We present a method that accelerates reconstruction of 3D scenes and objects, aiming to enable instant reconstruction on edge devices such as mobile phones and AR/VR headsets. While recent works have accelerated scene reconstruction training to minute/second-level on high-end GPUs, there is still a large gap to the goal of instant training on edge devices which is yet highly desired in many emerging applications such as immersive AR/VR. To this end, this work aims to further accelerate training by leveraging geometry priors of the target scene. Our method proposes strategies to alleviate the noise of the imperfect geometry priors to accelerate the training speed on top of the highly optimized Instant-NGP. On the NeRF Synthetic dataset, our work uses half of the training iterations to reach an average test PSNR of >30.

使用自然语言作为培训视觉识别模型的监督持有巨大的承诺。最近的作品表明，如果在大型训练数据集中的图像和标题之间的对齐形式使用此类监督，则结果对齐模型在零拍摄分类中表现出色，如下游任务2。在本文中，我们专注于挑逗语言监督的哪些部分对于训练零拍摄图像分类模型至关重要。通过广泛和仔细的实验​​，我们表明：1）可以将简单的单词（弓）标题用作数据集中大多数图像标题的替代品。令人惊讶的是，我们观察到这种方法在与单词平衡结合时提高了零拍分类性能。 2）使用船首净化模型，我们可以通过在没有标题的图像上生成伪弓标题来获得更多培训数据。使用真实和伪弓形标题培训的模型达到了更强的零射性能。在ImageNet-1K零拍评估中，我们只使用3M图像标题对的最佳模型，使用15M图像标题对培训的剪辑模型（31.5％VS 31.3％）进行剪辑。

传统的计算机视觉模型受过培训，以预测固定的预定义类别。最近，自然语言已被证明是一个更广泛而更丰富的监督来源，为视觉概念提供更精细的描述，而不是监督“黄金”标签。以前的作品，例如剪辑，使用InfoNce丢失来训练模型以预测图像和文本标题之间的配对。然而，剪辑是饥饿的数据，需要超过400米的图像文本对进行培训。效率低下可以归因于图像文本对嘈杂的事实。为了解决这个问题，我们提出了水獭（有效的零射击识别的最佳运输蒸馏），它使用在线熵最佳运输，找到一个软图像文本与标签进行对比学习。基于预磨料的图像和文本编码器，用电站培训的型号实现了强大的性能，只有3M图像文本对。与InfoNce损失相比，标记平滑和知识蒸馏，OTTER始终如一地优于零拍摄图像（19,958类）和来自腾讯ML图像的多标记Imagenet 10k（10032类）的零拍摄评估中的这些基线。在4个不同的数据集/架构设置x 6度量上，OTTER优于（32）或绑定（2）34中的所有基准。

我们解决对象检测中的域适应问题，其中在源（带有监控）和目标域（没有监督的域的域名）之间存在显着的域移位。作为广泛采用的域适应方法，自培训教师学生框架（学生模型从教师模型生成的伪标签学习）在目标域中产生了显着的精度增益。然而，由于其偏向源域，它仍然存在从教师产生的大量低质量伪标签（例如，误报）。为了解决这个问题，我们提出了一种叫做自适应无偏见教师（AUT）的自我训练框架，利用对抗的对抗学习和弱强的数据增强来解决域名。具体而言，我们在学生模型中使用特征级的对抗性培训，确保从源和目标域中提取的功能共享类似的统计数据。这使学生模型能够捕获域不变的功能。此外，我们在目标领域的教师模型和两个域上的学生模型之间应用了弱强的增强和相互学习。这使得教师模型能够从学生模型中逐渐受益，而不会遭受域移位。我们展示了AUT通过大边距显示所有现有方法甚至Oracle（完全监督）模型的优势。例如，我们在有雾的城市景观（Clipart1k）上实现了50.9％（49.3％）地图，分别比以前的最先进和甲骨文高9.2％（5.2％）和8.2％（11.0％）

神经结构搜索（NAS）已被广泛采用设计准确，高效的图像分类模型。但是，将NAS应用于新的计算机愿景任务仍然需要大量的努力。这是因为1）以前的NAS研究已经过度优先考虑图像分类，同时在很大程度上忽略了其他任务; 2）许多NAS工作侧重于优化特定于任务特定的组件，这些组件不能有利地转移到其他任务; 3）现有的NAS方法通常被设计为“Proxyless”，需要大量努力与每个新任务的培训管道集成。为了解决这些挑战，我们提出了FBNetv5，这是一个NAS框架，可以在各种视觉任务中寻找神经架构，以降低计算成本和人力努力。具体而言，我们设计1）一个简单但包容性和可转换的搜索空间; 2）用目标任务培训管道解开的多址搜索过程; 3）一种算法，用于同时搜索具有计算成本不可知的多个任务的架构到任务数。我们评估所提出的FBNetv5目标三个基本视觉任务 - 图像分类，对象检测和语义分割。 FBNETV5在单一搜索中搜索的模型在所有三个任务中都表现优于先前的议定书 - 现有技术：图像分类（例如，与FBNetv3相比，在与FBNetv3相比的同一拖鞋下的1 + 1.3％Imageet Top-1精度。 （例如，+ 1.8％较高的Ade20k Val。Miou比SegFormer为3.6倍的拖鞋），对象检测（例如，+ 1.1％Coco Val。与yolox相比，拖鞋的1.2倍的地图。

Designing accurate and efficient ConvNets for mobile devices is challenging because the design space is combinatorially large. Due to this, previous neural architecture search (NAS) methods are computationally expensive. ConvNet architecture optimality depends on factors such as input resolution and target devices. However, existing approaches are too resource demanding for case-by-case redesigns. Also, previous work focuses primarily on reducing FLOPs, but FLOP count does not always reflect actual latency. To address these, we propose a differentiable neural architecture search (DNAS) framework that uses gradient-based methods to optimize Con-vNet architectures, avoiding enumerating and training individual architectures separately as in previous methods. FBNets (Facebook-Berkeley-Nets), a family of models discovered by DNAS surpass state-of-the-art models both designed manually and generated automatically. FBNet-B achieves 74.1% top-1 accuracy on ImageNet with 295M FLOPs and 23.1 ms latency on a Samsung S8 phone, 2.4x smaller and 1.5x faster than MobileNetV2-1.3[17] with similar accuracy. Despite higher accuracy and lower latency than MnasNet[20], we estimate FBNet-B's search cost is 420x smaller than MnasNet's, at only 216 GPUhours. Searched for different resolutions and channel sizes, FBNets achieve 1.5% to 6.4% higher accuracy than Mo-bileNetV2. The smallest FBNet achieves 50.2% accuracy and 2.9 ms latency (345 frames per second) on a Samsung S8. Over a Samsung-optimized FBNet, the iPhone-Xoptimized model achieves a 1.4x speedup on an iPhone X. FBNet models are open-sourced at https://github. com/facebookresearch/mobile-vision. * Work done while interning at Facebook.… Figure 1. Differentiable neural architecture search (DNAS) for ConvNet design. DNAS explores a layer-wise space that each layer of a ConvNet can choose a different block. The search space is represented by a stochastic super net. The search process trains the stochastic super net using SGD to optimize the architecture distribution. Optimal architectures are sampled from the trained distribution. The latency of each operator is measured on target devices and used to compute the loss for the super net.

In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds. In particular, we wish to detect and categorize instances of interest, such as cars, pedestrians and cyclists. We formulate this problem as a pointwise classification problem, and propose an end-to-end pipeline called SqueezeSeg based on convolutional neural networks (CNN): the CNN takes a transformed LiDAR point cloud as input and directly outputs a point-wise label map, which is then refined by a conditional random field (CRF) implemented as a recurrent layer. Instance-level labels are then obtained by conventional clustering algorithms. Our CNN model is trained on LiDAR point clouds from the KITTI [1] dataset, and our point-wise segmentation labels are derived from 3D bounding boxes from KITTI. To obtain extra training data, we built a LiDAR simulator into Grand Theft Auto V (GTA-V), a popular video game, to synthesize large amounts of realistic training data. Our experiments show that SqueezeSeg achieves high accuracy with astonishingly fast and stable runtime (8.7 ± 0.5 ms per frame), highly desirable for autonomous driving applications. Furthermore, additionally training on synthesized data boosts validation accuracy on real-world data. Our source code and synthesized data will be open-sourced.

A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard. Code will be available at https://github.com/dvlab-research/Imbalanced-Learning.

Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.

Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit, and mitigate the sample inefficiency problem for visuomotor driving. Given the highly dynamic and variant nature of the input, the visuomotor driving task inherently lacks view and translation invariance, and the visual input contains massive irrelevant information for decision making, resulting in predominant pre-training approaches from general vision less suitable for the autonomous driving task. To this end, we propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. The proposed PPGeo is performed in two stages to support effective self-supervised training. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only. As such, the pre-trained visual encoder is equipped with rich driving policy related representations and thereby competent for multiple visuomotor driving tasks. Extensive experiments covering a wide span of challenging scenarios have demonstrated the superiority of our proposed approach, where improvements range from 2% to even over 100% with very limited data. Code and models will be available at https://github.com/OpenDriveLab/PPGeo.