Although existing multi-object tracking (MOT) algorithms have obtained competitive performance on various benchmarks, almost all of them train and validate models on the same domain. The domain generalization problem of MOT is hardly studied. To bridge this gap, we first draw the observation that the high-level information contained in natural language is domain invariant to different tracking domains. Based on this observation, we propose to introduce natural language representation into visual MOT models for boosting the domain generalization ability. However, it is infeasible to label every tracking target with a textual description. To tackle this problem, we design two modules, namely visual context prompting (VCP) and visual-language mixing (VLM). Specifically, VCP generates visual prompts based on the input frames. VLM joints the information in the generated visual prompts and the textual prompts from a pre-defined Trackbook to obtain instance-level pseudo textual description, which is domain invariant to different tracking scenes. Through training models on MOT17 and validating them on MOT20, we observe that the pseudo textual descriptions generated by our proposed modules improve the generalization performance of query-based trackers by large margins.
translated by 谷歌翻译
对象的时间建模是多个对象跟踪(MOT)的关键挑战。现有方法通过通过基于运动和基于外观的相似性启发式方法关联检测来跟踪。关联的后处理性质阻止了视频序列中时间变化的端到端。在本文中,我们提出了MOTR,它扩展了DETR并介绍了轨道查询,以模拟整个视频中的跟踪实例。轨道查询被转移并逐帧更新,以随着时间的推移执行迭代预测。我们提出了曲目感知的标签分配,以训练轨道查询和新生儿对象查询。我们进一步提出了时间聚集网络和集体平均损失,以增强时间关系建模。 Dancetrack上的实验结果表明,MOTR在HOTA度量方面的表现明显优于最先进的方法,字节范围为6.5%。在MOT17上,MOTR在关联性能方面优于我们的并发作品,跟踪器和Transtrack。 MOTR可以作为对时间建模和基于变压器的跟踪器的未来研究的更强基线。代码可在https://github.com/megvii-research/motr上找到。
translated by 谷歌翻译
随着大型预训练的Vison语言模型(如剪辑)的出现,可以通过及时调整来调整可转让表示形式。及时调整试图从存储在预训练的视觉模型的图像和文本编码器中的常识中探索有益信息,以探索下游任务。最近提出的名为“上下文优化”(COP)的方法将一组可学习的向量从语言侧引入文本提示符,而单独调整文本提示符则不会影响图像编码器的计算视觉特征,从而导致了次级优势。在本文中,我们通过学习文本提示并同时为文本和图像编码器提供双重模式提示调整范式。此外,为了使视觉提示更多地集中在目标视觉概念上,我们提出了类感知的视觉及时调整(CAVPT),该调整是通过在模板提示和视觉类别令牌嵌入的语言描述之间进行交叉注意来动态生成的。我们的方法提供了一种新的范式来调整大型预训练的视觉模型,并在8个数据集上进行了广泛的实验结果,证明了该方法的有效性。我们的代码在补充材料中可用。
translated by 谷歌翻译
Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are indexes, lacking concrete text descriptions. Therefore, it remains to be determined how such models could be applied to these tasks. This paper first finds out that simply fine-tuning the visual model initialized by the image encoder in CLIP, has already obtained competitive performances in various ReID tasks. Then we propose a two-stage strategy to facilitate a better visual representation. The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID and give them to the text encoder to form ambiguous descriptions. In the first training stage, image and text encoders from CLIP keep fixed, and only the text tokens are optimized from scratch by the contrastive loss computed within a batch. In the second stage, the ID-specific text tokens and their encoder become static, providing constraints for fine-tuning the image encoder. With the help of the designed loss in the downstream task, the image encoder is able to represent data as vectors in the feature embedding accurately. The effectiveness of the proposed strategy is validated on several datasets for the person or vehicle ReID tasks. Code is available at https://github.com/Syliz517/CLIP-ReID.
translated by 谷歌翻译
对比性语言图像预训练(剪辑)已被证明可以学习具有出色传递性的视觉表示,从而实现了零击分类的有希望的准确性。为了进一步提高其下游性能,现有作品在剪辑上提出了其他可学习的模块,并通过几次训练集对其进行微调。但是,由此产生的额外培训成本和数据要求严重阻碍了模型部署和知识转移的效率。在本文中,我们引入了一种自由午餐的增强方法CALIP,以通过无参数注意模块来提高Clip的零拍摄性能。具体而言,我们指导视觉和文本表示相互交互,并通过注意探索跨模式的信息特征。由于预训练大大降低了两种方式之间的嵌入距离,因此我们在注意力中丢弃所有可学习的参数,并在双向更新多模式特征,从而使整个过程无参数且无培训。通过这种方式,图像与文本感知信号混合在一起,文本表示形式被视觉引导以获得更好的自适应零射击对齐。我们在14个数据集的各种基准上评估CALIP,用于2D图像和3D Point Cloud几乎没有分类,显示出一致的零弹性性能改进了夹子。基于此,我们进一步在Calip的注意模块中插入了少量线性层,并在少量射击设置下验证我们的鲁棒性,与现有方法相比,这也可以实现领先的性能。这些广泛的实验证明了我们的方法在有效增强夹子方面的优势。
translated by 谷歌翻译
现有的时间动作检测(TAD)方法依赖于大型培训数据,包括细分级注释,仅限于在推理期间单独识别先前看到的课程。为每类兴趣收集和注释一个大型培训集是昂贵的,因此无法计算。零射TAD(ZS-TAD)通过启用预训练的模型来识别任何看不见的动作类别来解决这一障碍。同时,ZS-TAD的调查大大降低,ZS-Tad也更具挑战性。受零摄像图像分类的成功的启发,我们旨在解决更复杂的TAD任务。一种直观的方法是将现成的建议探测器与剪辑样式分类集成。但是,由于顺序定位(例如,提案生成)和分类设计,它很容易进行定位误差传播。为了克服这个问题,在本文中,我们通过视觉提示(陈旧)提出了一种新型的零射击时间动作检测模型。这种新颖的设计通过破坏介于两者之间的错误传播途径来有效地消除了定位和分类之间的依赖性。我们进一步介绍了分类和定位之间的相互作用机制,以改善优化。对标准ZS-TAD视频基准测试的广泛实验表明,我们的陈旧的表现明显优于最先进的替代方案。此外,我们的模型还与最近的强大竞争对手相比,在受到监督的TAD上还能产生卓越的成果。 Stale的Pytorch实现可从https://github.com/sauradip/stale获得。
translated by 谷歌翻译
Open-vocabulary object detection, which is concerned with the problem of detecting novel objects guided by natural language, has gained increasing attention from the community. Ideally, we would like to extend an open-vocabulary detector such that it can produce bounding box predictions based on user inputs in form of either natural language or exemplar image. This offers great flexibility and user experience for human-computer interaction. To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image. The biggest challenge of turning DETR into an open-vocabulary detector is that it is impossible to calculate the classification cost matrix of novel classes without access to their labeled images. To overcome this challenge, we formulate the learning objective as a binary matching one between input queries (class name or exemplar image) and the corresponding objects, which learns useful correspondence to generalize to unseen queries during testing. For training, we choose to condition the Transformer decoder on the input embeddings obtained from a pre-trained vision-language model like CLIP, in order to enable matching for both text and image queries. With extensive experiments on LVIS and COCO datasets, we demonstrate that our OV-DETR -- the first end-to-end Transformer-based open-vocabulary detector -- achieves non-trivial improvements over current state of the arts.
translated by 谷歌翻译
自动视觉解对我们多样化和开放的世界需要计算机视觉模型,以概括为特定任务的最小定制,类似于人类视力。计算机视觉基础型号培训,培训多样化,大型数据集,可以适应各种下游任务,对该任务来解决现实世界计算机视觉应用而言至关重要。虽然现有的视觉基础模型如剪辑,对齐和吴道2.0主要集中在映射图像和文本表示到跨模型共享表示,我们介绍了一台新的计算机视觉基础模型,佛罗伦萨,扩大粗糙的表示(现场)到精细(对象),从静态(图像)到动态(视频),以及从RGB到多个模态(标题,深度)。通过从Web级图像文本数据中纳入通用视觉语言表示,我们的佛罗伦萨模型可以很容易地适应各种计算机视觉任务,例如分类,检索,对象检测,VQA,图像标题,视频检索和动作识别。此外,佛罗伦萨在许多类型的转移学习中表现出出色的表现:全面采样的微调,线性探测,几次射击传输和用于新颖图像和物体的零拍摄传输。所有这些属性对于我们的视觉基础模型至关重要,以提供通用视觉任务。佛罗伦萨实现了新的最先进的导致44个代表性基准,例如Imagenet-1K零射击分类,最高1精度为83.74,最高5个精度为97.18,62.4地图上的Coco微调, 80.36在VQA上,动力学-600上的87.8。
translated by 谷歌翻译
最近的进展表明,使用对比图像文本对的大规模预训练可以是从自然语言监督的高质量视觉表演学习的有前途的替代方案。从更广泛的监督来源受益,这种新的范例展示了对下游分类任务和数据集的令人印象深刻的可转移性。然而,从图像文本对中学习的知识转移到更复杂的密集预测任务的问题几乎没有访问过。在这项工作中,我们通过隐式和明确地利用来自剪辑的预先训练的知识来提出了一种新的密集预测框架。具体地,我们将剪辑中的原始图像文本匹配问题转换为像素文本匹配问题,并使用像素文本分数图来指导致密预测模型的学习。通过进一步使用图像中的上下文信息来提示语言模型,我们能够促进我们的模型来更好地利用预先接受训练的知识。我们的方法是模型 - 不可行的,它可以应用于任意密集的预测系统和各种预先训练的视觉底座,包括夹模型和想象成预先训练的模型。广泛的实验证明了我们对语义分割,对象检测和实例分段任务的方法的卓越性能。代码可在https://github.com/raoyongming/denseclip获得
translated by 谷歌翻译
Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities (e.g., images, videos, text and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. We then cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering, visual reasoning, and visual grounding), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution, image enhancement, and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works. We hope this effort will ignite further interest in the community to solve current challenges towards the application of transformer models in computer vision.
translated by 谷歌翻译
We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decodert takes as input two types of queries: (i) generic non-semantic queries and (ii) semantic queries induced from text inputs, to decode different pixel-level and token-level outputs in the same semantic space. With such a novel design, X-Decoder is the first work that provides a unified way to support all types of image segmentation and a variety of vision-language (VL) tasks. Further, our design enables seamless interactions across tasks at different granularities and brings mutual benefits by learning a common and rich pixel-level visual-semantic understanding space, without any pseudo-labeling. After pretraining on a mixed set of a limited amount of segmentation data and millions of image-text pairs, X-Decoder exhibits strong transferability to a wide range of downstream tasks in both zero-shot and finetuning settings. Notably, it achieves (1) state-of-the-art results on open-vocabulary segmentation and referring segmentation on eight datasets; (2) better or competitive finetuned performance to other generalist and specialist models on segmentation and VL tasks; and (3) flexibility for efficient finetuning and novel task composition (e.g., referring captioning and image editing). Code, demo, video, and visualization are available at https://x-decoder-vl.github.io.
translated by 谷歌翻译
Few-shot (FS) and zero-shot (ZS) learning are two different approaches for scaling temporal action detection (TAD) to new classes. The former adapts a pretrained vision model to a new task represented by as few as a single video per class, whilst the latter requires no training examples by exploiting a semantic description of the new class. In this work, we introduce a new multi-modality few-shot (MMFS) TAD problem, which can be considered as a marriage of FS-TAD and ZS-TAD by leveraging few-shot support videos and new class names jointly. To tackle this problem, we further introduce a novel MUlti-modality PromPt mETa-learning (MUPPET) method. This is enabled by efficiently bridging pretrained vision and language models whilst maximally reusing already learned capacity. Concretely, we construct multi-modal prompts by mapping support videos into the textual token space of a vision-language model using a meta-learned adapter-equipped visual semantics tokenizer. To tackle large intra-class variation, we further design a query feature regulation scheme. Extensive experiments on ActivityNetv1.3 and THUMOS14 demonstrate that our MUPPET outperforms state-of-the-art alternative methods, often by a large margin. We also show that our MUPPET can be easily extended to tackle the few-shot object detection problem and again achieves the state-of-the-art performance on MS-COCO dataset. The code will be available in https://github.com/sauradip/MUPPET
translated by 谷歌翻译
对比视觉语言预培训(剪辑)最近淹没了其可转让的视觉表现学习的关注。由大规模的图像文本对进行监督,剪辑能够对准配对的图像和文本,从而在开放词汇场景中进行零拍摄识别。然而,特定应用与通常预先训练的知识之间存在语义差距,这使得匹配子最优在下游任务上。在本文中,我们提出了VT-CLIP通过可视导向文本来增强视觉语言建模。具体而言,我们指导文本功能以自适应地探索图像上的信息区域,并通过跨关注的Machanism聚合视觉特征。以这种方式,视觉引导文本与图像变得更加语义相关,这极大地利益匹配过程。在几次拍摄的设置中,我们在11名知名分类数据集中评估我们的VT-CLIP,并进行实验广泛的消融研究,以证明VT-CLIP的有效性。代码将很快发布。
translated by 谷歌翻译
由于与传统的基于RGB的跟踪相比,多模式跟踪的能力在复杂的情况下更准确和健壮,因此获得了关注。它的关键在于如何融合多模式数据并减少模式之间的差距。但是,多模式跟踪仍然严重遭受数据缺乏症的影响,从而导致融合模块的学习不足。我们没有在本文中构建这样的融合模块,而是通过将重要性附加到多模式的视觉提示中,为多模式跟踪提供了新的视角。我们设计了一种新型的多模式及时跟踪器(Protrack),可以通过及时范式将多模式输入传递到单个模态。通过最好地利用预先训练的RGB跟踪器在大规模学习的跟踪能力,我们的突起即使没有对多模式数据进行任何额外的培训,我们的突起也可以通过更改输入来实现高性能多模式跟踪。 5个基准数据集的广泛实验证明了所提出的突起的有效性。
translated by 谷歌翻译
变压器是一种基于关注的编码器解码器架构,彻底改变了自然语言处理领域。灵感来自这一重大成就,最近在将变形式架构调整到计算机视觉(CV)领域的一些开创性作品,这已经证明了他们对各种简历任务的有效性。依靠竞争力的建模能力,与现代卷积神经网络相比在本文中,我们已经为三百不同的视觉变压器进行了全面的审查,用于三个基本的CV任务(分类,检测和分割),提出了根据其动机,结构和使用情况组织这些方法的分类。 。由于培训设置和面向任务的差异,我们还在不同的配置上进行了评估了这些方法,以便于易于和直观的比较而不是各种基准。此外,我们已经揭示了一系列必不可少的,但可能使变压器能够从众多架构中脱颖而出,例如松弛的高级语义嵌入,以弥合视觉和顺序变压器之间的差距。最后,提出了三个未来的未来研究方向进行进一步投资。
translated by 谷歌翻译
视觉语言预培训对从大规模Web数据学习联合视觉文本表示的巨大成功,展示了零拍广泛的显着能力。本文介绍了一种简单的方法,可以将一个预先训练的视觉语言模型有效地调整到具有最小培训的新型任务,以及这里,我们考虑视频了解任务。具体而言,我们建议优化几个随机向量,称为连续提示向量,将新颖任务转换为与预培训目标相同的格式。此外,为了弥合静态图像和视频之间的差距,用堆叠在框架明智的视觉特征之上的轻量压变压器编码时分信息。在实验上,我们进行广泛的消融研究,以分析关键组成部分和必需品。在9个公共基准的行动认可,行动本地化和文本 - 视频检索,跨封闭式,几次射击,开放式场景,我们为现有方法实现了竞争或最先进的性能,尽管培训显着更少的参数。
translated by 谷歌翻译
参照视频对象分割(R-VOS)是一个新兴的跨通道任务,其目的是分割目标对象中的所有的视频帧称为一个语言表达式。在这项工作中,我们提出了一个简单并在变压器建成统一的框架,称为ReferFormer。它认为在语言查询,并直接参加到视频帧中的最相关的区域。具体而言,我们引入一个小套空调的语言作为输入Transformer对象的查询。通过这种方式,所有的查询有义务仅发现指的对象。他们最终都转化为动态的内核,其捕捉的关键对象级信息,并发挥卷积过滤器的作用,生成特征地图分割口罩。对象跟踪通过连接在帧之间相应的查询自然实现。这种机制极大地简化了管道和终端到终端的框架是从以前的方法不同显著。在REF-YouTube的VOS,REF-DAVIS17大量的实验,A2D-句子和JHMDB-句显示ReferFormer的有效性。上REF-YouTube的VOS,参见-前达到55.6J&F与RESNET-50主链而不花哨,这超过了8.4点之前的状态的最先进的性能。此外,与强斯文 - 大型骨干,ReferFormer实现了所有现有的方法中最好的J&62.4 F。歼&F度量可以通过采用一个简单的后处理技术来进一步升压到63.3。此外,我们分别显示55.0地图和43.7地图上A2D-句andJHMDB-句令人印象深刻的结果,这显著优于大幅度以前的方法。代码是公开的,在https://github.com/wjn922/ReferFormer。
translated by 谷歌翻译
多模式变压器表现出高容量和灵活性,可将图像和文本对齐以进行视觉接地。然而,由于自我发挥操作的二次时间复杂性,仅编码的接地框架(例如,transvg)遭受了沉重的计算。为了解决这个问题,我们通过将整个接地过程解散为编码和解码阶段,提出了一种新的多模式变压器体系结构,以动态MDETR形成。关键观察是,图像中存在很高的空间冗余。因此,我们通过在加快视觉接地过程之前利用这种稀疏性来设计一种新的动态多模式变压器解码器。具体而言,我们的动态解码器由2D自适应采样模块和文本引导的解码模块组成。采样模块旨在通过预测参考点的偏移来选择这些信息补丁,而解码模块则可以通过在图像功能和文本功能之间执行交叉注意来提取接地对象信息。这两个模块也被堆叠起来,以逐渐弥合模态间隙,并迭代地完善接地对象的参考点,最终实现了视觉接地的目的。对五个基准测试的广泛实验表明,我们提出的动态MDETR实现了计算和准确性之间的竞争权衡。值得注意的是,在解码器中仅使用9%的特征点,我们可以降低〜44%的多模式变压器的GLOP,但仍然比仅编码器的对应物更高的精度。此外,为了验证其概括能力并扩展我们的动态MDETR,我们构建了第一个单级剪辑授权的视觉接地框架,并在这些基准测试中实现最先进的性能。
translated by 谷歌翻译
作为剪辑的对比视觉语言预培训为通过使用大规模对比图像文本对提供了学习视觉表示的新范式。它显示了零击中知识转移到下游任务的令人印象深刻的性能。为了进一步增强剪辑的几次射击功能,提出的剪辑适配器提出微调轻量级残留功能适配器,并显着提高了几次拍摄分类的性能。但是,这样的过程仍然需要额外的培训和计算资源。在本文中,我们提出了\ textbf {t}下雨的cl \ textbf {ip} - \ textbf {适配器}(\ textbf {tip-adapter}),它不仅继承了剪辑的无训练优势,还可以相当地执行或甚至比剪辑适配器更好。提示 - 适配器不需要任何用于训练适配器的备份传播,而是通过从几次拍摄训练集构造的键值高速缓存模型创建权重。在这种非参数的方式中,提示适配器在没有任何训练的情况下获取良好的适配器权重,这既有效且有效。此外,可以通过微调这种适当的初始化适配器进一步提高尖端适配器的性能,仅用于具有超快速收敛速度的几个时期。我们对ImageNet和其他10个数据集进行了广泛的小型分类实验,以证明提出的提示适配器的优越性。代码将以\ URL {https://github.com/gaopengcuhk/tip-adapter}释放。
translated by 谷歌翻译
在这项工作中,我们探索了用于视觉接地的整洁而有效的基于变压器的框架。先前的方法通常解决了视觉接地的核心问题,即具有手动设计的机制,即多模式融合和推理。这样的启发式设计不仅复杂化,而且使模型容易过度拟合特定的数据分布。为了避免这种情况,我们首先提出了TransVG,该TransVG通过变压器建立了多模式的对应关系,并通过直接回归框坐标来定位引用区域。我们从经验上表明,复杂的融合模块可以用具有更高性能的变压器编码层的简单堆栈代替。但是,TransVG中的核心融合变压器是针对Uni-Modal编码器的独立性,因此应在有限的视觉接地数据上从头开始训练,这使得很难优化并导致次优性能。为此,我们进一步介绍了TransVG ++以进行两倍的改进。一方面,我们通过利用Vision Transformer(VIT)进行视觉功能编码来将框架升级到一个纯粹的基于变压器的框架。对于另一个人来说,我们设计了语言有条件的视觉变压器,以去除外部融合模块,并重用Uni-Modal vit进行中间层的视觉融合。我们对五个普遍数据集进行了广泛的实验,并报告一系列最先进的记录。
translated by 谷歌翻译