Vision-Centric Bird-Eye-View (BEV) perception has shown promising potential and attracted increasing attention in autonomous driving. Recent works mainly focus on improving efficiency or accuracy but neglect the domain shift problem, resulting in severe degradation of transfer performance. With extensive observations, we figure out the significant domain gaps existing in the scene, weather, and day-night changing scenarios and make the first attempt to solve the domain adaption problem for multi-view 3D object detection. Since BEV perception approaches are usually complicated and contain several components, the domain shift accumulation on multi-latent spaces makes BEV domain adaptation challenging. In this paper, we propose a novel Multi-level Multi-space Alignment Teacher-Student ($M^{2}ATS$) framework to ease the domain shift accumulation, which consists of a Depth-Aware Teacher (DAT) and a Multi-space Feature Aligned (MFA) student model. Specifically, DAT model adopts uncertainty guidance to sample reliable depth information in target domain. After constructing domain-invariant BEV perception, it then transfers pixel and instance-level knowledge to student model. To further alleviate the domain shift at the global level, MFA student model is introduced to align task-relevant multi-space features of two domains. To verify the effectiveness of $M^{2}ATS$, we conduct BEV 3D object detection experiments on four cross domain scenarios and achieve state-of-the-art performance (e.g., +12.6% NDS and +9.1% mAP on Day-Night). Code and dataset will be released.
translated by 谷歌翻译
Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs. Different from the recent CNNs that focus on large dense kernels, InternImage takes deformable convolution as the core operator, so that our model not only has the large effective receptive field required for downstream tasks such as detection and segmentation, but also has the adaptive spatial aggregation conditioned by input and task information. As a result, the proposed InternImage reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large-scale parameters from massive data like ViTs. The effectiveness of our model is proven on challenging benchmarks including ImageNet, COCO, and ADE20K. It is worth mentioning that InternImage-H achieved the new record 65.4 mAP on COCO test-dev. The code will be released at https://github.com/OpenGVLab/InternImage.
translated by 谷歌翻译
在基于脑电图的情感计算领域,跨数据库情绪识别是一项极具挑战性的任务,受许多因素的影响,这使得通用模型产生了不令人满意的结果。面对缺乏脑电图信息解码研究的情况,我们首先分析了通过样本空间可视化,样本聚合现象量化和对五个公共数据集的能量模式分析的不同脑电图信息(个人,会话,情绪,试验)对情绪识别的影响。并基于这些现象和模式,我们提供了各种脑电图差异的处理方法和可解释的工作。通过分析情绪特征分布模式,发现了个体的情感特征分布差异(IEFDD)。在分析了IEFDD遭受的传统建模方法的局限性之后,我们提出了基于重量的通道模型矩阵框架(WCMF)。为了合理地表征情绪特征分布模式,设计了四种重量提取方法,最佳是校正t检验(CT)重量提取方法。最后,WCMF的性能在两种实验中在跨数据库任务上进行了验证,这些实验模拟了不同的实践场景,结果表明WCMF具有更稳定和更好的情感识别能力。
translated by 谷歌翻译
视频阴影检测旨在在视频帧之间产生一致的阴影预测。但是,当前的方法遇到了整个框架的阴影预测不一致的,尤其是当视频中的照明和背景纹理发生变化时。我们观察到不一致的预测是由阴影特征不一致引起的,即,同一阴影区域的特征在附近的框架之间显示出不同的礼节。在本文中,我们提出了一种新颖的阴影通信方法(SC-COR)(SC-COR) ),以增强跨帧的特定阴影区域的像素相似性,以进行视频阴影检测。我们提出的SC-COR具有三个主要优势。首先,不需要密集的像素到像素对应标签,SC-COR可以以弱监督的方式学习跨帧的像素对应。其次,SC-COR考虑了阴影内的可分离性,这对视频中的变体纹理和照明是可靠的。最后,SC-COR是一个插件模块,可以轻松地集成到没有额外的计算成本的情况下。我们进一步设计了一个新的评估指标,以评估视频阴影检测结果的时间稳定性。实验结果表明,SC-COR的表现优于先前的最新方法,而IOU的表现为6.51%,而新引入的时间稳定性度量为3.35%。
translated by 谷歌翻译
本文研究了几种皮肤疾病分类问题。基于至关重要的观察,即皮肤病图像通常存在于一类中的多个子群体(即,一类疾病中图像的外观变化并形成多个不同的子组),我们设计了一种新型的亚群集感知网络,即扫描,以提高准确性以稀有皮肤疾病诊断。由于几次学习的性能很大程度上取决于学习特征编码器的质量,因此指导扫描设计的主要原理是每个类的内在子簇表示学习,以便更好地描述特征分布。具体而言,扫描遵循双分支框架,第一个分支是学习范围的特征以区分不同的皮肤疾病,第二个分支是学习可以有效地将每个班级划分为几个组的特征,以保留子 - 每个类中的聚集结构。为了实现第二个分支的目标,我们提出了一个集群损失,可以通过无监督的聚类学习图像相似性。为了确保每个子集群中的样品来自同一类,我们进一步设计了纯度损失,以完善无监督的聚类结果。我们在两个公共数据集上评估了拟议方法,以进行几次皮肤疾病分类。实验结果验证了我们的框架在SD-198和DERM7PT数据集​​上优于其他最先进方法约为2%至4%。
translated by 谷歌翻译
深度学习(DL)技术已被广泛用于医学图像分类。大多数基于DL的分类网络通常是层次结构化的,并通过最小化网络末尾测量的单个损耗函数而进行了优化。但是,这种单一的损失设计可能会导致优化一个特定的感兴趣价值,但无法利用中间层的信息特征,这些特征可能会受益于分类性能并降低过度拟合的风险。最近,辅助卷积神经网络(AUXCNNS)已在传统分类网络之上采用,以促进中间层的培训,以提高分类性能和鲁棒性。在这项研究中,我们提出了一个基于对抗性学习的AUXCNN,以支持对医学图像分类的深神经网络的培训。我们的AUXCNN分类框架采用了两项主要创新。首先,所提出的AUXCNN体系结构包括图像发生器和图像鉴别器,用于为医学图像分类提取更多信息图像特征,这是由生成对抗网络(GAN)的概念及其在近似目标数据分布方面令人印象深刻的能力的动机。其次,混合损失函数旨在通过合并分类网络和AUXCNN的不同目标来指导模型训练,以减少过度拟合。全面的实验研究表明,提出的模型的分类表现出色。研究了与网络相关因素对分类性能的影响。
translated by 谷歌翻译
我们提出了GLIPV2,这是一个接地的VL理解模型,该模型既服务于本地化任务(例如,对象检测,实例分割)和视觉语言(VL)理解任务(例如VQA,图像字幕)。 GLIPV2优雅地将本地化预训练和视觉语言预训练(VLP)具有三个预训练任务:短语接地作为对检测任务的VL重新重新制定,区域词对比度学习作为新型的区域词对比度对比度对比学习任务,以及蒙面的语言建模。这种统一不仅简化了先前的多阶段VLP程序,而且还可以在本地化和理解任务之间实现相互利益。实验结果表明,在各种本地化和理解任务上,单个GLIPV2模型(所有模型权重)在SOTA性能附近实现。该模型还显示了(1)在开放式摄制对象检测任务上进行的强零射击和很少的自适应性能,以及(2)VL理解任务上的卓越接地能力。代码将在https://github.com/microsoft/glip上发布。
translated by 谷歌翻译
在本文中,我们设计和训练生成的图像到文本变压器Git,以统一视觉语言任务,例如图像/视频字幕和问题答案。尽管生成模型在预训练和微调之间提供了一致的网络体系结构,但现有工作通常包含复杂的结构(Uni/多模式编码器/解码器),并取决于外部模块,例如对象检测器/标记器和光学角色识别(OCR) )。在git中,我们将体系结构简化为一个图像编码器,而在单语言建模任务下将架构简化为一个文本解码器。我们还扩展了预训练数据和模型大小,以提高模型性能。没有铃铛和哨子,我们的git在12个具有挑战性的基准下建立了新的艺术状态。例如,我们的模型在文本贴图上首次超过了人类的表现(138.2 vs. 125.5在苹果酒中)。此外,我们提出了一种新的基于一代的图像分类和场景文本识别的方案,在标准基准上实现了不错的表现。
translated by 谷歌翻译
包括传统浅层模型和深图神经网络(GNN)在内的图形嵌入方法已导致有希望的应用。然而,由于其优化范式,浅层模型尤其是基于随机步行的算法无法充分利用采样子图或序列中的邻居接近度。基于GNN的算法遇到了高阶信息的利用不足,在堆叠过多的层时很容易引起过度平滑的问题,这可能会恶化低度(长尾)项目的建议,从而限制了表现力和可伸缩性。在本文中,我们提出了一个新颖的框架SAC,即空间自动回归编码,以统一的方式解决上述问题。为了充分利用邻居接近和高级信息,我们设计了一种新型的空间自回旋范式。具体而言,我们首先随机掩盖了多跳的邻居,并通过以明确的多跳上注意来整合所有其他周围的邻居来嵌入目标节点。然后,我们加强模型,通过对比编码和蒙面邻居的嵌入来学习目标节点的邻居预测性编码,并配备了新的硬性阴性采样策略。为了了解目标到邻居预测任务的最小足够表示并删除邻居的冗余,我们通过最大化目标预测性编码和蒙面邻居的嵌入以及同时约束编码之间的相互信息来设计邻居信息瓶颈和周围的邻居的嵌入。公共推荐数据集和实际方案网络规模数据集Douyin-Friend-Recormendation的实验结果证明了SAC的优势与最先进的方法相比。
translated by 谷歌翻译
Surgical phase recognition is a fundamental task in computer-assisted surgery systems. Most existing works are under the supervision of expensive and time-consuming full annotations, which require the surgeons to repeat watching videos to find the precise start and end time for a surgical phase. In this paper, we introduce timestamp supervision for surgical phase recognition to train the models with timestamp annotations, where the surgeons are asked to identify only a single timestamp within the temporal boundary of a phase. This annotation can significantly reduce the manual annotation cost compared to the full annotations. To make full use of such timestamp supervisions, we propose a novel method called uncertainty-aware temporal diffusion (UATD) to generate trustworthy pseudo labels for training. Our proposed UATD is motivated by the property of surgical videos, i.e., the phases are long events consisting of consecutive frames. To be specific, UATD diffuses the single labelled timestamp to its corresponding high confident ( i.e., low uncertainty) neighbour frames in an iterative way. Our study uncovers unique insights of surgical phase recognition with timestamp supervisions: 1) timestamp annotation can reduce 74% annotation time compared with the full annotation, and surgeons tend to annotate those timestamps near the middle of phases; 2) extensive experiments demonstrate that our method can achieve competitive results compared with full supervision methods, while reducing manual annotation cost; 3) less is more in surgical phase recognition, i.e., less but discriminative pseudo labels outperform full but containing ambiguous frames; 4) the proposed UATD can be used as a plug and play method to clean ambiguous labels near boundaries between phases, and improve the performance of the current surgical phase recognition methods.
translated by 谷歌翻译