The mainstream of the existing approaches for video prediction builds up their models based on a Single-In-Single-Out (SISO) architecture, which takes the current frame as input to predict the next frame in a recursive manner. This way often leads to severe performance degradation when they try to extrapolate a longer period of future, thus limiting the practical use of the prediction model. Alternatively, a Multi-In-Multi-Out (MIMO) architecture that outputs all the future frames at one shot naturally breaks the recursive manner and therefore prevents error accumulation. However, only a few MIMO models for video prediction are proposed and they only achieve inferior performance due to the date. The real strength of the MIMO model in this area is not well noticed and is largely under-explored. Motivated by that, we conduct a comprehensive investigation in this paper to thoroughly exploit how far a simple MIMO architecture can go. Surprisingly, our empirical studies reveal that a simple MIMO model can outperform the state-of-the-art work with a large margin much more than expected, especially in dealing with longterm error accumulation. After exploring a number of ways and designs, we propose a new MIMO architecture based on extending the pure Transformer with local spatio-temporal blocks and a new multi-output decoder, namely MIMO-VP, to establish a new standard in video prediction. We evaluate our model in four highly competitive benchmarks (Moving MNIST, Human3.6M, Weather, KITTI). Extensive experiments show that our model wins 1st place on all the benchmarks with remarkable performance gains and surpasses the best SISO model in all aspects including efficiency, quantity, and quality. We believe our model can serve as a new baseline to facilitate the future research of video prediction tasks. The code will be released.

工业推荐系统通常提出包含来自多个子系统的结果的混合列表。实际上，每个子系统都使用自己的反馈数据进行了优化，以避免不同子系统之间的干扰。但是，我们认为，由于\ textit {数据稀疏}，此类数据使用可能会导致次优的在线性能。为了减轻此问题，我们建议从包含网络尺度和长期印象数据的\ textit {super-domain}中提取知识，并进一步协助在线推荐任务（下游任务）。为此，我们提出了一个新颖的工业\ textbf {k} nowl \ textbf {e} dge \ textbf {e} xtraction和\ textbf {p} lugging（\ textbf {keep}）框架，这是一个两阶段的框架其中包括1）超级域上有监督的预训练知识提取模块，以及2）将提取的知识纳入下游模型的插件网络。这使得对在线推荐的逐步培训变得友好。此外，我们设计了一种有效的经验方法，用于在大规模工业系统中实施Keep时保持和介绍我们的动手经验。在两个现实世界数据集上进行的实验表明，保持可以实现有希望的结果。值得注意的是，Keep也已部署在阿里巴巴的展示广告系统上，带来了$+5.4 \％$ CTR和$+4.7 \％\％$ rpm的提升。

尽管发展了排名优化技术，但点式模型仍然是点击率（CTR）预测的主导方法。它可以归因于点式模型的校准能力，因为可以将预测视为点击概率。在实践中，通常还以排名能力来评估CTR预测模型，基于排名损失（例如，成对或列表损失）的预测模型通常比点置损失更好。先前的研究已经实验了两种损失的直接组合，以从损失中获得收益并观察到改善的性能。但是，先前的研究将输出logit的含义作为点击率，这可能会导致次优的解决方案。为了解决这个问题，我们提出了一种可以共同优化排名和校准能力的方法（简称JRC）。 JRC通过将样品的logit值与不同的标签进行对比，并约束预测概率是logit减法的函数，从而提高了排名能力。我们进一步表明JRC巩固了对逻辑的解释，其中逻辑在其中建模关节分布。通过这样的解释，我们证明JRC近似优化了上下文化的混合歧视生成目标。公共和工业数据集以及在线A/B测试的实验表明，我们的方法提高了排名和校准能力。自2022年5月以来，JRC已被部署在阿里巴巴的展示广告平台上，并获得了显着改进的绩效。

我们提出了一个新的框架，以重建整体3D室内场景，包括单视图像的房间背景和室内对象。由于室内场景的严重阻塞，现有方法只能产生具有有限几何质量的室内物体的3D形状。为了解决这个问题，我们提出了一个与实例一致的隐式函数（InstPifu），以进行详细的对象重建。与实例对齐的注意模块结合使用，我们的方法有权将混合的局部特征与遮挡实例相结合。此外，与以前的方法不同，该方法仅代表房间背景为3D边界框，深度图或一组平面，我们通过隐式表示恢复了背景的精细几何形状。在E SUN RGB-D，PIX3D，3D-FUTURE和3D-FRONT数据集上进行的广泛实验表明，我们的方法在背景和前景对象重建中均优于现有方法。我们的代码和模型将公开可用。

半监督域的适应性（SSDA）旨在将从完全标记的源域学习的知识应用于几乎没有标记的目标域。在本文中，我们为SSDA提出了一个多级一致性学习（MCL）框架。具体而言，我们的MCL将目标域样本的不同视图的一致性定于三个级别：（i）在域间级别，我们使用基于原型的最佳传输方法来稳健，准确地对齐源和目标域，该方法利用了PROS和PROS和PROS域目标样本不同观点的缺点； （ii）在域内层面上，我们通过提出新颖的班级对比聚类损失来促进歧视性和紧凑的目标特征表示。 （iii）在样本级别，我们遵循标准实践，并通过进行基于一致性的自我训练来提高预测准确性。从经验上，我们验证了MCL框架对三个流行的SSDA基准的有效性，即Visda2017，域名和办公室家庭数据集，实验结果表明我们的MCL框架可以实现最新的性能。

点云的语义分割通常依赖于累累且昂贵的致密注释，因此它吸引了广泛的关注，以研究弱监督方案的解决方案，仅稀疏点注释。现有作品从给定的标签开始，并将其传播到高度相关但无标记的点，例如数据的指导，例如内部关系。但是，它遭受了（i）对数据信息的效率低下的利用，并且（ii）在给出更少的注释时，很容易抑制对标签的强烈依赖。因此，我们提出了一个新颖的框架，即DimpMatch，它通过将一致性正则化应用于数据本身的足够探测信息，并同时利用弱标签作为帮助，该框架具有数据和标签。通过这样做，可以从数据和标签中学习有意义的信息，以获得更好的表示，这也使模型可以在标签稀疏度的范围内更强大。简单而有效的是，提议的尖头竞赛在Scannet-V2和S3DIS数据集上都在各种弱监督的方案下实现了最先进的性能，尤其是在具有极为稀疏标签的设置上，例如。在0.01％和0.1％的扫描仪V2设置上，SQN超过21.2％和17.2％。

如今，数据驱动的深度神经模式已经在点击率（CTR）预测上已经显示出显着的进展。不幸的是，当数据不足时，这种模型的有效性可能会失败。为了处理这个问题，研究人员经常采用勘探战略来审查基于估计奖励的项目，例如UCB或汤普森采样。在CTR预测的开发和探索的背景下，最近的研究已经尝试利用预测不确定性以及模型预测作为奖励得分。但是，我们认为这种方法可以使最终排名分数偏离原始分布，从而影响在线系统中的模型性能。在本文中，我们提出了一种名为\ textbf {a} dversarial \ textbf {g} vlient driven \ textbf {e} xploration（年龄）的新颖探索方法。具体地，我们提出了一个伪探索模块来模拟渐变更新过程，其可以近似模型的探索项目的样本的影响。此外，为了更好的探索效率，我们提出了一种动态阈值单元，以消除具有低电位CTR的样本的效果。在开放式学术数据集上证明了我们方法的有效性。同时，年龄也部署在现实世界展示广告平台中，所有在线指标都得到了显着改善。

Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token- and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViT-base models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.

Few Shot Instance Segmentation (FSIS) requires models to detect and segment novel classes with limited several support examples. In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework. Our key insights are two folds: Firstly, with the aid of support masks, we can generate dynamic class centers more appropriately to re-weight query features. Secondly, we find that support object queries have already encoded key factors after base training. In this way, the query features can be enhanced twice from two aspects, i.e., feature-level and instance-level. In particular, we firstly design a mask-based dynamic weighting module to enhance support features and then propose to link object queries for better calibration via cross-attention. After the above steps, the novel classes can be improved significantly over our strong baseline. Additionally, our new framework can be easily extended to incremental FSIS with minor modification. When benchmarking results on the COCO dataset for FSIS, gFSIS, and iFSIS settings, our method achieves a competitive performance compared to existing approaches across different shots, e.g., we boost nAP by noticeable +8.2/+9.4 over the current state-of-the-art FSIS method for 10/30-shot. We further demonstrate the superiority of our approach on Few Shot Object Detection. Code and model will be available.

When using LiDAR semantic segmentation models for safety-critical applications such as autonomous driving, it is essential to understand and improve their robustness with respect to a large range of LiDAR corruptions. In this paper, we aim to comprehensively analyze the robustness of LiDAR semantic segmentation models under various corruptions. To rigorously evaluate the robustness and generalizability of current approaches, we propose a new benchmark called SemanticKITTI-C, which features 16 out-of-domain LiDAR corruptions in three groups, namely adverse weather, measurement noise and cross-device discrepancy. Then, we systematically investigate 11 LiDAR semantic segmentation models, especially spanning different input representations (e.g., point clouds, voxels, projected images, and etc.), network architectures and training schemes. Through this study, we obtain two insights: 1) We find out that the input representation plays a crucial role in robustness. Specifically, under specific corruptions, different representations perform variously. 2) Although state-of-the-art methods on LiDAR semantic segmentation achieve promising results on clean data, they are less robust when dealing with noisy data. Finally, based on the above observations, we design a robust LiDAR segmentation model (RLSeg) which greatly boosts the robustness with simple but effective modifications. It is promising that our benchmark, comprehensive analysis, and observations can boost future research in robust LiDAR semantic segmentation for safety-critical applications.