网络体系结构搜索（NAS），尤其是可区分的体系结构搜索（DARTS）方法，已经显示出在特定感兴趣的特定数据集中学习出色的模型体系结构的强大力量。与使用固定的数据集相反，在这项工作中，我们关注NAS的不同但重要的方案：如何完善部署的网络模型体系结构，以增强其鲁棒性，并通过一些收集和错误分类的示例的指导来增强其鲁棒性，这些示例被某些降低了现实世界中的未知损坏具有特定的模式（例如噪声，模糊等）。为此，我们首先进行了一项实证研究，以验证模型体系结构绝对与腐败模式有关。令人惊讶的是，通过仅添加一些损坏和错误分类的示例（例如，$ 10^3 $示例）到清洁培训数据集（例如$ 5.0 \ times 10^4 $示例）中，我们可以完善模型体系结构并显着增强鲁棒性。为了使其更加实用，应仔细研究关键问题，即如何为有效的NAS指导选择适当的失败示例。然后，我们提出了一个新颖的核心失效指导飞镖，该飞镖嵌入了K-Center-Greedy算法的飞镖，以选择合适的损坏故障示例以完善模型体系结构。我们使用我们的方法在清洁和15个腐败上使用飞镖精制的DNN，并在四个特定的现实世界腐败的指导下进行了指导。与最先进的NAS以及基于数据启发的增强方法相比，我们的最终方法可以在损坏的数据集和原始清洁数据集上获得更高的精度。在某些腐败模式上，我们可以达到超过45％的绝对准确性提高。

基于图像的3D检测是自主驾驶感知系统的必不可少的组成部分。但是，它仍然受到不满意的表现，这是有限的培训数据的主要原因之一。不幸的是，在3D空间中注释对象是极度时间/资源消耗的，这使得很难任意扩展训练集。在这项工作中，我们专注于半监督的方式，并探索更便宜的替代方案（即伪标记）的可行性，以利用未标记的数据。为此，我们进行了广泛的实验，以研究伪标签是否可以在不同环境下为基线模型提供有效的监督。实验结果不仅证明了基于图像的3D检测的伪标记机制的有效性（例如，在单眼设置下，我们在没有铃铛和哨声的Kitti-3D测试集上实现了20.23 AP，用于中等水平，从6.03 AP），但还显示了几个有趣且值得注意的发现（例如，经过伪标签训练的模型的性能要比基于相同培训数据的地面真相注释训练的表现更好）。我们希望这项工作可以在半监督环境下为基于图像的3D检测社区提供见解。代码，伪标签和预培训模型将公开可用。

知识蒸馏（KD）在将学习表征从大型模型（教师）转移到小型模型（学生）方面表现出非常有希望的能力。但是，随着学生和教师之间的容量差距变得更大，现有的KD方法无法获得更好的结果。我们的工作表明，“先验知识”对KD至关重要，尤其是在应用大型老师时。特别是，我们提出了动态的先验知识（DPK），该知识将教师特征的一部分作为特征蒸馏之前的先验知识。这意味着我们的方法还将教师的功能视为“输入”，而不仅仅是``目标''。此外，我们根据特征差距动态调整训练阶段的先验知识比率，从而引导学生在适当的困难中。为了评估所提出的方法，我们对两个图像分类基准（即CIFAR100和Imagenet）和一个对象检测基准（即MS Coco）进行了广泛的实验。结果表明，在不同的设置下，我们方法在性能方面具有优势。更重要的是，我们的DPK使学生模型的表现与教师模型的表现呈正相关，这意味着我们可以通过应用更大的教师进一步提高学生的准确性。我们的代码将公开用于可重复性。

Efficient use of the space in an elevator is very necessary for a service robot, due to the need for reducing the amount of time caused by waiting for the next elevator. To provide a solution for this, we propose a hybrid approach that combines reinforcement learning (RL) with voice interaction for robot navigation in the scene of entering the elevator. RL provides robots with a high exploration ability to find a new clear path to enter the elevator compared to traditional navigation methods such as Optimal Reciprocal Collision Avoidance (ORCA). The proposed method allows the robot to take an active clear path action towards the elevator whilst a crowd of people stands at the entrance of the elevator wherein there are still lots of space. This is done by embedding a clear path action (voice prompt) into the RL framework, and the proposed navigation policy helps the robot to finish tasks efficiently and safely. Our model approach provides a great improvement in the success rate and reward of entering the elevator compared to state-of-the-art navigation policies without active clear path operation.

背景和目的：胃癌已经成为全球第五次常见的癌症，早期检测胃癌对于拯救生命至关重要。胃癌的组织病理学检查是诊断胃癌的金标准。然而，计算机辅助诊断技术是挑战，以评估由于公开胃组织病理学图像数据集的稀缺而评估。方法：在本文中，公布了一种贵族公共胃组织病理学子尺寸图像数据库（GashissdB）以识别分类器的性能。具体地，包括两种类型的数据：正常和异常，总共245,196个组织案例图像。为了证明图像分类领域的不同时期的方法在GashissdB上具有差异，我们选择各种分类器进行评估。选择七种古典机器学习分类器，三个卷积神经网络分类器和新颖的基于变压器的分类器进行测试，用于测试图像分类任务。结果：本研究采用传统机器学习和深入学习方法进行了广泛的实验，以证明不同时期的方法对GashissdB具有差异。传统的机器学习实现了86.08％的最佳精度率，最低仅为41.12％。深度学习的最佳准确性达到96.47％，最低为86.21％。分类器的精度率显着变化。结论：据我们所知，它是第一个公开的胃癌组织病理学数据集，包含大量的弱监督学习的图像。我们认为Gashissdb可以吸引研究人员来探索胃癌自动诊断的新算法，这可以帮助医生和临床环境中的患者。

Most existing text-video retrieval methods focus on cross-modal matching between the visual content of offline videos and textual query sentences. However, in real scenarios, online videos are frequently accompanied by relevant text information such as titles, tags, and even subtitles, which can be utilized to match textual queries. This inspires us to generate associated captions from offline videos to help with existing text-video retrieval methods. To do so, we propose to use the zero-shot video captioner with knowledge of pre-trained web-scale models (e.g., CLIP and GPT-2) to generate captions for offline videos without any training. Given the captions, one question naturally arises: what can auxiliary captions do for text-video retrieval? In this paper, we present a novel framework Cap4Video, which makes use of captions from three aspects: i) Input data: The video and captions can form new video-caption pairs as data augmentation for training. ii) Feature interaction: We perform feature interaction between video and caption to yield enhanced video representations. iii) Output score: The Query-Caption matching branch can be complementary to the original Query-Video matching branch for text-video retrieval. We conduct thorough ablation studies to demonstrate the effectiveness of our method. Without any post-processing, our Cap4Video achieves state-of-the-art performance on MSR-VTT (51.4%), VATEX (66.6%), MSVD (51.8%), and DiDeMo (52.0%).

Vision-language models (VLMs) that are pre-trained on large-scale image-text pairs have demonstrated impressive transferability on a wide range of visual tasks. Transferring knowledge from such powerful pre-trained VLMs is emerging as a promising direction for building effective video recognition models. However, the current exploration is still limited. In our opinion, the greatest charm of pre-trained vision-language models is to build a bridge between visual and textual domains. In this paper, we present a novel framework called BIKE which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We propose a Video Attribute Association mechanism which leverages the Video-to-Text knowledge to generate textual auxiliary attributes to complement video recognition. ii) We also present a Temporal Concept Spotting mechanism which uses the Text-to-Video expertise to capture temporal saliency in a parameter-free manner to yield enhanced video representation. The extensive studies on popular video datasets (ie, Kinetics-400 & 600, UCF-101, HMDB-51 and ActivityNet) show that our method achieves state-of-the-art performance in most recognition scenarios, eg, general, zero-shot, and few-shot video recognition. To the best of our knowledge, our best model achieves a state-of-the-art accuracy of 88.4% on challenging Kinetics-400 with the released CLIP pre-trained model.

We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering. Motivated by the fact that informative point cloud features should be able to encode rich geometry and appearance cues and render realistic images, we train a point-cloud encoder within a devised point-based neural renderer by comparing the rendered images with real images on massive RGB-D data. The learned point-cloud encoder can be easily integrated into various downstream tasks, including not only high-level tasks like 3D detection and segmentation, but low-level tasks like 3D reconstruction and image synthesis. Extensive experiments on various tasks demonstrate the superiority of our approach compared to existing pre-training methods.

Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains an open problem due to the data sparsity and scene complexity. The conventional random masking paradigm used in 2D images often causes a high risk of ambiguity when recovering the masked region of 3D scenes. To this end, we propose a novel informative-preserved reconstruction, which explores local statistics to discover and preserve the representative structured points, effectively enhancing the pretext masking task for 3D scene understanding. Integrated with a progressive reconstruction manner, our method can concentrate on modeling regional geometry and enjoy less ambiguity for masked reconstruction. Besides, such scenes with progressive masking ratios can also serve to self-distill their intrinsic spatial consistency, requiring to learn the consistent representations from unmasked areas. By elegantly combining informative-preserved reconstruction on masked areas and consistency self-distillation from unmasked areas, a unified framework called MM-3DScene is yielded. We conduct comprehensive experiments on a host of downstream tasks. The consistent improvement (e.g., +6.1 mAP@0.5 on object detection and +2.2% mIoU on semantic segmentation) demonstrates the superiority of our approach.

The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets. However, compared with 2D image datasets, the current pre-training data of 3D point cloud is limited. To overcome this limitation, we propose a knowledge distillation method for 3D point cloud pre-trained models to acquire knowledge directly from the 2D representation learning model, particularly the image encoder of CLIP, through concept alignment. Specifically, we introduce a cross-attention mechanism to extract concept features from 3D point cloud and compare them with the semantic information from 2D images. In this scheme, the point cloud pre-trained models learn directly from rich information contained in 2D teacher models. Extensive experiments demonstrate that the proposed knowledge distillation scheme achieves higher accuracy than the state-of-the-art 3D pre-training methods for synthetic and real-world datasets on downstream tasks, including object classification, object detection, semantic segmentation, and part segmentation.