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.

Generating new fonts is a time-consuming and labor-intensive, especially in a language with a huge amount of characters like Chinese. Various deep learning models have demonstrated the ability to efficiently generate new fonts with a few reference characters of that style. This project aims to develop a few-shot cross-lingual font generator based on AGIS-Net and improve the performance metrics mentioned. Our approaches include redesigning the encoder and the loss function. We will validate our method on multiple languages and datasets mentioned.

We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks. To the best of our knowledge, MEM is the first approach that combines multi-view representation learning and intrinsic reward-driven exploration in reinforcement learning (RL). More specifically, MEM first extracts the specific and shared information of multi-view observations to form high-quality features before performing RL on the learned features, enabling the agent to fully comprehend the environment and yield better actions. Furthermore, MEM transforms the multi-view features into intrinsic rewards based on entropy maximization to encourage exploration. As a result, MEM can significantly promote the sample-efficiency and generalization ability of the RL agent, facilitating solving real-world problems with high-dimensional observations and spare-reward space. We evaluate MEM on various tasks from DeepMind Control Suite and Procgen games. Extensive simulation results demonstrate that MEM can achieve superior performance and outperform the benchmarking schemes with simple architecture and higher efficiency.

Flow-guide synthesis provides a common framework for frame interpolation, where optical flow is typically estimated by a pyramid network, and then leveraged to guide a synthesis network to generate intermediate frames between input frames. In this paper, we present UPR-Net, a novel Unified Pyramid Recurrent Network for frame interpolation. Cast in a flexible pyramid framework, UPR-Net exploits lightweight recurrent modules for both bi-directional flow estimation and intermediate frame synthesis. At each pyramid level, it leverages estimated bi-directional flow to generate forward-warped representations for frame synthesis; across pyramid levels, it enables iterative refinement for both optical flow and intermediate frame. In particular, we show that our iterative synthesis can significantly improve the robustness of frame interpolation on large motion cases. Despite being extremely lightweight (1.7M parameters), UPR-Net achieves excellent performance on a large range of benchmarks. Code will be available soon.

探索对于具有高维观察和稀疏奖励的复杂环境中的深度强化学习至关重要。为了解决这个问题，最新的方法旨在利用内在的奖励来改善勘探，例如基于新颖的探索和基于预测的探索。但是，许多固有的奖励模块需要复杂的结构和表示学习，从而导致了过度的计算复杂性和不稳定的性能。在本文中，我们提出了一种有益的情节访问差异（REVD），这是一种计算有效且量化的探索方法。更具体地说，REVD通过评估情节之间的基于R \'Enyi Divergence的访问差异来提供内在的奖励。为了进行有效的差异估计，使用随机定义状态编码器使用K-Nearest邻居估计器。最后，在Pybullet机器人环境和Atari游戏上测试了REVD。广泛的实验表明，REVD可以显着提高强化学习算法的样本效率，并优于基准测定方法。

在无监督的域适应性（UDA）中，直接从源到目标域的适应通常会遭受明显的差异，并导致对齐不足。因此，许多UDA的作品试图通过各种中间空间逐渐和轻柔地消失域间隙，这些空间被称为域桥接（DB）。但是，对于诸如域自适应语义分割（DASS）之类的密集预测任务，现有的解决方案主要依赖于粗糙的样式转移以及如何优雅地桥接域的优雅桥梁。在这项工作中，我们诉诸于数据混合以建立用于DASS的经过经过经过经过讨论的域桥接（DDB），通过该域的源和目标域的联合分布与中间空间中的每个分布进行对齐并与每个分布。 DDB的核心是双路径域桥接步骤，用于使用粗糙和精细的数据混合技术生成两个中间域，以及一个跨路径知识蒸馏步骤，用于对两个互补模型进行对生成的中间样品进行培训的互补模型作为“老师”以多教老师的蒸馏方式发展出色的“学生”。这两个优化步骤以交替的方式工作，并相互加强以具有强大的适应能力引起DDB。对具有不同设置的自适应分割任务进行的广泛实验表明，我们的DDB显着优于最先进的方法。代码可从https://github.com/xiaoachen98/ddb.git获得。

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。

延时摄影是在电影和宣传电影中使用的，因为它可以在短时间内反映时间的流逝并增强视觉吸引力。但是，由于需要很长时间才需要稳定的射击，因此对摄影师来说是一个巨大的挑战。在本文中，我们提出了一个带有虚拟和真实机器人的延时摄影系统。为了帮助用户有效拍摄延时视频，我们首先参数化延时摄影并提出参数优化方法。对于不同的参数，使用不同的美学模型，包括图像和视频美学质量评估网络，用于生成最佳参数。然后，我们提出了一个延时摄影界面，以促进用户查看和调整参数，并使用虚拟机器人在三维场景中进行虚拟摄影。该系统还可以导出参数并将其提供给真实的机器人，以便可以在现实世界中拍摄延时视频。此外，我们提出了一种延时摄影美学评估方法，该方法可以自动评估及时视频的美学质量。实验结果表明，我们的方法可以有效地获得延时视频。我们还进行了用户研究。结果表明，我们的系统具有与专业摄影师相似的效果，并且更有效。

最近，行动识别因其在智能监视和人为计算机互动方面的全面和实用应用而受到了越来越多的关注。但是，由于数据稀缺性，很少有射击动作识别并未得到充分的探索，并且仍然具有挑战性。在本文中，我们提出了一种新型的分层组成表示（HCR）学习方法，以进行几次识别。具体而言，我们通过精心设计的层次聚类将复杂的动作分为几个子行动，并将子动作进一步分解为更细粒度的空间注意力亚actions（SAS-Actions）。尽管基类和新颖类之间存在很大的差异，但它们可以在子行动或SAS行为中共享相似的模式。此外，我们在运输问题中采用了地球移动器的距离，以测量视频样本之间的相似性在亚行动表示方面。它计算为距离度量的子行动之间的最佳匹配流，这有利于比较细粒模式。广泛的实验表明，我们的方法在HMDB51，UCF101和动力学数据集上实现了最新结果。

在本文中，我们提出了一种基于排名的水下图像质量评估（UIQA）方法，该方法缩写为Uranker。乌兰克（Uranker）建立在高效的注意力图像变压器上。在水下图像方面，我们特别设计（1）直方图嵌入了水下图像作为直方图表的颜色分布以参加全局降解，以及（2）与模型局部降解的动态跨尺度对应关系。最终预测取决于不同量表的类代币，该标记是全面考虑多尺度依赖性的。随着保证金排名损失，我们的乌员可以根据其视觉质量通过不同的水下图像增强（UIE）算法来准确对同一场景的水下图像的顺序进行排名。为此，我们还贡献了一个数据集，即Urankerset，其中包含不同的UIE算法和相应的感知排名增强的足够结果，以训练我们的uranker。除了Uranker的良好表现外，我们发现一个简单的U-Shape UIE网络与我们的预训练的Uranker相结合时可以获得有希望的性能。此外，我们还提出了一个标准化尾巴，可以显着提高UIE网络的性能。广泛的实验证明了我们方法的最新性能。讨论了我们方法的关键设计。我们将发布我们的数据集和代码。