很少有学习模型学习人类注释有限,而这种学习范式在各种任务中证明了实用性数据使该模型无法充分探索语义信息。为了解决这个问题,我们将知识蒸馏引入了几个弹出的对象检测学习范式。我们进一步进行了激励实验,该实验表明,在知识蒸馏的过程中,教师模型的经验误差将少数拍物对象检测模型的预测性能(作为学生)退化。为了了解这种现象背后的原因,我们从因果理论的角度重新审视了几个对象检测任务上知识蒸馏的学习范式,并因此发展了一个结构性因果模型。遵循理论指导,我们建议使用基于后门调整的知识蒸馏方法,用于少数拍物检测任务,即Disentangle和Remerge(D&R),以对相应的结构性因果模型进行有条件的因果干预。从理论上讲,我们为后门标准提供了扩展的定义,即一般后门路径,可以在特定情况下扩展后门标准的理论应用边界。从经验上讲,多个基准数据集上的实验表明,D&R可以在几个射击对象检测中产生显着的性能提升。
translated by 谷歌翻译
基于对比度学习(CL)以成对的方式学习视觉表示。尽管流行的CL模型取得了长足的进步,但在本文中,我们发现了一种不断被忽视的现象:当CL模型接受完整图像训练时,以完整图像测试的性能要比前景区域的表现更好。当CL模型接受前景区域训练时,以完整图像测试的性能要比前景区域差。该观察结果表明,图像中的背景可能会干扰模型学习语义信息及其影响尚未完全消除。为了解决这个问题,我们建立了一个结构性因果模型(SCM),以建模背景作为混杂因素。我们提出了一种基于后门调整的正则化方法,即用元语义正常器(ICL-MSR)进行介入的对比度学习,以对所提出的SCM进行因果干预。可以将ICL-MSR纳入任何现有的CL方法中,以减轻代表学习的背景干扰。从理论上讲,我们证明ICL-MSR达到了更严格的误差。从经验上讲,我们在多个基准数据集上的实验表明,ICL-MSR能够改善不同最先进的CL方法的性能。
translated by 谷歌翻译
虽然基于微调对象检测的基于微调的方法已经取得了显着的进步,但尚未得到很好的解决的关键挑战是基本类别的潜在特定于类别的过度拟合,并且针对新颖的类别的样本特异性过度拟合。在这项工作中,我们设计了一个新颖的知识蒸馏框架,以指导对象探测器的学习,从而抑制基础类别的前训练阶段的过度拟合,并在小型课程上进行微调阶段。要具体而言,我们首先提出了一种新颖的位置感知的视觉袋模型,用于从有限尺寸的图像集中学习代表性的视觉袋(BOVW),该模型用于基于相似性来编码常规图像在学习的视觉单词和图像之间。然后,我们基于以下事实执行知识蒸馏,即图像应在两个不同的特征空间中具有一致的BOVW表示。为此,我们独立于对象检测的特征空间预先学习特征空间,并在此空间中使用BOVW编码图像。可以将图像的BOVW表示形式视为指导对象探测器的学习:对象检测器的提取特征对同一图像的提取特征有望通过蒸馏知识得出一致的BOVW表示。广泛的实验验证了我们方法的有效性,并证明了优于其他最先进方法的优势。
translated by 谷歌翻译
几次射击对象检测的大多数现有方法都遵循微调范式,该范式可能假设可以通过众多样本的基本类别学习并将其隐式转移到具有限量样本的新颖类中,从而将类别的概括性知识隐含地转移到有限的类别中。舞台培训策略。但是,这不一定是正确的,因为对象检测器几乎无法在没有明确的建模的情况下自动区分类别不合时宜的知识和特定于类的知识。在这项工作中,我们建议在基础和新颖类之间学习三种类型的类不足的共同点:与识别相关的语义共同点,与定位相关的语义共同点和分布共同点。我们基于内存库设计了一个统一的蒸馏框架,该框架能够共同有效地进行所有三种类型的共同点。广泛的实验表明,我们的方法可以很容易地集成到大多数现有的基于微调的方法中,并始终如一地通过大幅度提高性能。
translated by 谷歌翻译
Although significant progress has been made in few-shot learning, most of existing few-shot learning methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability in real world application. Recently, large-scale self-supervised vision-language models (e.g., CLIP) have provided a new paradigm for transferable visual representation learning. However, the pre-trained VLPs may neglect detailed visual information that is difficult to describe by language sentences, but important for learning an effective classifier in few-shot classification. To address the above problem, we propose a new framework, named Semantic-guided Visual Adapting (SgVA), which can effectively extend vision-language pre-trained models to produce discriminative task-specific visual features by comprehensively using a vision-specific contrastive loss, a cross-modal contrastive loss, and an implicit knowledge distillation. The implicit knowledge distillation is designed to transfer the fine-grained cross-modal knowledge to guide the updating of the vision adapter. State-of-the-art results on 13 datasets demonstrate that the adapted visual features can well complement the cross-modal features to improve few-shot image classification.
translated by 谷歌翻译
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.
translated by 谷歌翻译
知识蒸馏(KD)是一种广泛使用的技术,将繁琐的教师模型继承到紧凑的学生模型,从而实现模型压缩和加速度。与图像分类相比,对象检测是一个更复杂的任务,设计特定的KD方法用于对象检测是非微小的。在这项工作中,我们精心研究教师和学生检测模型之间的行为差​​异,并获得了两个有趣的观察:首先,教师和学生对其检测到的候选盒子相得益彰,这导致了它们的精确差异。其次,教师和学生之间的特征响应差异和预测差异之间存在相当大的差距,表明同样模仿老师的所有特征映射是提高学生准确性的次优选。基于这两个观察,我们提出了用于分别蒸馏单级探测器的测量模拟(RM)和预测引导的特征模仿(PFI)。 RM从教师那里夺取候选人盒的等级作为一种新的知识形式,蒸馏,这始终如一地优于传统的软标签蒸馏。 PFI试图将特征差异与预测差异相关,使特征模仿直接有助于提高学生的准确性。在MS Coco和Pascal VOC基准测试中,广泛的实验在不同骨干的各种探测器上进行,以验证我们方法的有效性。具体而言,具有Reset50的RetinAnet在MS Coco中实现了40.4%的图,比其基线高3.5%,并且还优于先前的KD方法。
translated by 谷歌翻译
Recently, large-scale pre-trained models have shown their advantages in many tasks. However, due to the huge computational complexity and storage requirements, it is challenging to apply the large-scale model to real scenes. A common solution is knowledge distillation which regards the large-scale model as a teacher model and helps to train a small student model to obtain a competitive performance. Cross-task Knowledge distillation expands the application scenarios of the large-scale pre-trained model. Existing knowledge distillation works focus on directly mimicking the final prediction or the intermediate layers of the teacher model, which represent the global-level characteristics and are task-specific. To alleviate the constraint of different label spaces, capturing invariant intrinsic local object characteristics (such as the shape characteristics of the leg and tail of the cattle and horse) plays a key role. Considering the complexity and variability of real scene tasks, we propose a Prototype-guided Cross-task Knowledge Distillation (ProC-KD) approach to transfer the intrinsic local-level object knowledge of a large-scale teacher network to various task scenarios. First, to better transfer the generalized knowledge in the teacher model in cross-task scenarios, we propose a prototype learning module to learn from the essential feature representation of objects in the teacher model. Secondly, for diverse downstream tasks, we propose a task-adaptive feature augmentation module to enhance the features of the student model with the learned generalization prototype features and guide the training of the student model to improve its generalization ability. The experimental results on various visual tasks demonstrate the effectiveness of our approach for large-scale model cross-task knowledge distillation scenes.
translated by 谷歌翻译
Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine in-context learning objectives with language modeling objectives to distill both the ability to read in-context examples and task knowledge to the smaller models. We perform in-context learning distillation under two different few-shot learning paradigms: Meta In-context Tuning (Meta-ICT) and Multitask In-context Tuning (Multitask-ICT). Multitask-ICT performs better on multitask few-shot learning but also requires more computation than Meta-ICT. Our method shows consistent improvements for both Meta-ICT and Multitask-ICT on two benchmarks: LAMA and CrossFit. Our extensive experiments and analysis reveal that in-context learning objectives and language modeling objectives are complementary under the Multitask-ICT paradigm. In-context learning objectives achieve the best performance when combined with language modeling objectives.
translated by 谷歌翻译
Despite significant accuracy improvement in convolutional neural networks (CNN) based object detectors, they often require prohibitive runtimes to process an image for real-time applications. State-of-the-art models often use very deep networks with a large number of floating point operations. Efforts such as model compression learn compact models with fewer number of parameters, but with much reduced accuracy. In this work, we propose a new framework to learn compact and fast object detection networks with improved accuracy using knowledge distillation [20] and hint learning [34]. Although knowledge distillation has demonstrated excellent improvements for simpler classification setups, the complexity of detection poses new challenges in the form of regression, region proposals and less voluminous labels. We address this through several innovations such as a weighted cross-entropy loss to address class imbalance, a teacher bounded loss to handle the regression component and adaptation layers to better learn from intermediate teacher distributions. We conduct comprehensive empirical evaluation with different distillation configurations over multiple datasets including PASCAL, KITTI, ILSVRC and MS-COCO. Our results show consistent improvement in accuracy-speed trade-offs for modern multi-class detection models.
translated by 谷歌翻译
尽管配备的远景和语言预处理(VLP)在过去两年中取得了显着的进展,但它遭受了重大缺点:VLP型号不断增加的尺寸限制了其部署到现实世界的搜索场景(高潜伏期是不可接受的)。为了减轻此问题,我们提出了一种新颖的插件动态对比度蒸馏(DCD)框架,以压缩ITR任务的大型VLP模型。从技术上讲,我们面临以下两个挑战:1)由于GPU内存有限,在处理交叉模式融合功能期间优化了太多的负样本,因此很难直接应用于跨模式任务,因此很难直接应用于跨模式任务。 。 2)从不同的硬样品中静态优化学生网络的效率效率低下,这些样本对蒸馏学习和学生网络优化具有不同的影响。我们试图从两点克服这些挑战。首先,为了实现多模式对比度学习并平衡培训成本和效果,我们建议使用教师网络估算学生的困难样本,使学生吸收了预培训的老师的强大知识,并掌握知识来自硬样品。其次,要从硬样品对学习动态,我们提出动态蒸馏以动态学习不同困难的样本,从更好地平衡知识和学生的自学能力的困难的角度。我们成功地将我们提出的DCD策略应用于两个最先进的视觉语言预处理模型,即vilt和仪表。关于MS-Coco和FlickR30K基准测试的广泛实验显示了我们DCD框架的有效性和效率。令人鼓舞的是,与现有的ITR型号相比,我们可以至少加快推断至少129美元的$ \ times $。
translated by 谷歌翻译
Recent years have witnessed the rapid progress of image captioning. However, the demands for large memory storage and heavy computational burden prevent these captioning models from being deployed on mobile devices. The main obstacles lie in the heavyweight visual feature extractors (i.e., object detectors) and complicated cross-modal fusion networks. To this end, we propose LightCap, a lightweight image captioner for resource-limited devices. The core design is built on the recent CLIP model for efficient image captioning. To be specific, on the one hand, we leverage the CLIP model to extract the compact grid features without relying on the time-consuming object detectors. On the other hand, we transfer the image-text retrieval design of CLIP to image captioning scenarios by devising a novel visual concept extractor and a cross-modal modulator. We further optimize the cross-modal fusion model and parallel prediction heads via sequential and ensemble distillations. With the carefully designed architecture, our model merely contains 40M parameters, saving the model size by more than 75% and the FLOPs by more than 98% in comparison with the current state-of-the-art methods. In spite of the low capacity, our model still exhibits state-of-the-art performance on prevalent datasets, e.g., 136.6 CIDEr on COCO Karpathy test split. Testing on the smartphone with only a single CPU, the proposed LightCap exhibits a fast inference speed of 188ms per image, which is ready for practical applications.
translated by 谷歌翻译
开放式视频对象检测(OVD)旨在扩展词汇大小,以检测训练词汇以外的新颖类别的对象。最近的工作诉诸于预先训练的视觉模型中的丰富知识。但是,现有方法在提案级视觉语言对准方面无效。同时,这些模型通常遭受对基本类别的信心偏见,并且在新颖的类别上表现较差。为了克服挑战,我们提出了Medet,这是一个新颖有效的OVD框架,并具有建议挖掘和预测均衡。首先,我们设计了一个在线建议挖掘,以完善从粗到细的继承的视觉语义知识,从而允许提案级别以检测为导向的特征对齐。其次,基于因果推论理论,我们引入了班级的后门调整,以加强对新类别的预测,以提高整体OVD性能。对可可和LVIS基准的广泛实验验证了MEDET在检测新型类别的对象(例如可可的32.6%AP50)和LVI上的22.4%蒙版图中的优越性。
translated by 谷歌翻译
我们提出了一种跨模型关注蒸馏框架,用于培训双编码器模型,用于了解视觉语言理解任务,例如视觉推理和视觉问题应答。双编码器模型的推理速度比Fusion-encoder模型更快,并在推理期间启用图像和文本的预算。然而,双编码器模型中使用的浅交互模块不足以处理复杂的视觉语言理解任务。为了学习图像和文本的深度互动,我们引入了跨模型注意蒸馏,它使用融合编码器模型的图像到文本和文本到图像注意力分布来指导我们的双编码器的培训模型。此外,我们表明,适用于预训练和微调阶段的跨模型注意蒸馏实现了进一步的改进。实验结果表明,蒸馏的双编码器模型可实现视觉推理,视觉征求和视觉问题的竞争性能,同时享受比Fusion-Conoder模型更快的推理速度。我们的代码和型号将在https://github.com/kugwzk/distilled -dualiCoder上公开提供。
translated by 谷歌翻译
由于学术和工业领域的异质图无处不在,研究人员最近提出了许多异质图神经网络(HGNN)。在本文中,我们不再采用更强大的HGNN模型,而是有兴趣设计一个多功能的插件模块,该模块解释了从预先训练的HGNN中提取的关系知识。据我们所知,我们是第一个在异质图上提出高阶(雇用)知识蒸馏框架的人,无论HGNN的模型体系结构如何,它都可以显着提高预测性能。具体而言,我们的雇用框架最初执行一阶节点级知识蒸馏,该蒸馏曲线及其预测逻辑编码了老师HGNN的语义。同时,二阶关系级知识蒸馏模仿了教师HGNN生成的不同类型的节点嵌入之间的关系相关性。在各种流行的HGNN模型和三个现实世界的异质图上进行了广泛的实验表明,我们的方法获得了一致且相当大的性能增强,证明了其有效性和泛化能力。
translated by 谷歌翻译
主流对象检测器通常由两个子任务组成,包括由两个并行头部实现的分类和回归任务。这种经典的设计范式不可避免地会导致分类得分和本地化质量(IOU)之间的空间分布不一致。因此,本文从知识蒸馏的角度来减轻这种错位。首先,我们观察到,与轻量级学生相比,庞大的老师获得的和谐预测比例更高。基于这个有趣的观察,设计了一种新颖的和谐评分(HS),以估计分类和回归质量的一致性。 HS对两个子任务之间的关系进行建模,并被视为先验知识,以促进学生的和谐预测。其次,这种空间未对准将在提炼特征时会导致选择性区域的选择。为了减轻这个问题,通过灵活平衡分类和回归任务的贡献,提出了一种新颖的任务功能蒸馏(TFD)。最终,HD和TFD构成了所提出的方法,称为任务均衡蒸馏(TBD)。广泛的实验证明了该方法的巨大潜力和概括。具体而言,当配备TBD时,带有Resnet-50的视网膜在可可基准下获得41.0地图,表现优于最近的FGD和FRS。
translated by 谷歌翻译
现实世界的识别系统在实践中经常遇到许多看不见的标签。为了识别这种看不见的标签,多标签的零光学习(ML-ZSL)着重于通过预先训练的文本标签嵌入(例如,手套)传输知识。但是,这种方法仅利用语言模型利用单极知识,同时忽略了图像文本对固有的丰富语义信息。取而代之的是,最近开发的基于开放式摄影的方法(OV)方法成功地利用了对象检测中图像文本对的此类信息,并实现了令人印象深刻的性能。受基于OV的方法的成功启发,我们提出了一个新型的开放式视频框架,称为多模式知识转移(MKT),用于多标签分类。具体而言,我们的方法利用基于视觉和语言预处理(VLP)模型的图像文本对的多模式知识。为了促进VLP模型的Imagetext匹配能力,使用知识蒸馏来保证图像和标签嵌入的一致性以及及时调整以进一步更新标签嵌入。为了进一步识别多个对象,开发了一个简单但有效的两流模块,以捕获本地和全局功能。广泛的实验结果表明,我们的方法在公共基准数据集上的表现明显优于最先进的方法。代码将在https://github.com/seanhe97/mkt上找到。
translated by 谷歌翻译
知识蒸馏(KD)在将学习表征从大型模型(教师)转移到小型模型(学生)方面表现出非常有希望的能力。但是,随着学生和教师之间的容量差距变得更大,现有的KD方法无法获得更好的结果。我们的工作表明,“先验知识”对KD至关重要,尤其是在应用大型老师时。特别是,我们提出了动态的先验知识(DPK),该知识将教师特征的一部分作为特征蒸馏之前的先验知识。这意味着我们的方法还将教师的功能视为“输入”,而不仅仅是``目标''。此外,我们根据特征差距动态调整训练阶段的先验知识比率,从而引导学生在适当的困难中。为了评估所提出的方法,我们对两个图像分类基准(即CIFAR100和Imagenet)和一个对象检测基准(即MS Coco)进行了广泛的实验。结果表明,在不同的设置下,我们方法在性能方面具有优势。更重要的是,我们的DPK使学生模型的表现与教师模型的表现呈正相关,这意味着我们可以通过应用更大的教师进一步提高学生的准确性。我们的代码将公开用于可重复性。
translated by 谷歌翻译
在这项工作中,我们探讨了用于语义分割知识蒸馏的数据增强。为了避免过度适合教师网络中的噪音,大量培训示例对于知识蒸馏至关重要。 Imagelevel论证技术(例如翻转,翻译或旋转)在先前的知识蒸馏框架中广泛使用。受到功能空间上语义方向的最新进展的启发,我们建议在功能空间中包括以进行有效蒸馏的功能。具体而言,给定语义方向,可以在功能空间中为学生获得无限数量的增强。此外,分析表明,可以通过最大程度地减少增强损失的上限来同时优化这些增强。基于观察结果,开发了一种用于语义分割的知识蒸馏的新算法。对四个语义分割基准测试的广泛实验表明,所提出的方法可以提高当前知识蒸馏方法的性能而没有任何明显的开销。代码可在以下网址获得:https://github.com/jianlong-yuan/fakd。
translated by 谷歌翻译
使用图像文本对的对比语言图像预测(剪辑)在零拍摄和传输学习设置中的图像分类中取得了令人印象深刻的结果。但是,我们表明,直接应用此类模型以识别对象检测的图像区域导致由于域移位导致的性能差:剪辑训练以与文本描述的整体匹配,而不捕获图像之间的细粒度对齐地区和文本跨度。为了缓解此问题,我们提出了一种称为RegionClip的新方法,可显着扩展剪辑以学习区域级视觉表示,从而在图像区域和文本概念之间实现细粒度对齐。我们的方法利用剪辑模型将图像区域与模板标题匹配,然后预先列出我们的模型以对准要素空间中的这些区域文本对。将预磨料模型转移到开放词汇对象检测任务时,我们的方法显着优于3.8 AP50和2.2 AP的最新技术,分别用于COCO和LVIS数据集的新型类别。更多,学习区域表示支持对象检测的零拍摄推断,显示了对COCO和LVIS数据集的有希望的结果。我们的代码可在https://github.com/microsoft/regionclip上获得。
translated by 谷歌翻译