Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different degradation levels, which significantly restricts their practical deployments on resource-limited devices. In this paper, we propose a novel Dynamic Channel Splitting scheme for efficient Real-world Image Super-Resolution, termed DCS-RISR. Specifically, we first introduce the light degradation prediction network to regress the degradation vector to simulate the real-world degradations, upon which the channel splitting vector is generated as the input for an efficient SR model. Then, a learnable octave convolution block is proposed to adaptively decide the channel splitting scale for low- and high-frequency features at each block, reducing computation overhead and memory cost by offering the large scale to low-frequency features and the small scale to the high ones. To further improve the RISR performance, Non-local regularization is employed to supplement the knowledge of patches from LR and HR subspace with free-computation inference. Extensive experiments demonstrate the effectiveness of DCS-RISR on different benchmark datasets. Our DCS-RISR not only achieves the best trade-off between computation/parameter and PSNR/SSIM metric, and also effectively handles real-world images with different degradation levels.

The deep learning community has witnessed an exponentially growing interest in self-supervised learning (SSL). However, it still remains unexplored how to build a framework for learning useful representations of raw music waveforms in a self-supervised manner. In this work, we design Music2Vec, a framework exploring different SSL algorithmic components and tricks for music audio recordings. Our model achieves comparable results to the state-of-the-art (SOTA) music SSL model Jukebox, despite being significantly smaller with less than 2% of parameters of the latter. The model will be released on Huggingface(Please refer to: https://huggingface.co/m-a-p/music2vec-v1)

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. To facilitate GAN training, current methods propose to use data-specific augmentation techniques. Despite the effectiveness, it is difficult for these methods to scale to practical applications. In this work, we present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks. We first produce augmented samples using the convex combinations of the real samples. Then, we optimize the augmented samples by minimizing the norms of the data scores, i.e., the gradients of the log-density functions. This procedure enforces the augmented samples close to the data manifold. To estimate the scores, we train a deep estimation network with multi-scale score matching. For different image synthesis tasks, we train the score estimation network using different data. We do not require the tuning of the hyperparameters or modifications to the network architecture. The ScoreMix method effectively increases the diversity of data and reduces the overfitting problem. Moreover, it can be easily incorporated into existing GAN models with minor modifications. Experimental results on numerous tasks demonstrate that GAN models equipped with the ScoreMix method achieve significant improvements.

Multi-view graph clustering (MGC) methods are increasingly being studied due to the explosion of multi-view data with graph structural information. The critical point of MGC is to better utilize the view-specific and view-common information in features and graphs of multiple views. However, existing works have an inherent limitation that they are unable to concurrently utilize the consensus graph information across multiple graphs and the view-specific feature information. To address this issue, we propose Variational Graph Generator for Multi-View Graph Clustering (VGMGC). Specifically, a novel variational graph generator is proposed to extract common information among multiple graphs. This generator infers a reliable variational consensus graph based on a priori assumption over multiple graphs. Then a simple yet effective graph encoder in conjunction with the multi-view clustering objective is presented to learn the desired graph embeddings for clustering, which embeds the inferred view-common graph and view-specific graphs together with features. Finally, theoretical results illustrate the rationality of VGMGC by analyzing the uncertainty of the inferred consensus graph with information bottleneck principle. Extensive experiments demonstrate the superior performance of our VGMGC over SOTAs.

无监督的句子嵌入学习最近由对比度学习方法（例如SIMCSE）主导，该方法保持积极对相似，并将负面对拆开。对比操作旨在通过在积极实例之间最大化相互信息来保持尽可能多的信息，从而导致句子嵌入中的冗余信息。为了解决这个问题，我们提出了一个基于信息最小化的对比度学习（Informin-CL）模型，以保留有用的信息并通过最大化相互信息并最大程度地减少无监督句子表示学习的正面实例之间的信息熵，从而丢弃冗余信息。具体而言，我们发现信息最小化可以通过简单的对比度和重建目标来实现。重建操作通过另一个正实例重构积极实例，以最大程度地减少正实例之间的信息熵。我们在下游任务中评估了我们的模型，包括受监督和无监督的（语义文本相似性）任务。广泛的实验结果表明，我们的Informin-CL获得了最先进的性能。

尽管具有明显的区分靶向分布样本的能力，但深度神经网络在检测异常分布数据方面的性能差。为了解决此缺陷，最先进的解决方案选择在离群值的辅助数据集上训练深网。这些辅助离群值的各种培训标准是根据启发式直觉提出的。但是，我们发现这些直观设计的离群训练标准可能会损害分布学习，并最终导致劣等的表现。为此，我们确定了分布不兼容的三个原因：矛盾的梯度，错误的可能性和分布变化。基于我们的新理解，我们通过调整深层模型和损耗函数的顶级设计，提出一种新的分布检测方法。我们的方法通过减少对分布特征的概率特征的干扰来实现分布兼容性。在几个基准上，我们的方法不仅可以实现最新的分布检测性能，而且还提高了分布精度。

事件参数提取（EAE）的目的是从文本中提取具有给定角色的参数，这些参数已在自然语言处理中得到广泛研究。以前的大多数作品在具有专用神经体系结构的特定EAE数据集中取得了良好的性能。鉴于，这些架构通常很难适应具有各种注释模式或格式的新数据集/方案。此外，他们依靠大规模标记的数据进行培训，由于大多数情况下的标签成本高，因此无法获得培训。在本文中，我们提出了一个具有变异信息瓶颈的多格式转移学习模型，该模型利用了信息，尤其是新数据集中EAE现有数据集中的常识。具体而言，我们引入了一个共享特定的及时框架，以从具有不同格式的数据集中学习格式共享和格式特定的知识。为了进一步吸收EAE的常识并消除无关的噪音，我们将变异信息瓶颈整合到我们的体系结构中以完善共享表示。我们在三个基准数据集上进行了广泛的实验，并在EAE上获得新的最先进的性能。

本文介绍了Z-Code ++，这是一种针对抽象文本摘要优化的新的预训练的语言模型。该模型使用三种技术扩展了艺术编码器模型的状态。首先，我们使用两阶段的预训练过程来改善模型在低资源摘要任务上的性能。该模型首先是使用文本语料库进行语言理解的预先培训的，然后在汇总语料库中不断预先培训，以进行基础文本生成。其次，我们用分离的注意力层代替编码器中的自我发项层，其中每个单词都使用两个向量分别代表其内容和位置。第三，我们使用融合编码器，这是一种以层次方式编码长序列的简单而有效的方法。 Z-Code ++在13个文本摘要任务中的9个跨5种语言中创建了新的艺术状态。我们的模型的参数有效，因为它的表现优于XSUM上600倍较大的Palm-540b，并且在Samsum上的易经的200倍GPT3-175B较大。在零射击和少量设置中，我们的模型大大优于竞争模型。

单步反转合作是逆合合成计划的基石，这是计算机辅助药物发现的至关重要的任务。单步回合合成的目的是确定导致一个反应中靶产物合成的可能反应物。通过将有机分子表示为规范串，现有的基于序列的折叠方法将乘积 - 反应性逆合合成视为序列到序列翻译问题。但是，由于确定性推断，他们中的大多数人都难以识别所需产物的多种化学反应，这与以下事实相矛盾：许多化合物可以通过各种反应类型与不同的反应物组成。在这项工作中，我们旨在增加反应多样性并使用离散的潜在变量产生各种反应物。我们提出了一种基于序列的新方法，即RetrodVcae，该方法将条件变分自动化码器纳入单步回逆转录中，并将离散的潜在变量与生成过程相关联。具体而言，RetroDVCAE使用Gumbel-Softmax分布来近似于潜在反应的分类分布，并生成与变异解码器的多组反应物。实验表明，RetroDVCAE在基准数据集和自制数据集上的最先进基准均优于最先进的基线。定量和定性结果都表明，转化vcae可以在反应类型上对多模式分布进行建模，并产生各种反应物候选物。