We present ODISE: Open-vocabulary DIffusion-based panoptic SEgmentation, which unifies pre-trained text-image diffusion and discriminative models to perform open-vocabulary panoptic segmentation. Text-to-image diffusion models have the remarkable ability to generate high-quality images with diverse open-vocabulary language descriptions. This demonstrates that their internal representation space is highly correlated with open concepts in the real world. Text-image discriminative models like CLIP, on the other hand, are good at classifying images into open-vocabulary labels. We leverage the frozen internal representations of both these models to perform panoptic segmentation of any category in the wild. Our approach outperforms the previous state of the art by significant margins on both open-vocabulary panoptic and semantic segmentation tasks. In particular, with COCO training only, our method achieves 23.4 PQ and 30.0 mIoU on the ADE20K dataset, with 8.3 PQ and 7.9 mIoU absolute improvement over the previous state of the art. We open-source our code and models at //github.com/NVlabs/ODISE .
相關內容
The recent progress in diffusion-based text-to-image generation models has significantly expanded generative capabilities via conditioning the text descriptions. However, since relying solely on text prompts is still restrictive for fine-grained customization, we aim to extend the boundaries of conditional generation to incorporate diverse types of modalities, e.g., sketch, box, and style embedding, simultaneously. We thus design a multimodal text-to-image diffusion model, coined as DiffBlender, that achieves the aforementioned goal in a single model by training only a few small hypernetworks. DiffBlender facilitates a convenient scaling of input modalities, without altering the parameters of an existing large-scale generative model to retain its well-established knowledge. Furthermore, our study sets new standards for multimodal generation by conducting quantitative and qualitative comparisons with existing approaches. By diversifying the channels of conditioning modalities, DiffBlender faithfully reflects the provided information or, in its absence, creates imaginative generation.
Visual document understanding is a complex task that involves analyzing both the text and the visual elements in document images. Existing models often rely on manual feature engineering or domain-specific pipelines, which limit their generalization ability across different document types and languages. In this paper, we propose DUBLIN, which is pretrained on webpages using three novel objectives that leverage the spatial and semantic information in the document images: Masked Document Content Generation Task, Bounding Box Task, and Rendered Question Answering Task. We evaluate our model on several benchmarks, such as Web-Based Structural Reading Comprehension, Document Visual Question Answering, Key Information Extraction, Diagram Understanding, and Table Question Answering. We show that our model achieves competitive or better results than the state-of-the-art models on these tasks. In particular, we show that DUBLIN is the first pixel-based model to achieve an EM of 77.75 and F1 of 84.25 on the WebSRC dataset. We also show that our model outperforms the current pixel-based SOTA models on DocVQA and AI2D datasets by significant margins, 2% and 21% increase in performance, respectively. Also, DUBLIN is the first ever pixel-based model which achieves comparable to text-based SOTA methods on XFUND dataset for Semantic Entity Recognition showcasing its multilingual capability. Moreover, we create new baselines for text-based datasets by rendering them as document images and applying this model.
Open-vocabulary segmentation of 3D scenes is a fundamental function of human perception and thus a crucial objective in computer vision research. However, this task is heavily impeded by the lack of large-scale and diverse 3D open-vocabulary segmentation datasets for training robust and generalizable models. Distilling knowledge from pre-trained 2D open-vocabulary segmentation models helps but it compromises the open-vocabulary feature significantly as the 2D models are mostly finetuned with close-vocabulary datasets. We tackle the challenges in 3D open-vocabulary segmentation by exploiting the open-vocabulary multimodal knowledge and object reasoning capability of pre-trained foundation models CLIP and DINO, without necessitating any fine-tuning. Specifically, we distill open-vocabulary visual and textual knowledge from CLIP into a neural radiance field (NeRF) which effectively lifts 2D features into view-consistent 3D segmentation. Furthermore, we introduce the Relevancy-Distribution Alignment loss and Feature-Distribution Alignment loss to respectively mitigate the ambiguities of CLIP features and distill precise object boundaries from DINO features, eliminating the need for segmentation annotations during training. Extensive experiments show that our method even outperforms fully supervised models trained with segmentation annotations, suggesting that 3D open-vocabulary segmentation can be effectively learned from 2D images and text-image pairs.
Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, these models fail to semantically align the generated images with the text descriptions due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these three issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending on the predicted boxes, unique mask control is applied to the cross- and self-attention maps. Our approach produces a more semantically accurate synthesis by constraining the attention regions of each token in the prompt to the image. In addition, the proposed method is straightforward and effective, and can be readily integrated into existing cross-attention-diffusion-based T2I generators. We compare our approach to competing methods and demonstrate that it not only faithfully conveys the semantics of the original text to the generated content, but also achieves high availability as a ready-to-use plugin.
This paper presents a controllable text-to-video (T2V) diffusion model, named Video-ControlNet, that generates videos conditioned on a sequence of control signals, such as edge or depth maps. Video-ControlNet is built on a pre-trained conditional text-to-image (T2I) diffusion model by incorporating a spatial-temporal self-attention mechanism and trainable temporal layers for efficient cross-frame modeling. A first-frame conditioning strategy is proposed to facilitate the model to generate videos transferred from the image domain as well as arbitrary-length videos in an auto-regressive manner. Moreover, Video-ControlNet employs a novel residual-based noise initialization strategy to introduce motion prior from an input video, producing more coherent videos. With the proposed architecture and strategies, Video-ControlNet can achieve resource-efficient convergence and generate superior quality and consistent videos with fine-grained control. Extensive experiments demonstrate its success in various video generative tasks such as video editing and video style transfer, outperforming previous methods in terms of consistency and quality. Project Page: //controlavideo.github.io/
Powered by large-scale pre-training, vision foundation models exhibit significant potential in open-world image understanding. Even though individual models have limited capabilities, combining multiple such models properly can lead to positive synergies and unleash their full potential. In this work, we present Matcher, which segments anything with one shot by integrating an all-purpose feature extraction model and a class-agnostic segmentation model. Naively connecting the models results in unsatisfying performance, e.g., the models tend to generate matching outliers and false-positive mask fragments. To address these issues, we design a bidirectional matching strategy for accurate cross-image semantic dense matching and a robust prompt sampler for mask proposal generation. In addition, we propose a novel instance-level matching strategy for controllable mask merging. The proposed Matcher method delivers impressive generalization performance across various segmentation tasks, all without training. For example, it achieves 52.7% mIoU on COCO-20$^i$ for one-shot semantic segmentation, surpassing the state-of-the-art specialist model by 1.6%. In addition, our visualization results show open-world generality and flexibility on images in the wild. The code shall be released at //github.com/aim-uofa/Matcher.
Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text, it is not trivial to extend continuous diffusion models to natural language, and text diffusion models are less studied. Sequence-to-sequence text generation is one of the essential natural language processing topics. In this work, we apply diffusion models to approach sequence-to-sequence text generation, and explore whether the superiority generation performance of diffusion model can transfer to natural language domain. We propose SeqDiffuSeq, a text diffusion model for sequence-to-sequence generation. SeqDiffuSeq uses an encoder-decoder Transformers architecture to model denoising function. In order to improve generation quality, SeqDiffuSeq combines the self-conditioning technique and a newly proposed adaptive noise schedule technique. The adaptive noise schedule has the difficulty of denoising evenly distributed across time steps, and considers exclusive noise schedules for tokens at different positional order. Experiment results illustrate the good performance on sequence-to-sequence generation in terms of text quality and inference time.
In recent years, image generation has shown a great leap in performance, where diffusion models play a central role. Although generating high-quality images, such models are mainly conditioned on textual descriptions. This begs the question: "how can we adopt such models to be conditioned on other modalities?". In this paper, we propose a novel method utilizing latent diffusion models trained for text-to-image-generation to generate images conditioned on audio recordings. Using a pre-trained audio encoding model, the proposed method encodes audio into a new token, which can be considered as an adaptation layer between the audio and text representations. Such a modeling paradigm requires a small number of trainable parameters, making the proposed approach appealing for lightweight optimization. Results suggest the proposed method is superior to the evaluated baseline methods, considering objective and subjective metrics. Code and samples are available at: //pages.cs.huji.ac.il/adiyoss-lab/AudioToken.
The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It designed a novel promotable segmentation task, ensuring zero-shot image segmentation using the pre-trained model via two main modes including automatic everything and manual prompt. SAM has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging due to the complex modalities, fine anatomical structures, uncertain and complex object boundaries, and wide-range object scales. Meanwhile, zero-shot and efficient MIS can well reduce the annotation time and boost the development of medical image analysis. Hence, SAM seems to be a potential tool and its performance on large medical datasets should be further validated. We collected and sorted 52 open-source datasets, and built a large medical segmentation dataset with 16 modalities, 68 objects, and 553K slices. We conducted a comprehensive analysis of different SAM testing strategies on the so-called COSMOS 553K dataset. Extensive experiments validate that SAM performs better with manual hints like points and boxes for object perception in medical images, leading to better performance in prompt mode compared to everything mode. Additionally, SAM shows remarkable performance in some specific objects and modalities, but is imperfect or even totally fails in other situations. Finally, we analyze the influence of different factors (e.g., the Fourier-based boundary complexity and size of the segmented objects) on SAM's segmentation performance. Extensive experiments validate that SAM's zero-shot segmentation capability is not sufficient to ensure its direct application to the MIS.
Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread of pre-training models for NLP applications, they almost focused on text-level manipulation, while neglecting the layout and style information that is vital for document image understanding. In this paper, we propose the LayoutLM to jointly model the interaction between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned documents. Furthermore, we also leverage the image features to incorporate the visual information of words into LayoutLM. To the best of our knowledge, this is the first time that text and layout are jointly learned in a single framework for document-level pre-training. It achieves new state-of-the-art results in several downstream tasks, including form understanding (from 70.72 to 79.27), receipt understanding (from 94.02 to 95.24) and document image classification (from 93.07 to 94.42). The code and pre-trained LayoutLM models are publicly available at //github.com/microsoft/unilm/tree/master/layoutlm.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191