Score-based diffusion models have captured widespread attention and funded fast progress of recent vision generative tasks. In this paper, we focus on diffusion model backbone which has been much neglected before. We systematically explore vision Transformers as diffusion learners for various generative tasks. With our improvements the performance of vanilla ViT-based backbone (IU-ViT) is boosted to be on par with traditional U-Net-based methods. We further provide a hypothesis on the implication of disentangling the generative backbone as an encoder-decoder structure and show proof-of-concept experiments verifying the effectiveness of a stronger encoder for generative tasks with ASymmetriC ENcoder Decoder (ASCEND). Our improvements achieve competitive results on CIFAR-10, CelebA, LSUN, CUB Bird and large-resolution text-to-image tasks. To the best of our knowledge, we are the first to successfully train a single diffusion model on text-to-image task beyond 64x64 resolution. We hope this will motivate people to rethink the modeling choices and the training pipelines for diffusion-based generative models.

Traditional multilingual neural machine translation (MNMT) uses a single model to translate all directions. However, with the increasing scale of language pairs, simply using a single model for massive MNMT brings new challenges: parameter tension and large computations. In this paper, we revisit multi-way structures by assigning an individual branch for each language (group). Despite being a simple architecture, it is challenging to train de-centralized models due to the lack of constraints to align representations from all languages. We propose a localized training recipe to map different branches into a unified space, resulting in an efficient detachable model, Lego-MT. For a fair comparison, we collect data from OPUS and build the first large-scale open-source translation benchmark covering 7 language-centric data, each containing 445 language pairs. Experiments show that Lego-MT (1.2B) brings gains of more than 4 BLEU while outperforming M2M-100 (12B) (We will public all training data, models, and checkpoints)

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.

We propose a sparse end-to-end multi-person pose regression framework, termed QueryPose, which can directly predict multi-person keypoint sequences from the input image. The existing end-to-end methods rely on dense representations to preserve the spatial detail and structure for precise keypoint localization. However, the dense paradigm introduces complex and redundant post-processes during inference. In our framework, each human instance is encoded by several learnable spatial-aware part-level queries associated with an instance-level query. First, we propose the Spatial Part Embedding Generation Module (SPEGM) that considers the local spatial attention mechanism to generate several spatial-sensitive part embeddings, which contain spatial details and structural information for enhancing the part-level queries. Second, we introduce the Selective Iteration Module (SIM) to adaptively update the sparse part-level queries via the generated spatial-sensitive part embeddings stage-by-stage. Based on the two proposed modules, the part-level queries are able to fully encode the spatial details and structural information for precise keypoint regression. With the bipartite matching, QueryPose avoids the hand-designed post-processes and surpasses the existing dense end-to-end methods with 73.6 AP on MS COCO mini-val set and 72.7 AP on CrowdPose test set. Code is available at https://github.com/buptxyb666/QueryPose.

Semantic segmentation of Very High Resolution (VHR) remote sensing images is a fundamental task for many applications. However, large variations in the scales of objects in those VHR images pose a challenge for performing accurate semantic segmentation. Existing semantic segmentation networks are able to analyse an input image at up to four resizing scales, but this may be insufficient given the diversity of object scales. Therefore, Multi Scale (MS) test-time data augmentation is often used in practice to obtain more accurate segmentation results, which makes equal use of the segmentation results obtained at the different resizing scales. However, it was found in this study that different classes of objects had their preferred resizing scale for more accurate semantic segmentation. Based on this behaviour, a Stacking-Based Semantic Segmentation (SBSS) framework is proposed to improve the segmentation results by learning this behaviour, which contains a learnable Error Correction Module (ECM) for segmentation result fusion and an Error Correction Scheme (ECS) for computational complexity control. Two ECS, i.e., ECS-MS and ECS-SS, are proposed and investigated in this study. The Floating-point operations (Flops) required for ECS-MS and ECS-SS are similar to the commonly used MS test and the Single-Scale (SS) test, respectively. Extensive experiments on four datasets (i.e., Cityscapes, UAVid, LoveDA and Potsdam) show that SBSS is an effective and flexible framework. It achieved higher accuracy than MS when using ECS-MS, and similar accuracy as SS with a quarter of the memory footprint when using ECS-SS.

The success of deep neural networks requires both high annotation quality and massive data. However, the size and the quality of a dataset are usually a trade-off in practice, as data collection and cleaning are expensive and time-consuming. Therefore, automatic noisy label detection (NLD) techniques are critical to real-world applications, especially those using crowdsourcing datasets. As this is an under-explored topic in automatic speaker verification (ASV), we present a simple but effective solution to the task. First, we compare the effectiveness of various commonly used metric learning loss functions under different noise settings. Then, we propose two ranking-based NLD methods, inter-class inconsistency and intra-class inconsistency ranking. They leverage the inconsistent nature of noisy labels and show high detection precision even under a high level of noise. Our solution gives rise to both efficient and effective cleaning of large-scale speaker recognition datasets.

Three-phase PWM voltage-source rectifier (VSR) systems have been widely used in various energy conversion systems, where current sensors are the key component for state monitoring and system control. The current sensor faults may bring hidden danger or damage to the whole system; therefore, this paper proposed a random forest (RF) and current fault texture feature-based method for current sensor fault diagnosis in three-phase PWM VSR systems. First, the three-phase alternating currents (ACs) of the three-phase PWM VSR are collected to extract the current fault texture features, and no additional hardware sensors are needed to avoid causing additional unstable factors. Then, the current fault texture features are adopted to train the random forest current sensor fault detection and diagnosis (CSFDD) classifier, which is a data-driven CSFDD classifier. Finally, the effectiveness of the proposed method is verified by simulation experiments. The result shows that the current sensor faults can be detected and located successfully and that it can effectively provide fault locations for maintenance personnel to keep the stable operation of the whole system.

在本文中，我们考虑了基于系数的正则分布回归，该回归旨在从概率措施中回归到复制的内核希尔伯特空间（RKHS）的实现响应（RKHS），该响应将正则化放在系数上，而内核被假定为无限期的。 。该算法涉及两个采样阶段，第一阶段样本由分布组成，第二阶段样品是从这些分布中获得的。全面研究了回归函数的不同规律性范围内算法的渐近行为，并通过整体操作员技术得出学习率。我们在某些温和条件下获得最佳速率，这与单级采样的最小最佳速率相匹配。与文献中分布回归的内核方法相比，所考虑的算法不需要内核是对称的和阳性的半明确仪，因此为设计不确定的内核方法提供了一个简单的范式，从而丰富了分布回归的主题。据我们所知，这是使用不确定核进行分配回归的第一个结果，我们的算法可以改善饱和效果。

本文回顾了AIM 2022上压缩图像和视频超级分辨率的挑战。这项挑战包括两条曲目。轨道1的目标是压缩图像的超分辨率，轨迹〜2靶向压缩视频的超分辨率。在轨道1中，我们使用流行的数据集DIV2K作为培训，验证和测试集。在轨道2中，我们提出了LDV 3.0数据集，其中包含365个视频，包括LDV 2.0数据集（335个视频）和30个其他视频。在这一挑战中，有12支球队和2支球队分别提交了赛道1和赛道2的最终结果。所提出的方法和解决方案衡量了压缩图像和视频上超分辨率的最先进。提出的LDV 3.0数据集可在https://github.com/renyang-home/ldv_dataset上找到。此挑战的首页是在https://github.com/renyang-home/aim22_compresssr。

基于图像的3D检测是自主驾驶感知系统的必不可少的组成部分。但是，它仍然受到不满意的表现，这是有限的培训数据的主要原因之一。不幸的是，在3D空间中注释对象是极度时间/资源消耗的，这使得很难任意扩展训练集。在这项工作中，我们专注于半监督的方式，并探索更便宜的替代方案（即伪标记）的可行性，以利用未标记的数据。为此，我们进行了广泛的实验，以研究伪标签是否可以在不同环境下为基线模型提供有效的监督。实验结果不仅证明了基于图像的3D检测的伪标记机制的有效性（例如，在单眼设置下，我们在没有铃铛和哨声的Kitti-3D测试集上实现了20.23 AP，用于中等水平，从6.03 AP），但还显示了几个有趣且值得注意的发现（例如，经过伪标签训练的模型的性能要比基于相同培训数据的地面真相注释训练的表现更好）。我们希望这项工作可以在半监督环境下为基于图像的3D检测社区提供见解。代码，伪标签和预培训模型将公开可用。