NeurIPS 2023 论文列表

Generative Adversarial Networks (GANs) are powerful tools for image synthesis. However, they require access to vast amounts of training data, which is often costly and prohibitive. Limited data affects GANs, leading to discriminator overfitting and training instability. In this paper, we present a novel approach called NoIse-modulated Consistency rEgularization (NICE) to overcome these challenges. To this end, we introduce an adaptive multiplicative noise into the discriminator to modulate its latent features. We demonstrate the effectiveness of such a modulation in preventing discriminator overfitting by adaptively reducing the Rademacher complexity of the discriminator. However, this modulation leads to an unintended consequence of increased gradient norm, which can undermine the stability of GAN training. To mitigate this undesirable effect, we impose a constraint on the discriminator, ensuring its consistency for the same inputs under different noise modulations. The constraint effectively penalizes the first and second-order gradients of latent features, enhancing GAN stability. Experimental evidence aligns with our theoretical analysis, demonstrating the reduction of generalization error and gradient penalization of NICE. This substantiates the efficacy of NICE in reducing discriminator overfitting and improving stability of GAN training. NICE achieves state-of-the-art results on CIFAR-10, CIFAR-100, ImageNet and FFHQ datasets when trained with limited data, as well as in low-shot generation tasks.

Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the issue, we study how Large Language Models (LLMs) can serve as visual planners by generating layouts from text conditions, and thus collaborate with visual generative models. We propose LayoutGPT, a method to compose in-context visual demonstrations in style sheet language to enhance visual planning skills of LLMs. We show that LayoutGPT can generate plausible layouts in multiple domains, ranging from 2D images to 3D indoor scenes. LayoutGPT also shows superior performance in converting challenging language concepts like numerical and spatial relations to layout arrangements for faithful text-to-image generation. When combined with a downstream image generation model, LayoutGPT outperforms text-to-image models/systems by 20-40\% and achieves comparable performance as human users in designing visual layouts for numerical and spatial correctness. Lastly, LayoutGPT achieves comparable performance to supervised methods in 3D indoor scene synthesis, demonstrating its effectiveness and potential in multiple visual domains.

Text-to-image generation models represent the next step of evolution in image synthesis, offering a natural way to achieve flexible yet fine-grained control over the result. One emerging area of research is the fast adaptation of large text-to-image models to smaller datasets or new visual concepts. However, many efficient methods of adaptation have a long training time, which limits their practical applications, slows down experiments, and spends excessive GPU resources. In this work, we study the training dynamics of popular text-to-image personalization methods (such as Textual Inversion or DreamBooth), aiming to speed them up. We observe that most concepts are learned at early stages and do not improve in quality later, but standard training convergence metrics fail to indicate that. Instead, we propose a simple drop-in early stopping criterion that only requires computing the regular training objective on a fixed set of inputs for all training iterations. Our experiments on Stable Diffusion for 48 different concepts and three personalization methods demonstrate the competitive performance of our approach, which makes adaptation up to 8 times faster with no significant drops in quality.

Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multimodal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

Recent breakthroughs in diffusion models, multimodal pretraining, and efficient finetuning have led to an explosion of text-to-image generative models. Given human evaluation is expensive and difficult to scale, automated methods are critical for evaluating the increasingly large number of new models. However, most current automated evaluation metrics like FID or CLIPScore only offer a distribution-level measure of image quality or image-text alignment, and are unsuited for fine-grained or instance-level analysis. In this paper, we introduce GenEval, an object-focused framework to evaluate compositional image properties such as object co-occurrence, position, count, and color. We show that current object detection models can be leveraged to evaluate text-to-image models on a variety of generation tasks with strong human agreement, and that other discriminative vision models can be linked to this pipeline to further verify properties like object color. We then evaluate several open-source text-to-image models and analyze their relative reasoning capabilities on our benchmark. We find that recent models demonstrate significant improvement on these tasks, though they are still lacking in complex capabilities such as spatial relations and attribute binding. Finally, we demonstrate how GenEval might be used to help discover existing failure modes, in order to inform development of the next generation of text-to-image models. Our code to run the GenEval framework will be made publicly available at https://github.com/djghosh13/geneval.

Backdoor attacks inject poisoned samples into the training data, resulting in the misclassification of the poisoned input during a model's deployment. Defending against such attacks is challenging, especially for real-world black-box models where only query access is permitted. In this paper, we propose a novel defense framework against backdoor attacks through Zero-shot Image Purification (ZIP). Our framework can be applied to poisoned models without requiring internal information about the model or any prior knowledge of the clean/poisoned samples. Our defense framework involves two steps. First, we apply a linear transformation (e.g., blurring) on the poisoned image to destroy the backdoor pattern. Then, we use a pre-trained diffusion model to recover the missing semantic information removed by the transformation. In particular, we design a new reverse process by using the transformed image to guide the generation of high-fidelity purified images, which works in zero-shot settings. We evaluate our ZIP framework on multiple datasets with different types of attacks. Experimental results demonstrate the superiority of our ZIP framework compared to state-of-the-art backdoor defense baselines. We believe that our results will provide valuable insights for future defense methods for black-box models. Our code is available at https://github.com/sycny/ZIP.

Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. However, despite their success, text descriptions often struggle to adequately convey detailed controls, even when composed of long and complex texts. Moreover, recent studies have also shown that these models face challenges in understanding such complex texts and generating the corresponding images. Therefore, there is a growing need to enable more control modes beyond text description. In this paper, we introduce Uni-ControlNet, a unified framework that allows for the simultaneous utilization of different local controls (e.g., edge maps, depth map, segmentation masks) and global controls (e.g., CLIP image embeddings) in a flexible and composable manner within one single model. Unlike existing methods, Uni-ControlNet only requires the fine-tuning of two additional adapters upon frozen pre-trained text-to-image diffusion models, eliminating the huge cost of training from scratch. Moreover, thanks to some dedicated adapter designs, Uni-ControlNet only necessitates a constant number (i.e., 2) of adapters, regardless of the number of local or global controls used. This not only reduces the fine-tuning costs and model size, making it more suitable for real-world deployment, but also facilitate composability of different conditions. Through both quantitative and qualitative comparisons, Uni-ControlNet demonstrates its superiority over existing methods in terms of controllability, generation quality and composability. Code is available at https://github.com/ShihaoZhaoZSH/Uni-ControlNet.

Video generation necessitates both global coherence and local realism. This work presents a novel non-autoregressive method GLOBER, which first generates global features to obtain comprehensive global guidance and then synthesizes video frames based on the global features to generate coherent videos. Specifically, we propose a video auto-encoder, where a video encoder encodes videos into global features, and a video decoder, built on a diffusion model, decodes the global features and synthesizes video frames in a non-autoregressive manner. To achieve maximum flexibility, our video decoder perceives temporal information through normalized frame indexes, which enables it to synthesize arbitrary sub video clips with predetermined starting and ending frame indexes. Moreover, a novel adversarial loss is introduced to improve the global coherence and local realism between the synthesized video frames. Finally, we employ a diffusion-based video generator to fit the global features outputted by the video encoder for video generation. Extensive experimental results demonstrate the effectiveness and efficiency of our proposed method, and new state-of-the-art results have been achieved on multiple benchmarks.

Although supervised image denoising networks have shown remarkable performance on synthesized noisy images, they often fail in practice due to the difference between real and synthesized noise. Since clean-noisy image pairs from the real world are extremely costly to gather, self-supervised learning, which utilizes noisy input itself as a target, has been studied. To prevent a self-supervised denoising model from learning identical mapping, each output pixel should not be influenced by its corresponding input pixel; This requirement is known as J-invariance. Blind-spot networks (BSNs) have been a prevalent choice to ensure J-invariance in self-supervised image denoising. However, constructing variations of BSNs by injecting additional operations such as downsampling can expose blinded information, thereby violating J-invariance. Consequently, convolutions designed specifically for BSNs have been allowed only, limiting architectural flexibility. To overcome this limitation, we propose PUCA, a novel J-invariant U-Net architecture, for self-supervised denoising. PUCA leverages patch-unshuffle/shuffle to dramatically expand receptive fields while maintaining J-invariance and dilated attention blocks (DABs) for global context incorporation. Experimental results demonstrate that PUCA achieves state-of-the-art performance, outperforming existing methods in self-supervised image denoising.

Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation. This issue is often attributed to exposure bias -- the difference between how a model is trained, and how it is used during inference. Denoising diffusion models provide an alternative approach in which a model can revisit and revise its output. However, they can be computationally expensive and prior efforts on text have led to models that produce less fluent output compared to autoregressive models, especially for longer text and paragraphs. In this paper, we propose PLANNER, a model that combines latent semantic diffusion with autoregressive generation, to generate fluent text while exercising global control over paragraphs. The model achieves this by combining an autoregressive "decoding" module with a "planning" module that uses latent diffusion to generate semantic paragraph embeddings in a coarse-to-fine manner. The proposed method is evaluated on various conditional generation tasks, and results on semantic generation, text completion and summarization show its effectiveness in generating high-quality long-form text in an efficient manner.

Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released, and the collection process has not been fully specified. We introduce the OBELICS dataset, an open web-scale filtered dataset of interleaved image-text documents comprising 141 million web pages extracted from Common Crawl, 353 million associated images, and 115 billion text tokens. We describe the dataset creation process, present comprehensive filtering rules, and provide an analysis of the dataset's content. To show the viability of OBELICS, we train on the dataset vision and language models of 9 and 80 billion parameters, IDEFICS-9B and IDEFICS, and obtain competitive performance on different multimodal benchmarks. We release our dataset, models and code.

Diffusion-based image generation models, such as Stable Diffusion or DALL·E 2, are able to learn from given images and generate high-quality samples following the guidance from prompts. For instance, they can be used to create artistic images that mimic the style of an artist based on his/her original artworks or to maliciously edit the original images for fake content. However, such ability also brings serious ethical issues without proper authorization from the owner of the original images. In response, several attempts have been made to protect the original images from such unauthorized data usage by adding imperceptible perturbations, which are designed to mislead the diffusion model and make it unable to properly generate new samples. In this work, we introduce a perturbation purification platform, named IMPRESS, to evaluate the effectiveness of imperceptible perturbations as a protective measure. IMPRESS is based on the key observation that imperceptible perturbations could lead to a perceptible inconsistency between the original image and the diffusion-reconstructed image, which can be used to devise a new optimization strategy for purifying the image, which may weaken the protection of the original image from unauthorized data usage (e.g., style mimicking, malicious editing). The proposed IMPRESS platform offers a comprehensive evaluation of several contemporary protection methods, and can be used as an evaluation platform for future protection methods.

Existing works have advanced Text-to-Image (TTI) diffusion models for video editing in a one-shot learning manner. Despite their low requirements of data and computation, these methods might produce results of unsatisfied consistency with text prompt as well as temporal sequence, limiting their applications in the real world. In this paper, we propose to address the above issues with a novel EI$^2$ model towards Enhancing vIdeo Editing consIstency of TTI-based frameworks. Specifically, we analyze and find that the inconsistent problem is caused by newly added modules into TTI models for learning temporal information. These modules lead to covariate shift in the feature space, which harms the editing capability. Thus, we design EI$^2$ to tackle the above drawbacks with two classical modules: Shift-restricted Temporal Attention Module (STAM) and Fine-coarse Frame Attention Module (FFAM). First, through theoretical analysis, we demonstrate that covariate shift is highly related to Layer Normalization, thus STAM employs a Instance Centering layer replacing it to preserve the distribution of temporal features. In addition, STAM employs an attention layer with normalized mapping to transform temporal features while constraining the variance shift. As the second part, we incorporate STAM with a novel FFAM, which efficiently leverages fine-coarse spatial information of overall frames to further enhance temporal consistency. Extensive experiments demonstrate the superiority of the proposed EI$^2$ model.

We present DiffInfinite, a hierarchical diffusion model that generates arbitrarily large histological images while preserving long-range correlation structural information. Our approach first generates synthetic segmentation masks, subsequently used as conditions for the high-fidelity generative diffusion process. The proposed sampling method can be scaled up to any desired image size while only requiring small patches for fast training. Moreover, it can be parallelized more efficiently than previous large-content generation methods while avoiding tiling artifacts. The training leverages classifier-free guidance to augment a small, sparsely annotated dataset with unlabelled data. Our method alleviates unique challenges in histopathological imaging practice: large-scale information, costly manual annotation, and protective data handling. The biological plausibility of DiffInfinite data is evaluated in a survey by ten experienced pathologists as well as a downstream classification and segmentation task. Samples from the model score strongly on anti-copying metrics which is relevant for the protection of patient data.

Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A prevailing perspective in deep learning encourages using highly complex data for training, with the expectation that richer image background content will facilitate overcoming the generalization problem. However, through comprehensive and systematic experimentation, we discover that this strategy does not enhance the generalization capability of these networks. On the contrary, it exacerbates the tendency of networks to overfit specific degradations. Our experiments reveal that better generalization in a deraining network can be achieved by simplifying the complexity of the training background images. This is because that the networks are ``slacking off'' during training, that is, learning the least complex elements in the image background and degradation to minimize training loss. When the background images are less complex than the rain streaks, the network will prioritize the background reconstruction, thereby suppressing overfitting the rain patterns and leading to improved generalization performance. Our research offers a valuable perspective and methodology for better understanding the generalization problem in low-level vision tasks and displays promising potential for practical application.

Semantic image synthesis (SIS) aims to generate realistic images according to semantic masks given by a user. Although recent methods produce high quality results with fine spatial control, SIS requires expensive pixel-level annotation of the training images. On the other hand, manipulating intermediate feature maps in a pretrained unconditional generator such as StyleGAN supports coarse spatial control without heavy annotation. In this paper, we introduce a new approach, for reflecting user's detailed guiding masks on a pretrained unconditional generator. Our method converts a user's guiding mask to a proxy mask through a semantic mapper. Then the proxy mask conditions the resulting image through a rearranging network based on cross-attention mechanism. The proxy mask is simple clustering of intermediate feature maps in the generator. The semantic mapper and the rearranging network are easy to train (less than half an hour). Our method is useful for many tasks: semantic image synthesis, spatially editing real images, and unaligned local transplantation. Last but not least, it is generally applicable to various datasets such as human faces, animal faces, and churches.

The remarkable capabilities of pretrained image diffusion models have been utilized not only for generating fixed-size images but also for creating panoramas. However, naive stitching of multiple images often results in visible seams. Recent techniques have attempted to address this issue by performing joint diffusions in multiple windows and averaging latent features in overlapping regions. However, these approaches, which focus on seamless montage generation, often yield incoherent outputs by blending different scenes within a single image. To overcome this limitation, we propose SyncDiffusion, a plug-and-play module that synchronizes multiple diffusions through gradient descent from a perceptual similarity loss. Specifically, we compute the gradient of the perceptual loss using the predicted denoised images at each denoising step, providing meaningful guidance for achieving coherent montages. Our experimental results demonstrate that our method produces significantly more coherent outputs compared to previous methods (66.35% vs. 33.65% in our user study) while still maintaining fidelity (as assessed by GIQA) and compatibility with the input prompt (as measured by CLIP score). We further demonstrate the versatility of our method across three plug-and-play applications: layout-guided image generation, conditional image generation and 360-degree panorama generation. Our project page is at https://syncdiffusion.github.io.

Recent accelerations in multi-modal applications have been made possible with the plethora of image and text data available online. However, the scarcity of analogous data in the medical field, specifically in histopathology, has slowed comparable progress. To enable similar representation learning for histopathology, we turn to YouTube, an untapped resource of videos, offering $1,087$ hours of valuable educational histopathology videos from expert clinicians. From YouTube, we curate QUILT: a large-scale vision-language dataset consisting of $802, 144$ image and text pairs. QUILT was automatically curated using a mixture of models, including large language models, handcrafted algorithms, human knowledge databases, and automatic speech recognition. In comparison, the most comprehensive datasets curated for histopathology amass only around $200$K samples. We combine QUILT with datasets from other sources, including Twitter, research papers, and the internet in general, to create an even larger dataset: QUILT-1M, with $1$M paired image-text samples, marking it as the largest vision-language histopathology dataset to date. We demonstrate the value of QUILT-1M by fine-tuning a pre-trained CLIP model. Our model outperforms state-of-the-art models on both zero-shot and linear probing tasks for classifying new histopathology images across $13$ diverse patch-level datasets of $8$ different sub-pathologies and cross-modal retrieval tasks.

Existing automatic evaluation on text-to-image synthesis can only provide an image-text matching score, without considering the object-level compositionality, which results in poor correlation with human judgments. In this work, we propose LLMScore, a new framework that offers evaluation scores with multi-granularity compositionality. LLMScore leverages the large language models (LLMs) to evaluate text-to-image models. Initially, it transforms the image into image-level and object-level visual descriptions. Then an evaluation instruction is fed into the LLMs to measure the alignment between the synthesized image and the text, ultimately generating a score accompanied by a rationale. Our substantial analysis reveals the highest correlation of LLMScore with human judgments on a wide range of datasets (Attribute Binding Contrast, Concept Conjunction, MSCOCO, DrawBench, PaintSkills). Notably, our LLMScore achieves Kendall's tau correlation with human evaluations that is 58.8% and 31.2% higher than the commonly-used text-image matching metrics CLIP and BLIP, respectively.