Personalized text-to-image (T2I) synthesis based on diffusion models has attracted significant attention in recent research. However, existing methods primarily concentrate on customizing subjects or styles, neglecting the exploration of global geometry. In this study, we propose an approach that focuses on the customization of 360-degree panoramas, which inherently possess global geometric properties, using a T2I diffusion model. To achieve this, we curate a paired image-text dataset specifically designed for the task and subsequently employ it to fine-tune a pre-trained T2I diffusion model with LoRA. Nevertheless, the fine-tuned model alone does not ensure the continuity between the leftmost and rightmost sides of the synthesized images, a crucial characteristic of 360-degree panoramas. To address this issue, we propose a method called StitchDiffusion. Specifically, we perform pre-denoising operations twice at each time step of the denoising process on the stitch block consisting of the leftmost and rightmost image regions. Furthermore, a global cropping is adopted to synthesize seamless 360-degree panoramas. Experimental results demonstrate the effectiveness of our customized model combined with the proposed StitchDiffusion in generating high-quality 360-degree panoramic images. Moreover, our customized model exhibits exceptional generalization ability in producing scenes unseen in the fine-tuning dataset. Code is available at https://github.com/littlewhitesea/StitchDiffusion.
Visual-language pre-training (VLP) have achieved remarkable success in multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that multi-modal large language models (MLLMs) can enhance visual-language representation learning by improving data quality. Our approach is simple, utilizing MLLMs to extend multiple captions for each image. To prevent the bias that introduced by MLLMs' hallucinations and intrinsic caption styles, we propose a "text shearing" to keep the lengths of extended captions identical to the originals. In image-text retrieval, our method consistently obtains 5.6 ~ 35.0% and 16.8 ~ 46.1% improvement on R@1 under the fine-tuning and zero-shot settings, respectively. Notably, our zero-shot results are comparable to fine-tuning on target datasets, which encourages more exploration on the versatile use of MLLMs.
Obtaining large-scale radiology reports can be difficult for medical images due to various reasons, limiting the effectiveness of contrastive pre-training in the medical image domain and underscoring the need for alternative methods. In this paper, we propose eye-tracking as an alternative to text reports, as it allows for the passive collection of gaze signals without disturbing radiologist's routine diagnosis process. By tracking the gaze of radiologists as they read and diagnose medical images, we can understand their visual attention and clinical reasoning. When a radiologist has similar gazes for two medical images, it may indicate semantic similarity for diagnosis, and these images should be treated as positive pairs when pre-training a computer-assisted diagnosis (CAD) network through contrastive learning. Accordingly, we introduce the Medical contrastive Gaze Image Pre-training (McGIP) as a plug-and-play module for contrastive learning frameworks. McGIP uses radiologist's gaze to guide contrastive pre-training. We evaluate our method using two representative types of medical images and two common types of gaze data. The experimental results demonstrate the practicality of McGIP, indicating its high potential for various clinical scenarios and applications.
Transfer learning of large-scale Text-to-Image (T2I) models has recently shown impressive potential for Novel View Synthesis (NVS) of diverse objects from a single image. While previous methods typically train large models on multi-view datasets for NVS, fine-tuning the whole parameters of T2I models not only demands a high cost but also reduces the generalization capacity of T2I models in generating diverse images in a new domain. In this study, we propose an effective method, dubbed NVS-Adapter, which is a plug-and-play module for a T2I model, to synthesize novel multi-views of visual objects while fully exploiting the generalization capacity of T2I models. NVS-Adapter consists of two main components; view-consistency cross-attention learns the visual correspondences to align the local details of view features, and global semantic conditioning aligns the semantic structure of generated views with the reference view. Experimental results demonstrate that the NVS-Adapter can effectively synthesize geometrically consistent multi-views and also achieve high performance on benchmarks without full fine-tuning of T2I models. The code and data are publicly available in ~\href{https://postech-cvlab.github.io/nvsadapter/}{https://postech-cvlab.github.io/nvsadapter/}.
Embeddings are a basic initial feature extraction step in many machine learning models, particularly in natural language processing. An embedding attempts to map data tokens to a low-dimensional space where similar tokens are mapped to vectors that are close to one another by some metric in the embedding space. A basic question is how well can such embedding be learned? To study this problem, we consider a simple probability model for discrete data where there is some "true" but unknown embedding where the correlation of random variables is related to the similarity of the embeddings. Under this model, it is shown that the embeddings can be learned by a variant of low-rank approximate message passing (AMP) method. The AMP approach enables precise predictions of the accuracy of the estimation in certain high-dimensional limits. In particular, the methodology provides insight on the relations of key parameters such as the number of samples per value, the frequency of the terms, and the strength of the embedding correlation on the probability distribution. Our theoretical findings are validated by simulations on both synthetic data and real text data.
In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt. However, obtaining desired editing results conformed with the editing prompt is nontrivial since there exist two significant challenges, including accurate editing of only foreground regions and multi-view consistency given a single-view reference image. To tackle the first challenge, we propose a Local-Global Iterative Editing (LGIE) training scheme that alternates between foreground region editing and full-image editing, aimed at foreground-only manipulation while preserving the background. For the second challenge, we also design a class-guided regularization that exploits class priors within the generation model to alleviate the inconsistency problem among different views in image-driven editing. Extensive experiments show that our CustomNeRF produces precise editing results under various real scenes for both text- and image-driven settings.
Image animation is a key task in computer vision which aims to generate dynamic visual content from static image. Recent image animation methods employ neural based rendering technique to generate realistic animations. Despite these advancements, achieving fine-grained and controllable image animation guided by text remains challenging, particularly for open-domain images captured in diverse real environments. In this paper, we introduce an open domain image animation method that leverages the motion prior of video diffusion model. Our approach introduces targeted motion area guidance and motion strength guidance, enabling precise control the movable area and its motion speed. This results in enhanced alignment between the animated visual elements and the prompting text, thereby facilitating a fine-grained and interactive animation generation process for intricate motion sequences. We validate the effectiveness of our method through rigorous experiments on an open-domain dataset, with the results showcasing its superior performance. Project page can be found at https://animationai.github.io/AnimateAnything.
Text-to-image diffusion models have remarkably excelled in producing diverse, high-quality, and photo-realistic images. This advancement has spurred a growing interest in incorporating specific identities into generated content. Most current methods employ an inversion approach to embed a target visual concept into the text embedding space using a single reference image. However, the newly synthesized faces either closely resemble the reference image in terms of facial attributes, such as expression, or exhibit a reduced capacity for identity preservation. Text descriptions intended to guide the facial attributes of the synthesized face may fall short, owing to the intricate entanglement of identity information with identity-irrelevant facial attributes derived from the reference image. To address these issues, we present the novel use of the extended StyleGAN embedding space $\mathcal{W}_+$, to achieve enhanced identity preservation and disentanglement for diffusion models. By aligning this semantically meaningful human face latent space with text-to-image diffusion models, we succeed in maintaining high fidelity in identity preservation, coupled with the capacity for semantic editing. Additionally, we propose new training objectives to balance the influences of both prompt and identity conditions, ensuring that the identity-irrelevant background remains unaffected during facial attribute modifications. Extensive experiments reveal that our method adeptly generates personalized text-to-image outputs that are not only compatible with prompt descriptions but also amenable to common StyleGAN editing directions in diverse settings. Our source code will be available at \url{https://github.com/csxmli2016/w-plus-adapter}.
Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients' data. User heterogeneity is a significant challenge for FL, which together with the class-distribution imbalance further enhances the difficulty of FL. Great progress has been made in large vision-language models, such as Contrastive Language-Image Pre-training (CLIP), which paves a new way for image classification and object recognition. Inspired by the success of CLIP on few-shot and zero-shot learning, we use CLIP to optimize the federated learning between server and client models under its vision-language supervision. It is promising to mitigate the user heterogeneity and class-distribution balance due to the powerful cross-modality representation and rich open-vocabulary prior knowledge. In this paper, we propose the CLIP-guided FL (CLIP2FL) method on heterogeneous and long-tailed data. In CLIP2FL, the knowledge of the off-the-shelf CLIP model is transferred to the client-server models, and a bridge is built between the client and server. Specifically, for client-side learning, knowledge distillation is conducted between client models and CLIP to improve the ability of client-side feature representation. For server-side learning, in order to mitigate the heterogeneity and class-distribution imbalance, we generate federated features to retrain the server model. A prototype contrastive learning with the supervision of the text encoder of CLIP is introduced to generate federated features depending on the client-side gradients, and they are used to retrain a balanced server classifier.
Incremental Learning (IL) has been a long-standing problem in both vision and Natural Language Processing (NLP) communities. In recent years, as Pre-trained Language Models (PLMs) have achieved remarkable progress in various NLP downstream tasks, utilizing PLMs as backbones has become a common practice in recent research of IL in NLP. Most assume that catastrophic forgetting is the biggest obstacle to achieving superior IL performance and propose various techniques to overcome this issue. However, we find that this assumption is problematic. Specifically, we revisit more than 20 methods on four classification tasks (Text Classification, Intent Classification, Relation Extraction, and Named Entity Recognition) under the two most popular IL settings (Class-Incremental and Task-Incremental) and reveal that most of them severely underestimate the inherent anti-forgetting ability of PLMs. Based on the observation, we propose a frustratingly easy method called SEQ* for IL with PLMs. The results show that SEQ* has competitive or superior performance compared to state-of-the-art (SOTA) IL methods and requires considerably less trainable parameters and training time. These findings urge us to revisit the IL with PLMs and encourage future studies to have a fundamental understanding of the catastrophic forgetting in PLMs. The data, code and scripts are publicly available at https://github.com/zzz47zzz/pretrained-lm-for-incremental-learning.