Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although tremendous efforts have been made to recall precise and complete locations for each class, existing methods still commonly suffer from the unsolicited Out-of-Candidate (OC) error predictions that not belongs to the label candidates, which could be avoidable since the contradiction with image-level class tags is easy to be detected. In this paper, we develop a group ranking-based Out-of-Candidate Rectification (OCR) mechanism in a plug-and-play fashion. Firstly, we adaptively split the semantic categories into In-Candidate (IC) and OC groups for each OC pixel according to their prior annotation correlation and posterior prediction correlation. Then, we derive a differentiable rectification loss to force OC pixels to shift to the IC group. Incorporating our OCR with seminal baselines (e.g., AffinityNet, SEAM, MCTformer), we can achieve remarkable performance gains on both Pascal VOC (+3.2%, +3.3%, +0.8% mIoU) and MS COCO (+1.0%, +1.3%, +0.5% mIoU) datasets with negligible extra training overhead, which justifies the effectiveness and generality of our OCR.
translated by 谷歌翻译
在自主驾驶的复杂情况下,培训多个代理商以进行安全和合作的控制是一个挑战。对于一小群汽车,本文提出了麻木,这是一种培训多个代理商的新方法。 Lepus采用了一种纯粹的合作方式来培训多个代理,以策略网络的共享参数和多个代理的共享奖励函数为特色。特别是,Lepus通过对抗过程预先培训政策网络,提高其协作决策能力并进一步促进汽车驾驶的稳定性。此外,由于减轻了稀疏奖励的问题,Lepus通过结合随机网络和蒸馏网络从专家轨迹中学习了近似奖励功能。我们在Madras模拟平台上进行了广泛的实验。实验结果表明,通过麻法训练的多种代理可以避免同时驾驶时尽可能多的碰撞并超越其他四种方法,即DDPG-FDE,PSDDPG,MADDPG和MAGAIL和MAGAIL(DDPG)(DDPG)在稳定性方面。
translated by 谷歌翻译
基于图形卷积网络的方法对车身连接关系进行建模,最近在基于3D骨架的人体运动预测中显示出巨大的希望。但是,这些方法有两个关键问题:首先,仅在有限的图形频谱中过滤特征,在整个频段中丢失了足够的信息;其次,使用单个图对整个身体进行建模,低估了各个身体部门的各种模式。为了解决第一个问题,我们提出了自适应图散射,该散射利用了多个可训练的带通滤波器将姿势特征分解为较丰富的图形频谱频段。为了解决第二个问题,分别对身体零件进行建模以学习多种动力学,从而沿空间维度提取更精细的特征提取。整合了上述两种设计,我们提出了一个新型的骨架派对图散射网络(SPGSN)。该模型的核心是级联的多部分图形散射块(MPGSB),在不同的身体部门建立自适应图散射,并基于推断的频谱重要性和身体零件相互作用融合分解的特征。广泛的实验表明,SPGSN的表现优于最先进的方法,其优于13.8%,9.3%和2.7%的SPGSN在每个联合位置误差(MPJPE)上,在36m,CMU MOCAP和3DPW Dataset,3D平均位置误差(MPJPE)方面,SPGSN优于最先进的方法。分别。
translated by 谷歌翻译
车辆到所有(V2X)通信技术使车辆与附近环境中许多其他实体之间的协作可以从根本上改善自动驾驶的感知系统。但是,缺乏公共数据集极大地限制了协作感知的研究进度。为了填补这一空白,我们提出了V2X-SIM,这是一个针对V2X辅助自动驾驶的全面模拟多代理感知数据集。 V2X-SIM提供:(1)\ hl {Multi-Agent}传感器记录来自路边单元(RSU)和多种能够协作感知的车辆,(2)多模式传感器流,可促进多模式感知和多模式感知和(3)支持各种感知任务的各种基础真理。同时,我们在三个任务(包括检测,跟踪和细分)上为最先进的协作感知算法提供了一个开源测试台,并为最先进的协作感知算法提供了基准。 V2X-SIM试图在现实数据集广泛使用之前刺激自动驾驶的协作感知研究。我们的数据集和代码可在\ url {https://ai4ce.github.io/v2x-sim/}上获得。
translated by 谷歌翻译
为了促进更好的性能带宽权衡,以实现多种代理人的感知,我们提出了一种新颖的蒸馏协作图(光盘),以模拟代理商之间的培训,姿势感知和适应性协作。我们的主要新科特迪斯在两个方面。首先,我们提出了一位教师学生框架通过知识蒸馏训练光盘。教师模型采用与全面查看输入的早期合作;学生模型基于中间协作与单视图输入。我们的框架通过在学生模型中约束协作后的特征地图来列进讨论,以匹配教师模型的对应关系。其次,我们提出了矩阵值的边缘重量。在这样的矩阵中,每个元素将互及的间歇注意力反映在特定空间区域,允许代理自适应地突出显示信息区域。在推论期间,我们只需要使用名为Distilled Collaboration Network的学生模型(Disconet)。归因于师生框架,具有共享Disconet的多个代理商可以协作地与整体视图进行假设教师模型的表现。我们的方法在V2X-SIM 1.0上验证了我们使用Carla和Sumo Co-Simulation合成的大规模多代理感知数据集。我们在多代理3D对象检测中的定量和定性实验表明,Disconet不仅可以实现比最先进的协作的感知方法更好的性能带宽权衡,而且还带来了更直接的设计理由。我们的代码可在https://github.com/ai4ce/disconet上找到。
translated by 谷歌翻译
差异私有随机梯度下降(DP-SGD)通过在SGD训练期间将噪声添加到剪切梯度以满足差异隐私(DP)定义来防止训练数据隐私泄露。另一方面,跨越训练步骤的相同剪辑操作和附加噪声导致不稳定的更新甚至是增值时间,这显着降低了模型的准确性。在本文中,我们延长了高斯DP中央极限定理,以分别校准每个单独的步骤的剪切值和噪声功率。因此,我们能够提出动态DP-SGD,其在更新期间具有比DP-SGD更低的隐私成本,直到它们在目标更新数量达到相同的目标隐私预算之前。特别是动态DP-SGD,特别提高了模型精度,而不会通过逐渐降低剪切值和噪声功率来遵循完全隐私预算约束来牺牲隐私。关于各种深度学习任务的广泛实验,包括图像分类,自然语言处理和联合学习,表明所提出的动态DP-SGD算法稳定更新,因此,在较强烈的隐私保护区中显着提高了模型精度与DP-SGD相比。
translated by 谷歌翻译
Action recognition with skeleton data has recently attracted much attention in computer vision. Previous studies are mostly based on fixed skeleton graphs, only capturing local physical dependencies among joints, which may miss implicit joint correlations. To capture richer dependencies, we introduce an encoder-decoder structure, called A-link inference module, to capture action-specific latent dependencies, i.e. actional links, directly from actions. We also extend the existing skeleton graphs to represent higherorder dependencies, i.e. structural links. Combing the two types of links into a generalized skeleton graph, we further propose the actional-structural graph convolution network (AS-GCN), which stacks actional-structural graph convolution and temporal convolution as a basic building block, to learn both spatial and temporal features for action recognition. A future pose prediction head is added in parallel to the recognition head to help capture more detailed action patterns through self-supervision. We validate AS-GCN in action recognition using two skeleton data sets, NTU-RGB+D and Kinetics. The proposed AS-GCN achieves consistently large improvement compared to the state-of-the-art methods. As a side product, AS-GCN also shows promising results for future pose prediction. Our code is available at https://github.com/limaosen0/AS-GCN . 1
translated by 谷歌翻译
Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain adaptation, which tends to corrupt feature discriminability. In this paper, we propose Discriminative Radial Domain Adaptation (DRDR) which bridges source and target domains via a shared radial structure. It's motivated by the observation that as the model is trained to be progressively discriminative, features of different categories expand outwards in different directions, forming a radial structure. We show that transferring such an inherently discriminative structure would enable to enhance feature transferability and discriminability simultaneously. Specifically, we represent each domain with a global anchor and each category a local anchor to form a radial structure and reduce domain shift via structure matching. It consists of two parts, namely isometric transformation to align the structure globally and local refinement to match each category. To enhance the discriminability of the structure, we further encourage samples to cluster close to the corresponding local anchors based on optimal-transport assignment. Extensively experimenting on multiple benchmarks, our method is shown to consistently outperforms state-of-the-art approaches on varied tasks, including the typical unsupervised domain adaptation, multi-source domain adaptation, domain-agnostic learning, and domain generalization.
translated by 谷歌翻译
多代理协作感知可以通过使代理商能够通过交流相互共享互补信息来显着升级感知表现。它不可避免地会导致感知表现与沟通带宽之间的基本权衡。为了解决这个瓶颈问题,我们提出了一个空间置信度图,该图反映了感知信息的空间异质性。它使代理只能在空间上共享稀疏而感知的关键信息,从而有助于沟通。基于这张新型的空间置信度图,我们提出了2Comm,即沟通有效的协作感知框架。其中2Comm具有两个不同的优势:i)它考虑了实用的压缩,并使用较少的沟通来通过专注于感知至关重要的领域来实现更高的感知表现; ii)它可以通过动态调整涉及通信的空间区域来处理不同的通信带宽。要评估2comm的位置,我们考虑了在现实世界和模拟方案中使用两种模式(相机/激光镜头)和两种代理类型(CAR/无人机)的3D对象检测:OPV2V,v2x-sim,dair-v2x和我们的原始的Coperception-uavs。其中2comm始终优于先前的方法;例如,它实现了超过$ 100,000 \ times $较低的通信量,并且在OPV2V上仍然优于脱颖而出和v2x-vit。我们的代码可在https://github.com/mediabrain-sjtu/where2comm上找到。
translated by 谷歌翻译
感知是自动驾驶系统的关键模块之一,最近取得了长足的进步。但是,单个车辆的能力有限,导致感知表现的瓶颈。为了突破个人感知的局限性,已经提出了协作感知,使车辆能够共享信息以了解超出视线和视野的环境。在本文中,我们对有关有前途的协作感知技术的相关工作进行了评论,包括介绍基本概念,推广协作模式并总结协作感知的关键成分和应用。最后,我们讨论了该研究领域的公开挑战和问题,并提供了一些潜在的方向。
translated by 谷歌翻译