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.

Recently, spoken dialogue systems have been widely deployed in a variety of applications, serving a huge number of end-users. A common issue is that the errors resulting from noisy utterances, semantic misunderstandings, or lack of knowledge make it hard for a real system to respond properly, possibly leading to an unsatisfactory user experience. To avoid such a case, we consider a proactive interaction mechanism where the system predicts the user satisfaction with the candidate response before giving it to the user. If the user is not likely to be satisfied according to the prediction, the system will ask the user a suitable question to determine the real intent of the user instead of providing the response directly. With such an interaction with the user, the system can give a better response to the user. Previous models that predict the user satisfaction are not applicable to DuerOS which is a large-scale commercial dialogue system. They are based on hand-crafted features and thus can hardly learn the complex patterns lying behind millions of conversations and temporal dependency in multiple turns of the conversation. Moreover, they are trained and evaluated on the benchmark datasets with adequate labels, which are expensive to obtain in a commercial dialogue system. To face these challenges, we propose a pipeline to predict the user satisfaction to help DuerOS decide whether to ask for clarification in each turn. Specifically, we propose to first generate a large number of weak labels and then train a transformer-based model to predict the user satisfaction with these weak labels. Empirically, we deploy and evaluate our model on DuerOS, and observe a 19% relative improvement on the accuracy of user satisfaction prediction and 2.3% relative improvement on user experience.

Multibeam forward-looking sonar (MFLS) plays an important role in underwater detection. There are several challenges to the research on underwater object detection with MFLS. Firstly, the research is lack of available dataset. Secondly, the sonar image, generally processed at pixel level and transformed to sector representation for the visual habits of human beings, is disadvantageous to the research in artificial intelligence (AI) areas. Towards these challenges, we present a novel dataset, the underwater acoustic target detection (UATD) dataset, consisting of over 9000 MFLS images captured using Tritech Gemini 1200ik sonar. Our dataset provides raw data of sonar images with annotation of 10 categories of target objects (cube, cylinder, tyres, etc). The data was collected from lake and shallow water. To verify the practicality of UATD, we apply the dataset to the state-of-the-art detectors and provide corresponding benchmarks for its accuracy and efficiency.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

在模板和搜索区域之间学习强大的功能匹配对于3D暹罗跟踪至关重要。暹罗功能匹配的核心是如何在模板和搜索区域之间的相应点上分配高特征相似性，以进行精确的对象本地化。在本文中，我们提出了一个新颖的点云登记驱动的暹罗跟踪框架，直觉是空间对齐相应点（通过3D注册）倾向于实现一致的特征表示。具体而言，我们的方法由两个模块组成，包括特定于特定的非局部注册模块和一个注册辅助的sindhorn模板 - 特征聚合模块。登记模块在模板和搜索区域之间的精确空间对齐中进行目标。提出了跟踪特异性的空间距离约束，以优化非局部模块中的交叉注意权重，以进行判别特征学习。然后，我们使用加权SVD来计算模板和搜索区域之间的刚性转换，并对齐它们以实现所需的空间对齐相应点。对于特征聚合模型，我们将转换模板和搜索区域之间的特征匹配作为最佳传输问题，并利用Sinkhorn优化来搜索异常型匹配匹配解决方案。同样，建造了登记辅助空间距离图，以改善无法区分的区域（例如光滑的表面）的匹配鲁棒性。最后，在获得的功能匹配地图的指导下，我们将目标信息从模板中汇总到搜索区域中以构建特定于目标的特征，然后将其馈送到一个类似中心点的检测头中以进行对象定位。关于Kitti，Nuscenes和Waymo数据集的广泛实验验证了我们提出的方法的有效性。

最近，后门攻击已成为对深神经网络（DNN）模型安全性的新兴威胁。迄今为止，大多数现有研究都集中于对未压缩模型的后门攻击。尽管在实际应用中广泛使用的压缩DNN的脆弱性尚未得到利用。在本文中，我们建议研究和发展针对紧凑型DNN模型（RIBAC）的强大和不可感知的后门攻击。通过对重要设计旋钮进行系统分析和探索，我们提出了一个框架，该框架可以有效地学习适当的触发模式，模型参数和修剪口罩。从而同时达到高触发隐形性，高攻击成功率和高模型效率。跨不同数据集的广泛评估，包括针对最先进的防御机制的测试，证明了RIBAC的高鲁棒性，隐身性和模型效率。代码可从https://github.com/huyvnphan/eccv2022-ribac获得

基于暹罗网络的跟踪器将3D单一对象跟踪作为模板和搜索区域的点特征之间的互相关学习。由于跟踪过程中模板和搜索区域之间的外观差异很大，因此如何学习它们之间的稳健跨相关性以识别搜索区域中的潜在目标仍然是一个挑战性的问题。在本文中，我们明确使用变压器形成一个3D Siamese变压器网络，以学习模板和点云的搜索区域之间的强大互相关。具体来说，我们开发了一个暹罗点变压器网络，以了解目标的形状上下文信息。它的编码器使用自我注意力来捕获点云的非本地信息来表征对象的形状信息，而解码器则利用交叉注意来提取歧视点特征。之后，我们开发了一个迭代的粗到加密相关网络，以了解模板与搜索区域之间的稳健跨相关性。它通过交叉注意将模板与搜索区域中的潜在目标联系起来，制定了交叉功能的增强。为了进一步增强潜在目标，它采用了自我功能增强，该增强功能将自我注意力应用于特征空间的本地K-NN图来汇总目标特征。 Kitti，Nuscenes和Waymo数据集的实验表明，我们的方法在3D单一对象跟踪任务上实现了最先进的性能。

现有的自我监督的单眼估计方法可以摆脱昂贵的注释并获得令人鼓舞的结果。但是，当直接采用接受固定分辨率训练的模型以评估其他不同决议时，这些方法会遭受严重的性能降解。在本文中，我们通过学习场景深度的规模不变性，提出了一个分辨率自适应自我监督的单眼估计方法（RA-DEPTH）。具体而言，我们提出了一种简单而有效的数据增强方法，以生成具有任意尺度的同一场景的图像。然后，我们开发了一个双重高分辨率网络，该网络使用具有密集交互的多路径编码器和解码器来汇总多尺度特征，以进行准确的深度推理。最后，为了明确了解场景深度的规模不变性，我们在具有不同尺度的深度预测上制定了跨尺度的深度一致性损失。对Kitti，Make3D和NYU-V2数据集进行了广泛的实验表明，RA-DEPTH不仅可以实现最新的性能，而且还表现出很好的解决能力。

我们为深神经网络引入了两个低位训练后训练量化（PTQ）方法，该方法满足硬件要求，并且不需要长期重新训练。两次量化的能力可以将通过量化和去除化引入的乘法转换为许多有效加速器采用的位移位。但是，两次量表因子的候选值较少，这会导致更多的舍入或剪辑错误。我们提出了一种新型的两个PTQ框架，称为RAPQ，该框架被动态调整了整个网络的两个尺度，而不是静态地确定它们一层。从理论上讲，它可以权衡整个网络的舍入错误和剪辑错误。同时，RAPQ中的重建方法基于每个单元的BN信息。对Imagenet的广泛实验证明了我们提出的方法的出色性能。没有铃铛和哨声，REPQ在RESNET-18和MOBILENETV2上的准确度可以达到65％和48％，分别具有INT2激活INT4的精度。我们是第一个为低位PTQ提出更受限制但对硬件友好型的两次量化方案的人，并证明它可以达到与SOTA PTQ方法几乎相同的准确性。该代码已发布。

面向任务导向的对话系统已经受到获得大规模和高质量的注释对话的困难困扰。此外，大多数公开的数据集仅包括书面对话，这不足以反映实际口头对话系统中的实际人类行为。在本文中，我们提出了面向任务的对话数据增强（TOD-DA），这是一种新型模型 - 不可知的数据增强范例，以提高面向任务对话建模的鲁棒性。 TOD-DA由两个模块组成：1）对话丰富，以扩展关于易于执行数据稀疏性的任务对话的培训数据，用于宽松数据稀疏性和2）口语对话模拟器，以模仿各种粒度的口语样式表达和语音识别错误，以弥合书面之间的差距和口头对话。通过这样的设计，我们的方法在DSTC10 Track2的两个任务中排名第一，这是针对口语对话的任务对话建模的基准，展示了我们提出的TOD-DA的优势和有效性。