Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning. However, they neglect the relationship between multiple granularities and different features in alignment, degrading detection. Addressing this, we introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning. The key is to encode the dependencies across different granularities including pixel-, instance-, and category-levels simultaneously to align two domains. Specifically, based on pixel-level features, we first develop an omni-scale gated fusion (OSGF) module to aggregate discriminative representations of instances with scale-aware convolutions, leading to robust multi-scale detection. Besides, we introduce multi-granularity discriminators to identify where, either source or target domains, different granularities of samples come from. Note that, MGA not only leverages instance discriminability in different categories but also exploits category consistency between two domains for detection. Furthermore, we present an adaptive exponential moving average (AEMA) strategy that explores model assessments for model update to improve pseudo labels and alleviate local misalignment problem, boosting detection robustness. Extensive experiments on multiple domain adaption scenarios validate the superiority of MGA over other approaches on FCOS and Faster R-CNN detectors. Code will be released at https://github.com/tiankongzhang/MGA.

In subcellular biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures. However, fluorescence staining is slow, expensive, and harmful to cells. In this paper, we treat it as a deep learning task termed subcellular structure prediction (SSP), aiming to predict the 3D fluorescent images of multiple subcellular structures from a 3D transmitted-light image. Unfortunately, due to the limitations of current biotechnology, each image is partially labeled in SSP. Besides, naturally, the subcellular structures vary considerably in size, which causes the multi-scale issue in SSP. However, traditional solutions can not address SSP well since they organize network parameters inefficiently and inflexibly. To overcome these challenges, we propose Re-parameterizing Mixture-of-Diverse-Experts (RepMode), a network that dynamically organizes its parameters with task-aware priors to handle specified single-label prediction tasks of SSP. In RepMode, the Mixture-of-Diverse-Experts (MoDE) block is designed to learn the generalized parameters for all tasks, and gating re-parameterization (GatRep) is performed to generate the specialized parameters for each task, by which RepMode can maintain a compact practical topology exactly like a plain network, and meanwhile achieves a powerful theoretical topology. Comprehensive experiments show that RepMode outperforms existing methods on ten of twelve prediction tasks of SSP and achieves state-of-the-art overall performance.

Neural Radiance Fields (NeRF) methods have proved effective as compact, high-quality and versatile representations for 3D scenes, and enable downstream tasks such as editing, retrieval, navigation, etc. Various neural architectures are vying for the core structure of NeRF, including the plain Multi-Layer Perceptron (MLP), sparse tensors, low-rank tensors, hashtables and their compositions. Each of these representations has its particular set of trade-offs. For example, the hashtable-based representations admit faster training and rendering but their lack of clear geometric meaning hampers downstream tasks like spatial-relation-aware editing. In this paper, we propose Progressive Volume Distillation (PVD), a systematic distillation method that allows any-to-any conversions between different architectures, including MLP, sparse or low-rank tensors, hashtables and their compositions. PVD consequently empowers downstream applications to optimally adapt the neural representations for the task at hand in a post hoc fashion. The conversions are fast, as distillation is progressively performed on different levels of volume representations, from shallower to deeper. We also employ special treatment of density to deal with its specific numerical instability problem. Empirical evidence is presented to validate our method on the NeRF-Synthetic, LLFF and TanksAndTemples datasets. For example, with PVD, an MLP-based NeRF model can be distilled from a hashtable-based Instant-NGP model at a 10X~20X faster speed than being trained the original NeRF from scratch, while achieving a superior level of synthesis quality. Code is available at https://github.com/megvii-research/AAAI2023-PVD.

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

RGB热点对象检测（SOD）结合了两个光谱，以分段图像中的视觉明显区域。大多数现有方法都使用边界图来学习锋利的边界。这些方法忽略了孤立的边界像素与其他自信像素之间的相互作用，从而导致了次优性能。为了解决这个问题，我们为基于SWIN Transformer的RGB-T SOD提出了一个职位感知关系学习网络（PRLNET）。 PRLNET探索像素之间的距离和方向关系，以增强阶层内的紧凑性和类间的分离，从而产生具有清晰边界和均匀区域的显着对象掩模。具体而言，我们开发了一个新颖的签名距离辅助模块（SDMAM）来改善编码器特征表示，该模块考虑了边界邻域中不同像素的距离关系。然后，我们使用定向字段（FRDF）设计一种功能改进方法，该方法通过利用明显对象内部的功能来纠正边界邻域的特征。 FRDF利用对象像素之间的方向信息有效地增强了显着区域的阶层紧凑性。此外，我们构成了一个纯变压器编码器 - 模块网络，以增强RGB-T SOD的多光谱特征表示。最后，我们对三个公共基准数据集进行了定量和定性实验。结果表明，我们所提出的方法的表现优于最新方法。

图神经网络（GNN）在图形分类和多样化的下游现实世界应用方面取得了巨大成功。尽管他们成功了，但现有的方法要么仅限于结构攻击，要么仅限于本地信息。这要求在图形分类上建立更一般的攻击框架，由于使用全球图表级信息生成本地节点级的对抗示例的复杂性，因此面临重大挑战。为了解决这个“全局到本地”问题，我们提出了一个通用框架CAMA，以通过层次样式操纵图形结构和节点特征来生成对抗性示例。具体而言，我们利用Graph类激活映射及其变体来产​​生与图形分类任务相对应的节点级的重要性。然后，通过算法的启发式设计，我们可以借助节点级别和子图级的重要性在不明显的扰动预算下执行功能和结构攻击。在六个现实世界基准上攻击四个最先进的图形分类模型的实验验证了我们框架的灵活性和有效性。

斑马鱼是一种出色的模型生物，已在生物实验，药物筛查和群智能领域广泛使用。近年来，有许多用于跟踪行为研究涉及斑马鱼的技术，这使其攻击许多领域的科学家的注意力。斑马鱼的多目标跟踪仍然面临许多挑战。高流动性和不确定性使得难以预测其运动；相似的外观和纹理功能使建立外观模型变得困难。由于频繁的阻塞，甚至很难将轨迹连接起来。在本文中，我们使用粒子过滤器来近似运动的不确定性。首先，通过分析斑马鱼的运动特性，我们建立了一个有效的混合运动模型来预测其位置。然后，我们根据预测位置建立一个外观模型，以预测每个目标的姿势，同时通过比较预测的姿势和观察姿势的差来称量颗粒；最后，我们通过加权位置获得了单斑马鱼的最佳位置，并使用关节颗粒过滤器来处理多个斑马鱼的轨迹链接。

图像美学质量评估在过去十年中很受欢迎。除数值评估外，还提出了自然语言评估（美学字幕）来描述图像的一般美学印象。在本文中，我们提出了美学属性评估，即审美属性字幕，即评估诸如组成，照明使用和颜色布置之类的美学属性。标记美学属性的注释是一项非平凡的任务，该评论限制了相应数据集的规模。我们以半自动方式构建了一个名为DPC-CAPTIONSV2的新型数据集。知识从带有完整注释的小型数据集转移到摄影网站的大规模专业评论。 DPC-CAPTIONSV2的图像包含最多4个美学属性的注释：组成，照明，颜色和主题。然后，我们根据BUTD模型和VLPSA模型提出了一种新版本的美学多属性网络（AMANV2）。 AMANV2融合了带有完整注释的小规模PCCD数据集和带有完整注释的大规模DPCCAPTIONSV2数据集的混合物的功能。 DPCCAPTIONSV2的实验结果表明，我们的方法可以预测对4种美学属性的评论，这些评论比上一个Aman模型所产生的方法更接近美学主题。通过图像字幕的评估标准，专门设计的AMANV2模型对CNN-LSTM模型和AMAN模型更好。

由于难以收集详尽的多标签注释，因此多标签数据集通常包含部分标签。我们考虑了这个弱监督的学习问题的极端，称为单个积极的多标签学习（SPML），其中每个多标签训练图像只有一个正标签。传统上，所有未注释的标签都被认为是SPML中的负标签，它引入了假阴性标签，并导致模型训练被假定的负标签所支配。在这项工作中，我们选择从替代角度来对待所有未经注释的标签，即承认它们是未知的。因此，我们提出熵最大化（EM）损失，以达到提供适当监督信号的特殊梯度制度。此外，我们提出了采用不对称耐受性策略和自定进度程序的不对称伪标记（APL），以与EM损失合作，然后提供更精确的监督。实验表明，我们的方法可显着提高性能，并在所有四个基准测试中实现最先进的结果。代码可从https://github.com/correr-zhou/spml-acktheunknown获得。

Vision-Language（V + L）预先润廓模型通过了解图像和文本之间的对齐来支持多媒体应用程序取得了巨大成功。虽然现有的视觉预押模型主要专注于了解文本中的图像或实体中的对象，但它们通常会忽略事件级别的对齐及其参数结构。 ％在这项工作中，我们提出了一种对比的学习框架来强制执行愿景 - 语言预押模型来理解事件和相关参数（参与者）角色。为此，我们利用文本信息提取技术来获得事件结构知识，并利用多个提示函数来通过操纵事件结构来对比难度的负面描述。我们还基于最佳传输来设计事件图对齐损耗以捕获事件参数结构。此外，我们收集了一个大型活动的数据集（106,875张图片），用于预磨平，这提供了更具挑战性的图像检索基准，以评估对复杂冗长的句子的理解。实验表明，我们的零射剪辑事件优于在多媒体事件提取中的参数提取中的最先进的监督模型，从而实现了事件提取中的5±绝对f得分增益，以及显着改进零拍摄设置下的各种下游任务。