Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has been widely studied recently. A typical EDNN has multiple prediction heads at different layers of the network backbone. During inference, the model will exit at either the last prediction head or an intermediate prediction head where the prediction confidence is higher than a predefined threshold. To optimize the model, these prediction heads together with the network backbone are trained on every batch of training data. This brings a train-test mismatch problem that all the prediction heads are optimized on all types of data in training phase while the deeper heads will only see difficult inputs in testing phase. Treating training and testing inputs differently at the two phases will cause the mismatch between training and testing data distributions. To mitigate this problem, we formulate an EDNN as an additive model inspired by gradient boosting, and propose multiple training techniques to optimize the model effectively. We name our method BoostNet. Our experiments show it achieves the state-of-the-art performance on CIFAR100 and ImageNet datasets in both anytime and budgeted-batch prediction modes. Our code is released at https://github.com/SHI-Labs/Boosted-Dynamic-Networks.

Universal Image Segmentation is not a new concept. Past attempts to unify image segmentation in the last decades include scene parsing, panoptic segmentation, and, more recently, new panoptic architectures. However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance. Ideally, a truly universal framework should be trained only once and achieve SOTA performance across all three image segmentation tasks. To that end, we propose OneFormer, a universal image segmentation framework that unifies segmentation with a multi-task train-once design. We first propose a task-conditioned joint training strategy that enables training on ground truths of each domain (semantic, instance, and panoptic segmentation) within a single multi-task training process. Secondly, we introduce a task token to condition our model on the task at hand, making our model task-dynamic to support multi-task training and inference. Thirdly, we propose using a query-text contrastive loss during training to establish better inter-task and inter-class distinctions. Notably, our single OneFormer model outperforms specialized Mask2Former models across all three segmentation tasks on ADE20k, CityScapes, and COCO, despite the latter being trained on each of the three tasks individually with three times the resources. With new ConvNeXt and DiNAT backbones, we observe even more performance improvement. We believe OneFormer is a significant step towards making image segmentation more universal and accessible. To support further research, we open-source our code and models at https://github.com/SHI-Labs/OneFormer

Image generation has been a long sought-after but challenging task, and performing the generation task in an efficient manner is similarly difficult. Often researchers attempt to create a "one size fits all" generator, where there are few differences in the parameter space for drastically different datasets. Herein, we present a new transformer-based framework, dubbed StyleNAT, targeting high-quality image generation with superior efficiency and flexibility. At the core of our model, is a carefully designed framework that partitions attention heads to capture local and global information, which is achieved through using Neighborhood Attention (NA). With different heads able to pay attention to varying receptive fields, the model is able to better combine this information, and adapt, in a highly flexible manner, to the data at hand. StyleNAT attains a new SOTA FID score on FFHQ-256 with 2.046, beating prior arts with convolutional models such as StyleGAN-XL and transformers such as HIT and StyleSwin, and a new transformer SOTA on FFHQ-1024 with an FID score of 4.174. These results show a 6.4% improvement on FFHQ-256 scores when compared to StyleGAN-XL with a 28% reduction in the number of parameters and 56% improvement in sampling throughput. Code and models will be open-sourced at https://github.com/SHI-Labs/StyleNAT .

Image completion with large-scale free-form missing regions is one of the most challenging tasks for the computer vision community. While researchers pursue better solutions, drawbacks such as pattern unawareness, blurry textures, and structure distortion remain noticeable, and thus leave space for improvement. To overcome these challenges, we propose a new StyleGAN-based image completion network, Spectral Hint GAN (SH-GAN), inside which a carefully designed spectral processing module, Spectral Hint Unit, is introduced. We also propose two novel 2D spectral processing strategies, Heterogeneous Filtering and Gaussian Split that well-fit modern deep learning models and may further be extended to other tasks. From our inclusive experiments, we demonstrate that our model can reach FID scores of 3.4134 and 7.0277 on the benchmark datasets FFHQ and Places2, and therefore outperforms prior works and reaches a new state-of-the-art. We also prove the effectiveness of our design via ablation studies, from which one may notice that the aforementioned challenges, i.e. pattern unawareness, blurry textures, and structure distortion, can be noticeably resolved. Our code will be open-sourced at: https://github.com/SHI-Labs/SH-GAN.

变形金刚迅速成为跨模式，域和任务的最深入学习架构之一。在视觉上，除了对普通变压器的持续努力外，层次变压器还引起了人们的重大关注，这要归功于它们的性能和轻松整合到现有框架中。这些模型通常采用局部注意机制，例如滑动窗口社区的注意力（NA）或Swin Transformer转移的窗户自我关注。尽管有效地降低了自我注意力的二次复杂性，但局部注意力却削弱了自我注意力最理想的两个特性：远距离相互依赖性建模和全球接受场。在本文中，我们引入了扩张的邻里注意力（DINA），这是NA的天然，灵活和有效的扩展，可以捕获更多的全球环境，并以无需额外的成本呈指数级扩展接受场。 NA的本地关注和Dina的稀疏全球关注相互补充，因此我们引入了扩张的邻里注意力变压器（Dinat），这是一种新的分层视觉变压器。 Dinat变体对基于注意的基线（例如NAT和SWIN）以及现代卷积基线Convnext都具有重大改进。我们的大型模型在可可对象检测中以1.5％的盒子AP领先于其在COCO物体检测中，1.3％的掩码AP在可可实例分段中，而ADE20K语义分段中的1.1％MIOU和更快的吞吐量。我们认为，NA和Dina的组合有可能增强本文提出的各种任务的能力。为了支持和鼓励朝着这个方向，远见和超越方向进行研究，我们在以下网址开放我们的项目：https：//github.com/shi-labs/neighborhood-cithention-transformer。

最近的研究表明，减少时间和空间冗余都是有效的视频识别方法的有效方法，例如，将大多数计算分配给与任务相关的框架或每个帧中最有价值的图像区域。但是，在大多数现有的作品中，任何一种类型的冗余通常都是用另一个缺失建模的。本文探讨了在最近提出的ADAFOCUSV2算法之上的时空动态计算的统一配方，从而有助于改进的ADAFOCUSV3框架。我们的方法仅在一些小但有益的3D视频立方体上激活昂贵的高容量网络来降低计算成本。这些立方体是从框架高度，宽度和视频持续时间形成的空间中裁剪的，而它们的位置则以每样本样本为基础的轻加权政策网络自适应地确定。在测试时间，与每个视频相对应的立方体的数量是动态配置的，即，对视频立方体进行顺序处理，直到产生足够可靠的预测为止。值得注意的是，可以通过近似可插入深度特征的插值来有效地训练adafocusv3。六个基准数据集（即ActivityNet，FCVID，Mini-Kinetics，Something Something V1＆V2和潜水48）上的广泛经验结果表明，我们的模型比竞争性基线要高得多。

视频效果旨在通过给定的输入视频序列预测每个帧的α哑光。在过去的几年中，深度卷积神经网络（CNN）的最新解决方案一直由深度卷积神经网络（CNN）主导，这已成为学术界和工业的事实上的标准。但是，它们具有内置的局部归纳性偏见，并且由于基于CNN的架构而不会捕获图像的全局特征。在处理多个帧的特征图时，考虑到计算成本，他们还缺乏远程时间建模。在本文中，我们提出了VMFormer：一种基于变压器的端对端方法，用于视频垫子。它可以通过视频输入序列从可学习的查询中对每个帧的α哑光进行预测。具体而言，它利用自我发挥的层来建立特征序列的全局集成，并在连续帧上使用短距离的时间建模。我们进一步应用查询来通过在所有查询上使用远程时间建模的变压器解码器中的交叉注意来学习全局表示形式。在预测阶段，查询和相应的特征图均用于对Alpha Matte的最终预测。实验表明，VMFormer在合成基准测试上的表现优于先前基于CNN的视频效果方法。据我们所知，这是第一个基于完整视觉变压器建立的端到端视频底漆解决方案，并对可学习的查询进行预测。该项目在https://chrisjuniorli.github.io/project/project/vmformer/上开源

深层图像介绍取得了令人印象深刻的进步，随着图像产生和处理算法的最新进展。我们声称，可以通过生成的结构和纹理更好地判断介入算法的性能。结构是指孔中生成的对象边界或新的几何结构，而纹理是指高频细节，尤其是在结构区域内填充的人造重复模式。我们认为，更好的结构通常是从基于粗糙的GAN的发电机网络中获得的，而如今重复模式可以通过最新的高频快速快速傅立叶卷积层进行更好的建模。在本文中，我们提出了一个新颖的介绍网络，结合了这两种设计的优势。因此，我们的模型具有出色的视觉质量，可以匹配结构生成和使用单个网络重复纹理合成的最新性能。广泛的实验证明了该方法的有效性，我们的结论进一步突出了图像覆盖质量，结构和纹理的两个关键因素，即未来的设计方向。

多年来，使用单点监督的对象检测受到了越来越多的关注。在本文中，我们将如此巨大的性能差距归因于产生高质量的提案袋的失败，这对于多个实例学习至关重要（MIL）。为了解决这个问题，我们引入了现成建议方法（OTSP）方法的轻量级替代方案，从而创建点对点网络（P2BNET），该网络可以通过在中生成建议袋来构建一个互平衡的提案袋一种锚点。通过充分研究准确的位置信息，P2BNET进一步构建了一个实例级袋，避免了多个物体的混合物。最后，以级联方式进行的粗到精细政策用于改善提案和地面真相（GT）之间的IOU。从这些策略中受益，P2BNET能够生产出高质量的实例级袋以进行对象检测。相对于MS可可数据集中的先前最佳PSOD方法，P2BNET将平均平均精度（AP）提高了50％以上。它还证明了弥合监督和边界盒监督检测器之间的性能差距的巨大潜力。该代码将在github.com/ucas-vg/p2bnet上发布。

尽管模型压缩和多任务学习的流行程度，但由于参数空间中任务的挑战性纠缠，如何有效地压缩多任务模型的分析程度不太彻底。在本文中，我们提出了一种简单，有效且首先的多任务修剪和稀疏培训计划。我们通过解开重要性测量值并在执行参数修剪和选择时独立考虑每个任务。我们的实验结果表明，与流行的稀疏训练和修剪方法相比，各种配置和设置的性能都出色。除了压缩的有效性外，Disparse还为多任务学习社区提供了强大的工具。令人惊讶的是，尽管迪斯特尔斯（Disparse）实现了高模型的稀疏性，但在某些情况下，我们甚至观察到比某些专用的多任务学习方法更好的性能。我们分析了用拆卸生成的修剪口罩，并在训练开始之前就观察到了每个任务都标识的非常相似的稀疏网络体系结构。我们还观察到了一个“分水岭”层的存在，该层与任务相关性急剧下降，这意味着持续参数共享没有任何好处。我们的代码和模型将在以下网址提供：https：//github.com/shi-labs/disparse-multitask-model-compression。