可扩展的网络已经证明了它们在处理灾难性遗忘问题方面的优势。考虑到不同的任务可能需要不同的结构，最近的方法设计了通过复杂技能适应不同任务的动态结构。他们的例程是首先搜索可扩展的结构，然后训练新任务，但是，这将任务分为多个培训阶段，从而导致次优或过度计算成本。在本文中，我们提出了一个名为E2-AEN的端到端可训练的可自适应扩展网络，该网络动态生成了新任务的轻量级结构，而没有任何精确的先前任务下降。具体而言，该网络包含一个功能强大的功能适配器的序列，用于扩大以前学习的表示新任务的表示形式，并避免任务干扰。这些适配器是通过基于自适应门的修剪策略来控制的，该策略决定是否可以修剪扩展的结构，从而根据新任务的复杂性动态地改变网络结构。此外，我们引入了一种新颖的稀疏激活正则化，以鼓励模型学习具有有限参数的区分特征。 E2-aen可以降低成本，并且可以以端到端的方式建立在任何饲喂前架构上。关于分类（即CIFAR和VDD）和检测（即可可，VOC和ICCV2021 SSLAD挑战）的广泛实验证明了提出的方法的有效性，从而实现了新的出色结果。

最近，由于其广泛的商业价值，从视觉丰富的文档（例如门票和简历）中自动提取信息已成为一个热门而重要的研究主题。大多数现有方法将此任务分为两个小节：用于从原始文档图像中获取纯文本的文本阅读部分以及用于提取密钥内容的信息提取部分。这些方法主要集中于改进第二个方法，同时忽略了这两个部分高度相关。本文提出了一个统一的端到端信息提取框架，从视觉上富含文档中提出，文本阅读和信息提取可以通过精心设计的多模式上下文块相互加强。具体而言，文本阅读部分提供了多模式功能，例如视觉，文本和布局功能。开发了多模式上下文块，以融合生成的多模式特征，甚至是从预训练的语言模型中获得的先验知识，以提供更好的语义表示。信息提取部分负责使用融合上下文功能生成密钥内容。该框架可以以端到端的可训练方式进行培训，从而实现全球优化。更重要的是，我们将视觉丰富的文档定义为跨两个维度的四个类别，即布局和文本类型。对于每个文档类别，我们提供或推荐相应的基准，实验设置和强大的基准，以弥补该研究领域缺乏统一评估标准的问题。报告了对四种基准测试的广泛实验（从固定布局到可变布局，从完整的文本到半未结构化的文本），证明了所提出的方法的有效性。数据，源代码和模型可用。

本文介绍了Davarocr，这是一种用于OCR和文档理解任务的开源工具箱。Davarocr目前实施19种高级算法，涵盖9个不同的任务表。Davarocr为每种算法提供了详细的用法说明和经过训练的模型。与以前的OpenSource OCR工具箱相比，Davarocr对文档理解的尖端技术的子任务具有相对完整的支持。为了促进OCR技术在学术界和行业中的开发和应用，我们更加关注使用不同的技术可以共享的模块的使用。Davarocr在https://github.com/hikopensource/davar-lab-ocr上公开发行。

端到端的文本发现最近由于其对全球优化的好处和对实际应用的高可维护性而引起了极大的关注。但是，输入量表一直是一个艰难的权衡，因为认识到一个小的文本实例通常需要扩大整个图像，从而带来了高度的计算成本。在本文中，为了解决这个问题，我们提出了一种新颖的成本效益动态低分辨率蒸馏（DLD）文本斑点框架，该框架旨在推断出不同的小但可识别的分辨率中的图像，并在准确性和效率之间取得更好的平衡。具体而言，我们采用一个分辨率选择器来动态地确定不同图像的输入分辨率，这是通过推理准确性和计算成本来限制的。在文本识别分支上进行了另一种顺序知识蒸馏策略，使低分辨率输入获得与高分辨率图像相当的性能。可以在任何当前文本斑点框架中采用提出的方法，并在任何文本斑点框架中采用以提高可实用性。对几个文本斑点基准测试的广泛实验表明，所提出的方法极大地提高了低分辨率模型的可用性。该代码可从https://github.com/hikopensource/davar-lab-ocr/获得。

在持续学习的SSLAD-TRACK 3B挑战中，我们提出了与变压器（COLT）继续学习的方法。与卷积神经网络相比，我们发现变压器遭受灾难性遗忘的损失。我们方法的主要原则是用旧知识蒸馏和头部扩展策略装备基于变压器的特征提取器来竞争灾难性的遗忘。在本报告中，我们首先介绍了对象检测的持续学习的整体框架。然后，我们分析了解决我们解决方案中灾难性遗址的关键要素对效果。我们的方法在SSLAD-TRACK 3B挑战测试集上实现70.78映射。

少量学习（FSL）旨在学习概括到具有有限培训样本的小型课程的模型。最近的作品将FSL推进一个场景，其中还提供了未标记的例子并提出半监督FSL方法。另一种方法还关心基类的性能，除了新颖的外，还建立了增量FSL方案。在本文中，我们在更现实但复杂的环境下概括了上述两个，通过半监督增量少量学习（S2 I-FSL）命名。为了解决任务，我们提出了一种包含两部分的新型范例：（1）一种精心设计的元训练算法，用于减轻由不可靠的伪标签和（2）模型适应机制来减轻基础和新颖类之间的模糊性，以学习歧视特征对于小说类，同时使用少数标记和所有未标记的数据保留基本知识。对标准FSL，半监控FSL，增量FSL的广泛实验，以及第一个构建的S2 I-FSL基准测试证明了我们提出的方法的有效性。

Panoptic Part Segmentation (PPS) unifies panoptic segmentation and part segmentation into one task. Previous works utilize separated approaches to handle thing, stuff, and part predictions without shared computation and task association. We aim to unify these tasks at the architectural level, designing the first end-to-end unified framework named Panoptic-PartFormer. Moreover, we find the previous metric PartPQ biases to PQ. To handle both issues, we make the following contributions: Firstly, we design a meta-architecture that decouples part feature and things/stuff feature, respectively. We model things, stuff, and parts as object queries and directly learn to optimize all three forms of prediction as a unified mask prediction and classification problem. We term our model as Panoptic-PartFormer. Secondly, we propose a new metric Part-Whole Quality (PWQ) to better measure such task from both pixel-region and part-whole perspectives. It can also decouple the error for part segmentation and panoptic segmentation. Thirdly, inspired by Mask2Former, based on our meta-architecture, we propose Panoptic-PartFormer++ and design a new part-whole cross attention scheme to further boost part segmentation qualities. We design a new part-whole interaction method using masked cross attention. Finally, the extensive ablation studies and analysis demonstrate the effectiveness of both Panoptic-PartFormer and Panoptic-PartFormer++. Compared with previous Panoptic-PartFormer, our Panoptic-PartFormer++ achieves 2% PartPQ and 3% PWQ improvements on the Cityscapes PPS dataset and 5% PartPQ on the Pascal Context PPS dataset. On both datasets, Panoptic-PartFormer++ achieves new state-of-the-art results with a significant cost drop of 70% on GFlops and 50% on parameters. Our models can serve as a strong baseline and aid future research in PPS. Code will be available.

Rankings are widely collected in various real-life scenarios, leading to the leakage of personal information such as users' preferences on videos or news. To protect rankings, existing works mainly develop privacy protection on a single ranking within a set of ranking or pairwise comparisons of a ranking under the $\epsilon$-differential privacy. This paper proposes a novel notion called $\epsilon$-ranking differential privacy for protecting ranks. We establish the connection between the Mallows model (Mallows, 1957) and the proposed $\epsilon$-ranking differential privacy. This allows us to develop a multistage ranking algorithm to generate synthetic rankings while satisfying the developed $\epsilon$-ranking differential privacy. Theoretical results regarding the utility of synthetic rankings in the downstream tasks, including the inference attack and the personalized ranking tasks, are established. For the inference attack, we quantify how $\epsilon$ affects the estimation of the true ranking based on synthetic rankings. For the personalized ranking task, we consider varying privacy preferences among users and quantify how their privacy preferences affect the consistency in estimating the optimal ranking function. Extensive numerical experiments are carried out to verify the theoretical results and demonstrate the effectiveness of the proposed synthetic ranking algorithm.

In this work, we focus on instance-level open vocabulary segmentation, intending to expand a segmenter for instance-wise novel categories without mask annotations. We investigate a simple yet effective framework with the help of image captions, focusing on exploiting thousands of object nouns in captions to discover instances of novel classes. Rather than adopting pretrained caption models or using massive caption datasets with complex pipelines, we propose an end-to-end solution from two aspects: caption grounding and caption generation. In particular, we devise a joint Caption Grounding and Generation (CGG) framework based on a Mask Transformer baseline. The framework has a novel grounding loss that performs explicit and implicit multi-modal feature alignments. We further design a lightweight caption generation head to allow for additional caption supervision. We find that grounding and generation complement each other, significantly enhancing the segmentation performance for novel categories. We conduct extensive experiments on the COCO dataset with two settings: Open Vocabulary Instance Segmentation (OVIS) and Open Set Panoptic Segmentation (OSPS). The results demonstrate the superiority of our CGG framework over previous OVIS methods, achieving a large improvement of 6.8% mAP on novel classes without extra caption data. Our method also achieves over 15% PQ improvements for novel classes on the OSPS benchmark under various settings.

Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets.