Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and quality of web-crawled data that naturally contain incomplete and noisy information (e.g., wrong or irrelevant content). Existing works either design manual rules to clean data or generate pseudo-targets as auxiliary signals for reducing noise impact, which do not explicitly tackle both the incorrect and incomplete challenges simultaneously. In this paper, to automatically mitigate the impact of noise by solely mining over existing data, we propose a principled Noise-robust Language-Image Pre-training framework (NLIP) to stabilize pre-training via two schemes: noise-harmonization and noise-completion. First, in noise-harmonization scheme, NLIP estimates the noise probability of each pair according to the memorization effect of cross-modal transformers, then adopts noise-adaptive regularization to harmonize the cross-modal alignments with varying degrees. Second, in noise-completion scheme, to enrich the missing object information of text, NLIP injects a concept-conditioned cross-modal decoder to obtain semantic-consistent synthetic captions to complete noisy ones, which uses the retrieved visual concepts (i.e., objects' names) for the corresponding image to guide captioning generation. By collaboratively optimizing noise-harmonization and noise-completion schemes, our NLIP can alleviate the common noise effects during image-text pre-training in a more efficient way. Extensive experiments show the significant performance improvements of our NLIP using only 26M data over existing pre-trained models (e.g., CLIP, FILIP and BLIP) on 12 zero-shot classification datasets, MSCOCO image captioning and zero-shot image-text retrieval tasks.

Geometry problem solving is a well-recognized testbed for evaluating the high-level multi-modal reasoning capability of deep models. In most existing works, two main geometry problems: calculation and proving, are usually treated as two specific tasks, hindering a deep model to unify its reasoning capability on multiple math tasks. However, in essence, these two tasks have similar problem representations and overlapped math knowledge which can improve the understanding and reasoning ability of a deep model on both two tasks. Therefore, we construct a large-scale Unified Geometry problem benchmark, UniGeo, which contains 4,998 calculation problems and 9,543 proving problems. Each proving problem is annotated with a multi-step proof with reasons and mathematical expressions. The proof can be easily reformulated as a proving sequence that shares the same formats with the annotated program sequence for calculation problems. Naturally, we also present a unified multi-task Geometric Transformer framework, Geoformer, to tackle calculation and proving problems simultaneously in the form of sequence generation, which finally shows the reasoning ability can be improved on both two tasks by unifying formulation. Furthermore, we propose a Mathematical Expression Pretraining (MEP) method that aims to predict the mathematical expressions in the problem solution, thus improving the Geoformer model. Experiments on the UniGeo demonstrate that our proposed Geoformer obtains state-of-the-art performance by outperforming task-specific model NGS with over 5.6% and 3.2% accuracies on calculation and proving problems, respectively.

Referring image segmentation aims at localizing all pixels of the visual objects described by a natural language sentence. Previous works learn to straightforwardly align the sentence embedding and pixel-level embedding for highlighting the referred objects, but ignore the semantic consistency of pixels within the same object, leading to incomplete masks and localization errors in predictions. To tackle this problem, we propose CoupAlign, a simple yet effective multi-level visual-semantic alignment method, to couple sentence-mask alignment with word-pixel alignment to enforce object mask constraint for achieving more accurate localization and segmentation. Specifically, the Word-Pixel Alignment (WPA) module performs early fusion of linguistic and pixel-level features in intermediate layers of the vision and language encoders. Based on the word-pixel aligned embedding, a set of mask proposals are generated to hypothesize possible objects. Then in the Sentence-Mask Alignment (SMA) module, the masks are weighted by the sentence embedding to localize the referred object, and finally projected back to aggregate the pixels for the target. To further enhance the learning of the two alignment modules, an auxiliary loss is designed to contrast the foreground and background pixels. By hierarchically aligning pixels and masks with linguistic features, our CoupAlign captures the pixel coherence at both visual and semantic levels, thus generating more accurate predictions. Extensive experiments on popular datasets (e.g., RefCOCO and G-Ref) show that our method achieves consistent improvements over state-of-the-art methods, e.g., about 2% oIoU increase on the validation and testing set of RefCOCO. Especially, CoupAlign has remarkable ability in distinguishing the target from multiple objects of the same class.

Text-guided 3D object generation aims to generate 3D objects described by user-defined captions, which paves a flexible way to visualize what we imagined. Although some works have been devoted to solving this challenging task, these works either utilize some explicit 3D representations (e.g., mesh), which lack texture and require post-processing for rendering photo-realistic views; or require individual time-consuming optimization for every single case. Here, we make the first attempt to achieve generic text-guided cross-category 3D object generation via a new 3D-TOGO model, which integrates a text-to-views generation module and a views-to-3D generation module. The text-to-views generation module is designed to generate different views of the target 3D object given an input caption. prior-guidance, caption-guidance and view contrastive learning are proposed for achieving better view-consistency and caption similarity. Meanwhile, a pixelNeRF model is adopted for the views-to-3D generation module to obtain the implicit 3D neural representation from the previously-generated views. Our 3D-TOGO model generates 3D objects in the form of the neural radiance field with good texture and requires no time-cost optimization for every single caption. Besides, 3D-TOGO can control the category, color and shape of generated 3D objects with the input caption. Extensive experiments on the largest 3D object dataset (i.e., ABO) are conducted to verify that 3D-TOGO can better generate high-quality 3D objects according to the input captions across 98 different categories, in terms of PSNR, SSIM, LPIPS and CLIP-score, compared with text-NeRF and Dreamfields.

开放世界对象检测是一个更具笼统和挑战性的目标，旨在识别和本地化由任意类别名称描述的对象。最近的工作GLIP通过将检测数据集的所有类别名称连接到句子中，从而将此问题作为接地问题，从而导致类别名称之间的效率低下的相互作用。本文介绍了Distclip，这是一种通过诉诸于设计概念词典的知识富集，是一种平行的视觉概念训练预训练方法，用于开放世界检测。为了提高学习效率，我们提出了一种新型的并行概念公式，该公式分别提取概念，以更好地利用异质数据集（即检测，接地和图像文本对）进行培训。我们进一步设计了来自各种在线资源和检测数据集的概念字典〜（带有描述），以提供每个概念的先验知识。通过用描述丰富这些概念，我们明确地建立了各种概念之间的关系，以促进开放域学习。所提出的概念词典进一步用于提供足够的负面概念，用于构建单词区域对齐损失\，并完成图像对文本对数据标题中缺少描述的对象的标签。所提出的框架显示出强烈的零射击性能性能，例如，在LVIS数据集上，我们的DETCLIP-T优于9.9％的地图GLIPT-T优于GLIP-T，并且与完全避免的型号相比，稀有类别的稀有类别提高了13.5％。作为我们的。

为了同时朝着对多个下游任务的整体理解，需要提取具有更好可传递性的功能。尽管许多最新的自我监管的预训练方法在普遍的预处理前范式下在各种视觉任务上取得了令人印象深刻的表现，但它们对多任务学习方案的概括能力尚待探索。在本文中，我们在三个下游任务上进行了广泛研究各种类型的自我监督方法的转移性能，例如Moco和Simc​​lr，包括语义细分，可驱动的区域细分和交通对象检测，在大规模驾驶数据集中BDD100K。我们出人意料地发现，他们的表现是最佳的甚至落后于单任务基线的滞后，这可能是由于训练目标和建筑设计的区别在于预处理范式。为了克服这一难题，并避免重新设计资源密集的预培训阶段，我们提出了一种简单而有效的预处理 - 适应性 - 赛范围，用于一般的多任务培训，可以有效地适应现行预审预周态的模型没有增加培训开销。在自适应阶段，我们利用可学习的多尺度适配器来动态调整由多任务目标监督的预验证的模型权重，同时使经过预告片的知识未经触及。此外，我们将视觉语言预训练模型剪辑视为对预处理 - 适应 - 最终范式的强烈补充，并提出了一个名为LV-Adapter的新型适配器，该适配器通过任务特定的提示将语言先验纳入了多任务的模型中和视觉和文本特征之间的对齐。

跨模式时尚图像合成已成为一代域中最有前途的方向之一，因为巨大的未开发的潜力融合了多种方式和广泛的时尚图像应用。为了促进准确的生成，跨模式合成方法通常依赖于对比的语言图像预训练（剪辑）来对齐文本和服装信息。在这项工作中，我们认为，简单地对齐纹理和服装信息不足以捕获视觉信息的语义，因此提出了maskClip。 MaskClip将服装分解为语义部分，以确保视觉和文本信息之间的细粒度和语义准确对齐。在MaskClip上，我们建议Armani，这是一位统一的跨模式时装设计师，具有零件级的服装文本对齐。 Armani在第一阶段将图像分散成统一令牌，并使用变压器在第二阶段的控制信号的标记中使用变压器为真实图像的图像令牌进行建模。与同样依赖两阶段范式的先前方法相反，Armani将文本令牌引入了代码簿中，使该模型可以利用细粒语义信息来生成更真实的图像。此外，通过引入跨模式变压器，Armani具有通用性，可以从各种控制信号（例如纯文本，草图图像和部分图像）中完成图像合成。在我们新收集的跨模式时尚数据集上进行的广泛实验表明，Armani在不同的合成任务中生成了光真实的图像，并且优于现有的最先进的跨模式图像综合方法。 github.com/harvey594/armani。

真实世界的文本应用程序通常涉及组成广泛的文本控制操作，例如编辑文本W.R.T.属性，操纵关键字和结构，并生成所需属性的新文本。事先的工作通常会学习/芬太尼语言模型（LM）以执行操作的个人或特定子集。最近的研究以插件方式研究了合并操作，通常在复杂序列空间中以昂贵的搜索或优化进行了研究。本文提出了一种新的有效方法，用于在紧凑的文本潜在空间中进行可复合的文本操作。文本潜在矢量的低维度和不同性使我们能够基于给定的任意插入运算符（例如属性分类器）基于普通微分方程（ODE）开发有效的采样器。通过通过有效的适应性将预告片的LMS（例如GPT2）连接到潜在空间，然后我们将采样向量解码为所需的文本序列。灵活的方法允许使用来自不同域中的任何相关数据获取的各种控制操作员（情感，时态，形式，关键字等）。实验表明，在我们的方法中构成这些操作员可以生成或编辑高质量文本，从而在发电质量和效率方面显着改善了以前的方法。

基于图像的虚拟试验是以人为中心的现实潜力，是以人为中心的图像生成的最有希望的应用之一。在这项工作中，我们迈出了一步，探索多功能的虚拟尝试解决方案，我们认为这应该具有三个主要属性，即，它们应支持无监督的培训，任意服装类别和可控的服装编辑。为此，我们提出了一个特征性的端到端网络，即用空间自适应的斑点适应性GAN ++（Pasta-gan ++），以实现用于高分辨率不合规的虚拟试验的多功能系统。具体而言，我们的意大利面++由一个创新的贴布贴片的拆卸模块组成，可以将完整的服装切换为归一化贴剂，该贴片能够保留服装样式信息，同时消除服装空间信息，从而减轻在未受监督训练期间过度适应的问题。此外，面食++引入了基于贴片的服装表示和一个贴片引导的解析合成块，使其可以处理任意服装类别并支持本地服装编辑。最后，为了获得具有逼真的纹理细节的尝试结果，面食gan ++结合了一种新型的空间自适应残留模块，以将粗翘曲的服装功能注入发电机。对我们新收集的未配对的虚拟试验（UPT）数据集进行了广泛的实验，证明了面食gan ++比现有SOTA的优越性及其可控服装编辑的能力。

在本文中，我们研究了如何使用现代视觉语言变形金刚实现更好的视觉接地，并为这项具有挑战性的任务提出了一种简单而强大的选择性训练（SIRI）机制。特别是，Siri传达了视觉接地研究的重要原则，即更好的初始视觉语言编码器将帮助该模型收敛到更好的局部最低限度，从而相应地提高性能。具体而言，随着训练的进行，我们不断更新编码器的参数，而定期重新定位的其余参数则可以根据增强的编码来更好地优化模型。 Siri在三个流行的基准测试中可以大大优于以前的方法。具体而言，我们的方法在Refcoco+ Testa上达到了83.04％的TOP1精度，超过了最先进的方法（从头开始训练）超过10.21％。此外，我们透露，即使培训数据有限，Siri也表现出色。我们还将其扩展到基于变压器的视觉接地模型和其他视觉语言任务，以验证有效性。