Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into $N\times N$ blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling `P" or ``O" in aPTP ``The block P has a O". This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT \cite{vilt} baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP \cite{blip} baseline. Moreover, PTP achieves comparable results with object-detector based methods, and much faster inference speed since PTP discards its object detector for inference while the later cannot. Our code and pre-trained weight will be released at \url{https://github.com/sail-sg/ptp}.
translated by 谷歌翻译
As the COVID-19 pandemic puts pressure on healthcare systems worldwide, the computed tomography image based AI diagnostic system has become a sustainable solution for early diagnosis. However, the model-wise vulnerability under adversarial perturbation hinders its deployment in practical situation. The existing adversarial training strategies are difficult to generalized into medical imaging field challenged by complex medical texture features. To overcome this challenge, we propose a Contour Attention Preserving (CAP) method based on lung cavity edge extraction. The contour prior features are injected to attention layer via a parameter regularization and we optimize the robust empirical risk with hybrid distance metric. We then introduce a new cross-nation CT scan dataset to evaluate the generalization capability of the adversarial robustness under distribution shift. Experimental results indicate that the proposed method achieves state-of-the-art performance in multiple adversarial defense and generalization tasks. The code and dataset are available at https://github.com/Quinn777/CAP.
translated by 谷歌翻译
在本报告中,我们建议针对四个EGO4D挑战任务,包括自然语言查询(NLQ),MOMMER QUERY(MQ),对象状态变更分类(OSCC),以及PNR定位(PNR)。尤其是,我们将最近发布的EGO4D数据集\ cite {grauman2021ego4d}从预处理数据集,预处理目标和开发集中从egecentric vlp中提升。基于上述三个设计,我们开发了一个验证的视频语言模型,该模型能够将其以自我为中心的视频文本表示或仅视频表示形式转移到几个视频下游任务中。我们的Egentric VLP在NLQ上实现10.46r@1&iou @0.3,MQ上的10.33地图,OSCC上的74%ACC,PNR上的0.67秒错误。该代码可在https://github.com/showlab/egovlp上找到。
translated by 谷歌翻译
在本报告中,我们为Epic-kitchens-100多实体检索(miR)挑战提出了一个基于视频的预处理(VLP)解决方案\ cite {kevin202222222egovlp}。尤其是,我们将最近发布的EGO4D数据集\ cite {grauman2021ego4d}从预处理数据集,预处理目标和开发集中从egecentric vlp中提升。基于上述三个设计,我们开发了一个预验证的视频语言模型,该模型能够将其自我为中心的视频文本表示为mir基准。此外,我们设计了一种自适应多构度最大损失,以有效地微调模型并为可靠的推理配备双重效果技术。我们最好的单个模型在挑战测试集上获得了强劲的性能,其中47.39%的地图和61.44%的NDCG。该代码可在https://github.com/showlab/egovlp上找到。
translated by 谷歌翻译
本文介绍了Thuee团队的语音识别系统,用于IARPA Open自动语音识别挑战(OpenASR21),并进行了进一步的实验探索。我们在受限和受约束的训练条件下取得了出色的成果。对于受限的训练条件,我们基于标准混合体系结构构建基本ASR系统。为了减轻摄影库(OOV)的问题,我们使用针对OOV和潜在的新单词的素式至phoneme(G2P)技术扩展了发音词典。采用了标准的声学模型结构,例如CNN-TDNN-F和CNN-TDNN-F-A。此外,还应用了多种数据增强技术。对于约束训练条件,我们使用自我监督的学习框架WAV2VEC2.0。我们在公开可用的预训练XLSR-53的基础上使用连接式时间分类(CTC)标准进行各种微调技术。我们发现,在将WAV2VEC2.0预训练的模型应用于基于编码器的CTC/CTC/COATION ASR体系结构时,前端特征提取器在将WAV2VEC2.0预训练的模型应用时起着重要作用。通过将目标语言用作为前端功能提取器使用的CTC模型填充可以实现额外的改进。
translated by 谷歌翻译
尽管通过深度卷积神经网络进行了视频理解的巨大进展,但现有方法学到的特征表示可能偏置到静态视觉线索。为了解决这个问题,我们提出了一种基于自我监督视频表示学习的概率分析来抑制静态视觉提示(SSVC)的新方法。在我们的方法中,首先编码视频帧以通过标准化流程根据标准正常分布获得潜在变量。通过将视频中的静态因子建模为随机变量,每个潜在变量的条件分布变为偏移并缩放正常。然后,选择沿着时间的较大潜伏变量作为静态线索并抑制以生成运动保留的视频。最后,通过运动保存的视频构建了正对,以便对比学习,以减轻对静态线索的表示偏差问题。较少偏置的视频表示可以更广泛地推广到各种下游任务。关于公开的基准测试的广泛实验表明,当仅使用单个RGB模型用于预训练时,所提出的方法优于现有技术。
translated by 谷歌翻译
视频文本预培训旨在通过对齐视觉和文本信息之间的语义来对齐大规模视频文本对学习可转换表示。最先进的方法以端到端的方式从原始像素提取视觉特征。然而,这些方法直接在帧级运行,从而忽略了视频中对象的时空结构,这在文本描述中具有名词的强烈协同作用。在这项工作中,我们提出了一个简单而有效的模块,即用于视频文本表示学习,即RegionLearner,它可以考虑在大规模视频文本对预训练中的对象结构。给定视频,我们的模块(1)首先将可视特征量化为语义集群,然后(2)生成被动掩码并使用它们聚合属于同一语义区域的功能,最后(3)模拟不同聚合区域之间的交互。与使用现成的对象探测器相比,我们所提出的模块不需要明确的监督,并且更加计算效率。我们在公共WebVID2M和CC3M数据集上预先列车。对四个下游视频文本检索基准测试的广泛评估清楚地展示了我们的地区learner的有效性。代码将在https://github.com/ruiyan1995/region_learner上获得。
translated by 谷歌翻译
最近,通过引入大规模的数据集和强大的变压器网络,视频预培训表明尤其是检索的巨大成功。然而,现有的视频语言变压器模型没有明确细粒度的语义对齐。在这项工作中,我们呈现了对象感知的变换器,以对象为中心的方法,该对象方法扩展了视频语言变压器来合并对象表示。关键的想法是利用边界框和对象标签来指导培训过程。我们在四个广泛使用的基准测试中评估了我们的三个标准子任务的模型。我们还提供了深入的分析和详细消融关于所提出的方法。我们在考虑的所有任务和数据集中表现出清晰的性能,展示将对象表示的模型中的型号集成到视频架构中。代码将以\ URL {https://github.com/fingerrec/oa -transformer}释放。
translated by 谷歌翻译
大多数息肉分段方法使用CNNS作为其骨干,导致在编码器和解码器之间的信息交换信息时的两个关键问题:1)考虑到不同级别特征之间的贡献的差异; 2)设计有效机制,以融合这些功能。不同于现有的基于CNN的方法,我们采用了一个变压器编码器,它学会了更强大和强大的表示。此外,考虑到息肉的图像采集影响和难以实现的性质,我们介绍了三种新模块,包括级联融合模块(CFM),伪装识别模块(CIM),A和相似性聚集模块(SAM)。其中,CFM用于从高级功能收集息肉的语义和位置信息,而CIM应用于在低级功能中伪装的息肉信息。在SAM的帮助下,我们将息肉区域的像素特征扩展到整个息肉区域的高电平语义位置信息,从而有效地融合了交叉级别特征。所提出的模型名为Polyp-PVT,有效地抑制了特征中的噪声,并显着提高了他们的表现力。在五个广泛采用的数据集上进行了广泛的实验表明,所提出的模型对各种具有挑战性的情况(例如,外观变化,小物体)比现有方法更加强大,并实现了新的最先进的性能。拟议的模型可在https://github.com/dengpingfan/polyp-pvt获得。
translated by 谷歌翻译
With the continuously thriving popularity around the world, fitness activity analytic has become an emerging research topic in computer vision. While a variety of new tasks and algorithms have been proposed recently, there are growing hunger for data resources involved in high-quality data, fine-grained labels, and diverse environments. In this paper, we present FLAG3D, a large-scale 3D fitness activity dataset with language instruction containing 180K sequences of 60 categories. FLAG3D features the following three aspects: 1) accurate and dense 3D human pose captured from advanced MoCap system to handle the complex activity and large movement, 2) detailed and professional language instruction to describe how to perform a specific activity, 3) versatile video resources from a high-tech MoCap system, rendering software, and cost-effective smartphones in natural environments. Extensive experiments and in-depth analysis show that FLAG3D contributes great research value for various challenges, such as cross-domain human action recognition, dynamic human mesh recovery, and language-guided human action generation. Our dataset and source code will be publicly available at https://andytang15.github.io/FLAG3D.
translated by 谷歌翻译