-Vision framework to perform high-level semantic understanding and low-level compression using RAW images without the ISP subsystem used for decades. Considering the scarcity of available RAW image datasets, we first develop an unpaired CycleR2R network based on unsupervised CycleGAN to train modular unrolled ISP and inverse ISP (invISP) models using unpaired RAW and RGB images. We can then flexibly generate simulated RAW images (simRAW) using any existing RGB image dataset and finetune different models originally trained for the RGB domain to process real-world camera RAW images. We demonstrate object detection and image compression capabilities in RAW-domain using RAW-domain YOLOv3 and RAW image compressor (RIC) on snapshots from various cameras. Quantitative results reveal that RAW-domain task inference provides better detection accuracy and compression compared to RGB-domain processing. Furthermore, the proposed \r{ho}-Vision generalizes across various camera sensors and different task-specific models. Additional advantages of the proposed $\rho$-Vision that eliminates the ISP are the potential reductions in computations and processing times.

This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage translation paradigm called Hybrid Regression Translation (HRT) to combine the advantages of autoregressive and non-autoregressive translation. Specifically, HRT first autoregressively generates a discontinuous sequence (e.g., make a prediction every $k$ tokens, $k>1$) and then fills in all previously skipped tokens at once in a non-autoregressive manner. Thus, we can easily trade off the translation quality and speed by adjusting $k$. In addition, by integrating other modeling techniques (e.g., sequence-level knowledge distillation and deep-encoder-shallow-decoder layer allocation strategy) and a mass of engineering efforts, HRT improves 80\% inference speed and achieves equivalent translation performance with the same-capacity AT counterpart. Our fastest system reaches 6k+ words/second on the GPU latency setting, estimated to be about 3.1x faster than the last year's winner.

Bird's-Eye-View (BEV) 3D Object Detection is a crucial multi-view technique for autonomous driving systems. Recently, plenty of works are proposed, following a similar paradigm consisting of three essential components, i.e., camera feature extraction, BEV feature construction, and task heads. Among the three components, BEV feature construction is BEV-specific compared with 2D tasks. Existing methods aggregate the multi-view camera features to the flattened grid in order to construct the BEV feature. However, flattening the BEV space along the height dimension fails to emphasize the informative features of different heights. For example, the barrier is located at a low height while the truck is located at a high height. In this paper, we propose a novel method named BEV Slice Attention Network (BEV-SAN) for exploiting the intrinsic characteristics of different heights. Instead of flattening the BEV space, we first sample along the height dimension to build the global and local BEV slices. Then, the features of BEV slices are aggregated from the camera features and merged by the attention mechanism. Finally, we fuse the merged local and global BEV features by a transformer to generate the final feature map for task heads. The purpose of local BEV slices is to emphasize informative heights. In order to find them, we further propose a LiDAR-guided sampling strategy to leverage the statistical distribution of LiDAR to determine the heights of local slices. Compared with uniform sampling, LiDAR-guided sampling can determine more informative heights. We conduct detailed experiments to demonstrate the effectiveness of BEV-SAN. Code will be released.

Recently, Bird's-Eye-View (BEV) representation has gained increasing attention in multi-view 3D object detection, which has demonstrated promising applications in autonomous driving. Although multi-view camera systems can be deployed at low cost, the lack of depth information makes current approaches adopt large models for good performance. Therefore, it is essential to improve the efficiency of BEV 3D object detection. Knowledge Distillation (KD) is one of the most practical techniques to train efficient yet accurate models. However, BEV KD is still under-explored to the best of our knowledge. Different from image classification tasks, BEV 3D object detection approaches are more complicated and consist of several components. In this paper, we propose a unified framework named BEV-LGKD to transfer the knowledge in the teacher-student manner. However, directly applying the teacher-student paradigm to BEV features fails to achieve satisfying results due to heavy background information in RGB cameras. To solve this problem, we propose to leverage the localization advantage of LiDAR points. Specifically, we transform the LiDAR points to BEV space and generate the foreground mask and view-dependent mask for the teacher-student paradigm. It is to be noted that our method only uses LiDAR points to guide the KD between RGB models. As the quality of depth estimation is crucial for BEV perception, we further introduce depth distillation to our framework. Our unified framework is simple yet effective and achieves a significant performance boost. Code will be released.

Vision-Centric Bird-Eye-View (BEV) perception has shown promising potential and attracted increasing attention in autonomous driving. Recent works mainly focus on improving efficiency or accuracy but neglect the domain shift problem, resulting in severe degradation of transfer performance. With extensive observations, we figure out the significant domain gaps existing in the scene, weather, and day-night changing scenarios and make the first attempt to solve the domain adaption problem for multi-view 3D object detection. Since BEV perception approaches are usually complicated and contain several components, the domain shift accumulation on multi-latent spaces makes BEV domain adaptation challenging. In this paper, we propose a novel Multi-level Multi-space Alignment Teacher-Student ($M^{2}ATS$) framework to ease the domain shift accumulation, which consists of a Depth-Aware Teacher (DAT) and a Multi-space Feature Aligned (MFA) student model. Specifically, DAT model adopts uncertainty guidance to sample reliable depth information in target domain. After constructing domain-invariant BEV perception, it then transfers pixel and instance-level knowledge to student model. To further alleviate the domain shift at the global level, MFA student model is introduced to align task-relevant multi-space features of two domains. To verify the effectiveness of $M^{2}ATS$, we conduct BEV 3D object detection experiments on four cross domain scenarios and achieve state-of-the-art performance (e.g., +12.6% NDS and +9.1% mAP on Day-Night). Code and dataset will be released.

In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs. Different from most existing classical graph kernels, the proposed HAQJSK kernels can incorporate hierarchical aligned structure information between graphs and transform graphs of random sizes into fixed-sized aligned graph structures, i.e., the Hierarchical Transitive Aligned Adjacency Matrix of vertices and the Hierarchical Transitive Aligned Density Matrix of the Continuous-Time Quantum Walk (CTQW). For a pair of graphs to hand, the resulting HAQJSK kernels are defined by measuring the Quantum Jensen-Shannon Divergence (QJSD) between their transitive aligned graph structures. We show that the proposed HAQJSK kernels not only reflect richer intrinsic global graph characteristics in terms of the CTQW, but also address the drawback of neglecting structural correspondence information arising in most existing R-convolution kernels. Furthermore, unlike the previous Quantum Jensen-Shannon Kernels associated with the QJSD and the CTQW, the proposed HAQJSK kernels can simultaneously guarantee the properties of permutation invariant and positive definiteness, explaining the theoretical advantages of the HAQJSK kernels. Experiments indicate the effectiveness of the proposed kernels.

Code pre-trained models (CodePTMs) have recently demonstrated significant success in code intelligence. To interpret these models, some probing methods have been applied. However, these methods fail to consider the inherent characteristics of codes. In this paper, to address the problem, we propose a novel probing method CAT-probing to quantitatively interpret how CodePTMs attend code structure. We first denoise the input code sequences based on the token types pre-defined by the compilers to filter those tokens whose attention scores are too small. After that, we define a new metric CAT-score to measure the commonality between the token-level attention scores generated in CodePTMs and the pair-wise distances between corresponding AST nodes. The higher the CAT-score, the stronger the ability of CodePTMs to capture code structure. We conduct extensive experiments to integrate CAT-probing with representative CodePTMs for different programming languages. Experimental results show the effectiveness of CAT-probing in CodePTM interpretation. Our codes and data are publicly available at https://github.com/nchen909/CodeAttention.

最近的工作表明，变异自动编码器（VAE）与速率失真理论之间有着密切的理论联系。由此激发，我们从生成建模的角度考虑了有损图像压缩的问题。从最初是为数据（图像）分布建模设计的Resnet VAE开始，我们使用量化意识的后验和先验重新设计其潜在变量模型，从而实现易于量化和熵编码的图像压缩。除了改进的神经网络块外，我们还提出了一类强大而有效的有损图像编码器类别，超过了自然图像（有损）压缩的先前方法。我们的模型以粗略的方式压缩图像，并支持并行编码和解码，从而在GPU上快速执行。

深度估计对于各种重要的现实世界应用至关重要，例如自动驾驶。但是，在高速场景中，它遭受了严重的性能退化，因为传统相机只能捕获模糊的图像。为了解决这个问题，Spike摄像头旨在以高框架速率捕获像素的亮度强度。但是，使用传统的单眼或立体声深度估计算法，使用尖峰摄像机的深度估计仍然非常具有挑战性，这些算法基于光度一致性。在本文中，我们提出了一种新型的不确定性引导深度融合（UGDF）框架，以融合Spike摄像机的单眼和立体声深度估计网络的预测。我们的框架是由于立体声尖峰深度估计在近距离取得更好的结果，而单眼尖峰深度估计获得了更好的结果。因此，我们引入了具有联合培训策略的双任务深度估计结构，并估算了分布式不确定性以融合单眼和立体声结果。为了证明尖峰深度估计比传统的摄像头深度估计的优势，我们为一个名为CitySpike20k的尖峰深度数据集，其中包含20k配对的样品，以进行尖峰深度估计。 UGDF在CitySpike20k上取得了最新的结果，超过了所有单眼或立体声尖峰深度估计基线。我们进行了广泛的实验，以评估我们方法对CitySpike20k的有效性和概括。据我们所知，我们的框架是第一个用于尖峰摄像头深度估算的双任务融合框架。代码和数据集将发布。

神经形态尖峰摄像机以生物启发的方式生成具有高时间分辨率的数据流，该方式在自动驾驶等现实世界应用中具有巨大的潜力。与RGB流相反，Spike流具有克服运动模糊的固有优势，从而导致对高速对象的更准确的深度估计。但是，几乎不可能以监督的方式培训尖峰深度估计网络，因为获得时间密集的尖峰流的配对深度标签非常费力和挑战。在本文中，我们没有构建带有完整深度标签的Spike流数据集，而是以不受监督的方式从开源RGB数据集（例如Kitti）和估算峰值深度转移知识。此类问题的关键挑战在于RGB和SPIKE模式之间的模态差距，以及标记的源RGB和未标记的目标尖峰域之间的域间隙。为了克服这些挑战，我们引入了无监督的尖峰深度估计的跨模式跨域（BICROSS）框架。我们的方法通过引入中介模拟的源尖峰域来缩小源RGB和目标尖峰之间的巨大差距。要具体而言，对于跨模式阶段，我们提出了一种新颖的粗到精细知识蒸馏（CFKD），将图像和像素级知识从源RGB转移到源尖峰。这种设计分别利用了RGB和SPIKE模式的大量语义和密集的时间信息。对于跨域阶段，我们引入了不确定性引导的均值老师（UGMT），以生成具有不确定性估计的可靠伪标签，从而减轻了源尖峰和目标尖峰域之间的变化。此外，我们提出了一种全局级特征对齐方法（GLFA），以对齐两个域之间的特征并生成更可靠的伪标签。