Spatial understanding is a fundamental aspect of computer vision and integral for human-level reasoning about images, making it an important component for grounded language understanding. While recent large-scale text-to-image synthesis (T2I) models have shown unprecedented improvements in photorealism, it is unclear whether they have reliable spatial understanding capabilities. We investigate the ability of T2I models to generate correct spatial relationships among objects and present VISOR, an evaluation metric that captures how accurately the spatial relationship described in text is generated in the image. To benchmark existing models, we introduce a large-scale challenge dataset SR2D that contains sentences describing two objects and the spatial relationship between them. We construct and harness an automated evaluation pipeline that employs computer vision to recognize objects and their spatial relationships, and we employ it in a large-scale evaluation of T2I models. Our experiments reveal a surprising finding that, although recent state-of-the-art T2I models exhibit high image quality, they are severely limited in their ability to generate multiple objects or the specified spatial relations such as left/right/above/below. Our analyses demonstrate several biases and artifacts of T2I models such as the difficulty with generating multiple objects, a bias towards generating the first object mentioned, spatially inconsistent outputs for equivalent relationships, and a correlation between object co-occurrence and spatial understanding capabilities. We conduct a human study that shows the alignment between VISOR and human judgment about spatial understanding. We offer the SR2D dataset and the VISOR metric to the community in support of T2I spatial reasoning research.

Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to input text prompts, while consistent with input images. We present Imagen Editor, a cascaded diffusion model built, by fine-tuning Imagen on text-guided image inpainting. Imagen Editor's edits are faithful to the text prompts, which is accomplished by using object detectors to propose inpainting masks during training. In addition, Imagen Editor captures fine details in the input image by conditioning the cascaded pipeline on the original high resolution image. To improve qualitative and quantitative evaluation, we introduce EditBench, a systematic benchmark for text-guided image inpainting. EditBench evaluates inpainting edits on natural and generated images exploring objects, attributes, and scenes. Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.

我们介绍了自回归文本到图像（Parti）模型的途径，该模型生成高保真的影像图像并支持涉及复杂组成和世界知识的内容丰富的合成。 Parti将文本对图像生成视为类似于机器翻译的序列到序列建模问题，图像令牌的序列是目标输出，而不是其他语言的文本令牌。这种策略自然可以利用大型语言模型的先前工作，通过扩展数据和模型尺寸，能力和性能的持续进展。我们的方法很简单：首先，Parti使用基于变压器的图像令牌VIT-VQGAN将图像编码为离散令牌的序列。其次，我们通过将编码器二次变压器模型缩放到20B参数来实现一致的质量改进，其新的最新零弹药FID得分为7.23，而MS-Coco的FIDED得分为3.22。我们对本地化叙述以及党的详细分析（P2），这是1600多个英语提示的新的整体基准，证明了Parti在各种类别和难度方面的有效性。我们还探索并突出了我们的模型的局限性，以定义和体现关注重点领域以进一步改进。有关高分辨率图像，请参见https://parti.research.google/。

Creativity is an indispensable part of human cognition and also an inherent part of how we make sense of the world. Metaphorical abstraction is fundamental in communicating creative ideas through nuanced relationships between abstract concepts such as feelings. While computer vision benchmarks and approaches predominantly focus on understanding and generating literal interpretations of images, metaphorical comprehension of images remains relatively unexplored. Towards this goal, we introduce MetaCLUE, a set of vision tasks on visual metaphor. We also collect high-quality and rich metaphor annotations (abstract objects, concepts, relationships along with their corresponding object boxes) as there do not exist any datasets that facilitate the evaluation of these tasks. We perform a comprehensive analysis of state-of-the-art models in vision and language based on our annotations, highlighting strengths and weaknesses of current approaches in visual metaphor Classification, Localization, Understanding (retrieval, question answering, captioning) and gEneration (text-to-image synthesis) tasks. We hope this work provides a concrete step towards developing AI systems with human-like creative capabilities.

Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such zero-shot performance of CLIP-based models does not realize in tasks that require a finer-grained correspondence between vision and language, such as Visual Question Answering (VQA). We investigate why this is the case, and report an interesting phenomenon of CLIP, which we call the Concept Association Bias (CAB), as a potential cause of the difficulty of applying CLIP to VQA and similar tasks. CAB is especially apparent when two concepts are present in the given image while a text prompt only contains a single concept. In such a case, we find that CLIP tends to treat input as a bag of concepts and attempts to fill in the other missing concept crossmodally, leading to an unexpected zero-shot prediction. For example, when asked for the color of a lemon in an image, CLIP predicts ``purple'' if the image contains a lemon and an eggplant. We demonstrate the Concept Association Bias of CLIP by showing that CLIP's zero-shot classification performance greatly suffers when there is a strong concept association between an object (e.g. lemon) and an attribute (e.g. its color). On the other hand, when the association between object and attribute is weak, we do not see this phenomenon. Furthermore, we show that CAB is significantly mitigated when we enable CLIP to learn deeper structure across image and text embeddings by adding an additional Transformer on top of CLIP and fine-tuning it on VQA. We find that across such fine-tuned variants of CLIP, the strength of CAB in a model predicts how well it performs on VQA.

通用视觉（GPV）系统是旨在解决各种视觉任务的模型，而无需进行架构更改。如今，GPV主要从大型完全监督的数据集中学习技能和概念。通过获取数据以迅速学习每个技能的每个概念，将GPV扩展到数万个概念都变得令人望而却步。这项工作提出了一种有效且廉价的替代方法：从监督数据集中学习技能，从Web图像搜索中学习概念，并利用GPV的关键特征：跨技能传递视觉知识的能力。我们使用跨越10K+视觉概念的1M+图像的数据集来演示3个基准上的两个现有GPV（GPV-1和VL-T5）的Webly Supumented概念扩展：5个基于可可的数据集（80个主要概念），这是一个新的策划系列，这是一个新的策划系列。基于OpenImages和VisualGenome存储库（〜500个概念）以及Web衍生的数据集（10K+概念）的5个数据集。我们还提出了一种新的体系结构GPV-2，该架构支持各种任务 - 从分类和本地化等视觉任务到Qu Viewer+语言任务，例如QA和字幕，再到更多的利基市场，例如人类对象互动检测。 GPV-2从Web数据中受益匪浅，并且在这些基准测试中胜过GPV-1和VL-T5。我们的数据，代码和Web演示可在https://prior.allenai.org/projects/gpv2上获得。

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in

A major goal of multimodal research is to improve machine understanding of images and text. Tasks include image captioning, text-to-image generation, and vision-language representation learning. So far, research has focused on the relationships between images and text. For example, captioning models attempt to understand the semantics of images which are then transformed into text. An important question is: which annotation reflects best a deep understanding of image content? Similarly, given a text, what is the best image that can present the semantics of the text? In this work, we argue that the best text or caption for a given image is the text which would generate the image which is the most similar to that image. Likewise, the best image for a given text is the image that results in the caption which is best aligned with the original text. To this end, we propose a unified framework that includes both a text-to-image generative model and an image-to-text generative model. Extensive experiments validate our approach.

Multimodal image-text models have shown remarkable performance in the past few years. However, evaluating their robustness against distribution shifts is crucial before adopting them in real-world applications. In this paper, we investigate the robustness of 9 popular open-sourced image-text models under common perturbations on five tasks (image-text retrieval, visual reasoning, visual entailment, image captioning, and text-to-image generation). In particular, we propose several new multimodal robustness benchmarks by applying 17 image perturbation and 16 text perturbation techniques on top of existing datasets. We observe that multimodal models are not robust to image and text perturbations, especially to image perturbations. Among the tested perturbation methods, character-level perturbations constitute the most severe distribution shift for text, and zoom blur is the most severe shift for image data. We also introduce two new robustness metrics (MMI and MOR) for proper evaluations of multimodal models. We hope our extensive study sheds light on new directions for the development of robust multimodal models.

A fundamental characteristic common to both human vision and natural language is their compositional nature. Yet, despite the performance gains contributed by large vision and language pretraining, we find that - across 6 architectures trained with 4 algorithms on massive datasets - they exhibit little compositionality. To arrive at this conclusion, we introduce a new compositionality evaluation benchmark CREPE which measures two important aspects of compositionality identified by cognitive science literature: systematicity and productivity. To measure systematicity, CREPE consists of three test datasets. The three test sets are designed to test models trained on three of the popular training datasets: CC-12M, YFCC-15M, and LAION-400M. They contain 385K, 385K, and 373K image-text pairs and 237K, 210K, and 178K hard negative captions. To test productivity, CREPE contains 17K image-text pairs with nine different complexities plus 246K hard negative captions with atomic, swapping, and negation foils. The datasets are generated by repurposing the Visual Genome scene graphs and region descriptions and applying handcrafted templates and GPT-3. For systematicity, we find that model performance decreases consistently when novel compositions dominate the retrieval set, with Recall@1 dropping by up to 8%. For productivity, models' retrieval success decays as complexity increases, frequently nearing random chance at high complexity. These results hold regardless of model and training dataset size.

We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ∼0.25M images, ∼0.76M questions, and ∼10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines and methods for VQA are provided and compared with human performance. Our VQA demo is available on CloudCV (http://cloudcv.org/vqa).

Shape can specify key object constraints, yet existing text-to-image diffusion models ignore this cue and synthesize objects that are incorrectly scaled, cut off, or replaced with background content. We propose a training-free method, Shape-Guided Diffusion, which uses a novel Inside-Outside Attention mechanism to constrain the cross-attention (and self-attention) maps such that prompt tokens (and pixels) referring to the inside of the shape cannot attend outside the shape, and vice versa. To demonstrate the efficacy of our method, we propose a new image editing task where the model must replace an object specified by its mask and a text prompt. We curate a new ShapePrompts benchmark based on MS-COCO and achieve SOTA results in shape faithfulness, text alignment, and realism according to both quantitative metrics and human preferences. Our data and code will be made available at https://shape-guided-diffusion.github.io.

Large-scale diffusion models have achieved state-of-the-art results on text-to-image synthesis (T2I) tasks. Despite their ability to generate high-quality yet creative images, we observe that attribution-binding and compositional capabilities are still considered major challenging issues, especially when involving multiple objects. In this work, we improve the compositional skills of T2I models, specifically more accurate attribute binding and better image compositions. To do this, we incorporate linguistic structures with the diffusion guidance process based on the controllable properties of manipulating cross-attention layers in diffusion-based T2I models. We observe that keys and values in cross-attention layers have strong semantic meanings associated with object layouts and content. Therefore, we can better preserve the compositional semantics in the generated image by manipulating the cross-attention representations based on linguistic insights. Built upon Stable Diffusion, a SOTA T2I model, our structured cross-attention design is efficient that requires no additional training samples. We achieve better compositional skills in qualitative and quantitative results, leading to a 5-8% advantage in head-to-head user comparison studies. Lastly, we conduct an in-depth analysis to reveal potential causes of incorrect image compositions and justify the properties of cross-attention layers in the generation process.

Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on billion-sized datasets randomly scraped from the internet, they also suffer, as we demonstrate, from degenerated and biased human behavior. In turn, they may even reinforce such biases. To help combat these undesired side effects, we present safe latent diffusion (SLD). Specifically, to measure the inappropriate degeneration due to unfiltered and imbalanced training sets, we establish a novel image generation test bed-inappropriate image prompts (I2P)-containing dedicated, real-world image-to-text prompts covering concepts such as nudity and violence. As our exhaustive empirical evaluation demonstrates, the introduced SLD removes and suppresses inappropriate image parts during the diffusion process, with no additional training required and no adverse effect on overall image quality or text alignment.

最近的文本到图像匹配模型对大型图像和句子的大公司进行了对比学习。虽然这些模型可以提供用于匹配和随后的零拍任务的强大分数，但它们不能给出给定图像的标题。在这项工作中，我们重新利用这些模型来生成在推理时间的图像时生成描述性文本，而无需进一步的训练或调整步骤。这是通过将具有大语言模型的视觉语义模型组合，从两种网络级模型中的知识中获益。由受监督标题方法获得的标题的限制性较小。此外，作为零射击学习方法，它非常灵活，我们展示了执行图像算法的能力，其中输入可以是图像或文本，输出是句子。这使得新颖的高级视觉能力，例如比较两个图像或解决视觉类比测试。

人们说：“一张照片值一千字”。那么，我们如何从图像中获取丰富的信息？我们认为，通过使用视觉线索来桥接大型的识别视觉基础模型和语言模型，我们可以无需任何额外的跨模式训练。得益于基础模型的强大零拍功能，我们首先构建图像的丰富语义表示（例如，图像标签，对象属性 /位置，字幕）作为结构化的文本提示，称为视觉线索，使用视觉基础模型。基于视觉线索，我们使用大型语言模型为视觉内容生成一系列综合描述，然后再次通过视觉模型验证，以选择与图像最合适的候选人。我们通过定量和定性测量评估生成的描述的质量。结果证明了这种结构化语义表示的有效性。

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}.

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.

最近的方法表明，直接在大规模图像文本对集合上训练深神网络可以在各种识别任务上进行零拍传输。一个中心问题是如何将其推广到对象检测，这涉及本地化的非语义任务以及分类的语义任务。为了解决这个问题，我们引入了一种视觉嵌入对准方法，该方法将审计模型（例如夹子）（例如夹子）的概括能力传输到像Yolov5这样的对象检测器。我们制定了一个损耗函数，使我们能够将图像和文本嵌入在预审计的模型夹中对齐与检测器的修改语义预测头。通过这种方法，我们能够训练一个对象检测器，该对象检测器可以在可可，ILSVRC和视觉基因组零摄像机检测基准上实现最先进的性能。在推断期间，我们的模型可以适应以检测任何数量的对象类，而无需其他培训。我们还发现，标准对象检测缩放可以很好地传输到我们的方法，并在Yolov5模型和Yolov3模型的各种尺度上找到一致的改进。最后，我们开发了一种自我标记的方法，该方法可提供显着的分数改进，而无需额外的图像或标签。

通过使用图像文本匹配模型的使用，零光学习在计算机视觉中的应用已彻底改变。最值得注意的示例，剪辑，已广泛用于带有文本提示的零摄像分类和指导生成模型。但是，对于输入文本的措辞，夹子的零拍情况不稳定，因此有必要仔细设计所用的提示。我们发现这种不稳定性源于选择性相似性分数，该得分仅基于语义上有意义的输入令牌的子集。为了减轻它，我们提出了一种新颖的基于可解释的方法，该方法增加了损失术语，以确保剪辑专注于输入的所有相关语义部分，此外还采用了以前的作品中使用的夹子相似性损失。当通过及时的工程应用于单发分类时，我们的方法可以提高识别率，而无需进行额外的培训或微调。此外，我们表明使用我们的方法对生成模型的剪辑指导显着改善了生成的图像。最后，我们通过在对象位置进行空间条件来证明对基于文本的图像生成的新颖使用，这是需要将图像解释性热图限制在预定的边界框中。