In computer-assisted surgery, automatically recognizing anatomical organs is crucial for understanding the surgical scene and providing intraoperative assistance. While machine learning models can identify such structures, their deployment is hindered by the need for labeled, diverse surgical datasets with anatomical annotations. Labeling multiple classes (i.e., organs) in a surgical scene is time-intensive, requiring medical experts. Although synthetically generated images can enhance segmentation performance, maintaining both organ structure and texture during generation is challenging. We introduce a multi-stage approach using diffusion models to generate multi-class surgical datasets with annotations. Our framework improves anatomy awareness by training organ specific models with an inpainting objective guided by binary segmentation masks. The organs are generated with an inference pipeline using pre-trained ControlNet to maintain the organ structure. The synthetic multi-class datasets are constructed through an image composition step, ensuring structural and textural consistency. This versatile approach allows the generation of multi-class datasets from real binary datasets and simulated surgical masks. We thoroughly evaluate the generated datasets on image quality and downstream segmentation, achieving a $15\%$ improvement in segmentation scores when combined with real images. The code is available at https://gitlab.com/nct_tso_public/muli-class-image-synthesis
3D-aware image generation necessitates extensive training data to ensure stable training and mitigate the risk of overfitting. This paper first considers a novel task known as One-shot 3D Generative Domain Adaptation (GDA), aimed at transferring a pre-trained 3D generator from one domain to a new one, relying solely on a single reference image. One-shot 3D GDA is characterized by the pursuit of specific attributes, namely, high fidelity, large diversity, cross-domain consistency, and multi-view consistency. Within this paper, we introduce 3D-Adapter, the first one-shot 3D GDA method, for diverse and faithful generation. Our approach begins by judiciously selecting a restricted weight set for fine-tuning, and subsequently leverages four advanced loss functions to facilitate adaptation. An efficient progressive fine-tuning strategy is also implemented to enhance the adaptation process. The synergy of these three technological components empowers 3D-Adapter to achieve remarkable performance, substantiated both quantitatively and qualitatively, across all desired properties of 3D GDA. Furthermore, 3D-Adapter seamlessly extends its capabilities to zero-shot scenarios, and preserves the potential for crucial tasks such as interpolation, reconstruction, and editing within the latent space of the pre-trained generator. Code will be available at https://github.com/iceli1007/3D-Adapter.
Diffusion models excel at generating high-dimensional data but fall short in training efficiency and representation quality compared to self-supervised methods. We identify a key bottleneck: the underutilization of high-quality, semantically rich representations during training notably slows down convergence. Our systematic analysis reveals a critical representation processing region -- primarily in the early layers -- where semantic and structural pattern learning takes place before generation can occur. To address this, we propose Embedded Representation Warmup (ERW), a plug-and-play framework where in the first stage we get the ERW module serves as a warmup that initializes the early layers of the diffusion model with high-quality, pretrained representations. This warmup minimizes the burden of learning representations from scratch, thereby accelerating convergence and boosting performance. Our theoretical analysis demonstrates that ERW's efficacy depends on its precise integration into specific neural network layers -- termed the representation processing region -- where the model primarily processes and transforms feature representations for later generation. We further establish that ERW not only accelerates training convergence but also enhances representation quality: empirically, our method achieves a 40$\times$ acceleration in training speed compared to REPA, the current state-of-the-art methods. Code is available at https://github.com/LINs-lab/ERW.
Large-scale text-to-image diffusion models have been a revolutionary milestone in the evolution of generative AI and multimodal technology, allowing wonderful image generation with natural-language text prompt. However, the issue of lacking controllability of such models restricts their practical applicability for real-life content creation. Thus, attention has been focused on leveraging a reference image to control text-to-image synthesis, which is also regarded as manipulating (or editing) a reference image as per a text prompt, namely, text-driven image-to-image translation. This paper contributes a novel, concise, and efficient approach that adapts pre-trained large-scale text-to-image (T2I) diffusion model to the image-to-image (I2I) paradigm in a plug-and-play manner, realizing high-quality and versatile text-driven I2I translation without any model training, model fine-tuning, or online optimization process. To guide T2I generation with a reference image, we propose to decompose diverse guiding factors with different frequency bands of diffusion features in the DCT spectral space, and accordingly devise a novel frequency band substitution layer which realizes dynamic control of the reference image to the T2I generation result in a plug-and-play manner. We demonstrate that our method allows flexible control over both guiding factor and guiding intensity of the reference image simply by tuning the type and bandwidth of the substituted frequency band, respectively. Extensive qualitative and quantitative experiments verify superiority of our approach over related methods in I2I translation visual quality, versatility, and controllability. The code is publicly available at: https://github.com/XiangGao1102/FBSDiff.
In this paper, we present Morse, a simple dual-sampling framework for accelerating diffusion models losslessly. The key insight of Morse is to reformulate the iterative generation (from noise to data) process via taking advantage of fast jump sampling and adaptive residual feedback strategies. Specifically, Morse involves two models called Dash and Dot that interact with each other. The Dash model is just the pre-trained diffusion model of any type, but operates in a jump sampling regime, creating sufficient space for sampling efficiency improvement. The Dot model is significantly faster than the Dash model, which is learnt to generate residual feedback conditioned on the observations at the current jump sampling point on the trajectory of the Dash model, lifting the noise estimate to easily match the next-step estimate of the Dash model without jump sampling. By chaining the outputs of the Dash and Dot models run in a time-interleaved fashion, Morse exhibits the merit of flexibly attaining desired image generation performance while improving overall runtime efficiency. With our proposed weight sharing strategy between the Dash and Dot models, Morse is efficient for training and inference. Our method shows a lossless speedup of 1.78X to 3.31X on average over a wide range of sampling step budgets relative to 9 baseline diffusion models on 6 image generation tasks. Furthermore, we show that our method can be also generalized to improve the Latent Consistency Model (LCM-SDXL, which is already accelerated with consistency distillation technique) tailored for few-step text-to-image synthesis. The code and models are available at https://github.com/deep-optimization/Morse.
Sign language gloss translation aims to translate the sign glosses into spoken language texts, which is challenging due to the scarcity of labeled gloss-text parallel data. Back translation (BT), which generates pseudo-parallel data by translating in-domain spoken language texts into sign glosses, has been applied to alleviate the data scarcity problem. However, the lack of large-scale high-quality domain spoken language text data limits the effect of BT. In this paper, to overcome the limitation, we propose a Prompt based domain text Generation (PGEN) approach to produce the large-scale in-domain spoken language text data. Specifically, PGEN randomly concatenates sentences from the original in-domain spoken language text data as prompts to induce a pre-trained language model (i.e., GPT-2) to generate spoken language texts in a similar style. Experimental results on three benchmarks of sign language gloss translation in varied languages demonstrate that BT with spoken language texts generated by PGEN significantly outperforms the compared methods. In addition, as the scale of spoken language texts generated by PGEN increases, the BT technique can achieve further improvements, demonstrating the effectiveness of our approach. We release the code and data for facilitating future research in this field.
Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training methods perform well on understanding table structures, but they still struggle with tasks that require various table reasoning skills. In this work, we develop ReasTAP to show that high-level table reasoning skills can be injected into models during pre-training without a complex table-specific architecture design. We define 7 table reasoning skills, such as numerical operation, temporal comparison, and conjunction. Each reasoning skill is associated with one example generator, which synthesizes questions over semi-structured tables according to the sampled templates. We model the table pre-training task as a sequence generation task and pre-train ReasTAP to generate precise answers to the synthetic examples. ReasTAP is evaluated on four benchmarks covering three downstream tasks including: 1) WikiSQL and WTQ for Table Question Answering; 2) TabFact for Table Fact Verification; and 3) LogicNLG for Faithful Table-to-Text Generation. Experimental results demonstrate that ReasTAP achieves new state-of-the-art performance on all benchmarks and delivers a significant improvement on low-resource setting. Our code is publicly available at https://github.com/Yale-LILY/ReasTAP.
Fast screening and diagnosis are critical in COVID-19 patient treatment. In addition to the gold standard RT-PCR, radiological imaging like X-ray and CT also works as an important means in patient screening and follow-up. However, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists. To reduce the workload of radiologists, we propose DeltaNet to generate medical reports automatically. Different from typical image captioning approaches that generate reports with an encoder and a decoder, DeltaNet applies a conditional generation process. In particular, given a medical image, DeltaNet employs three steps to generate a report: 1) first retrieving related medical reports, i.e., the historical reports from the same or similar patients; 2) then comparing retrieved images and current image to find the differences; 3) finally generating a new report to accommodate identified differences based on the conditional report. We evaluate DeltaNet on a COVID-19 dataset, where DeltaNet outperforms state-of-the-art approaches. Besides COVID-19, the proposed DeltaNet can be applied to other diseases as well. We validate its generalization capabilities on the public IU-Xray and MIMIC-CXR datasets for chest-related diseases. Code is available at \url{https://github.com/LX-doctorAI1/DeltaNet}.
Image-to-image translation (I2I) methods allow the generation of artificial images that share the content of the original image but have a different style. With the advances in Generative Adversarial Networks (GANs)-based methods, I2I methods enabled the generation of artificial images that are indistinguishable from natural images. Recently, I2I methods were also employed in histopathology for generating artificial images of in silico stained tissues from a different type of staining. We refer to this process as stain transfer. The number of I2I variants is constantly increasing, which makes a well justified choice of the most suitable I2I methods for stain transfer challenging. In our work, we compare twelve stain transfer approaches, three of which are based on traditional and nine on GAN-based image processing methods. The analysis relies on complementary quantitative measures for the quality of image translation, the assessment of the suitability for deep learning-based tissue grading, and the visual evaluation by pathologists. Our study highlights the strengths and weaknesses of the stain transfer approaches, thereby allowing a rational choice of the underlying I2I algorithms. Code, data, and trained models for stain transfer between H&E and Masson's Trichrome staining will be made available online.
Video generation remains a challenging task due to spatiotemporal complexity and the requirement of synthesizing diverse motions with temporal consistency. Previous works attempt to generate videos in arbitrary lengths either in an autoregressive manner or regarding time as a continuous signal. However, they struggle to synthesize detailed and diverse motions with temporal coherence and tend to generate repetitive scenes after a few time steps. In this work, we argue that a single time-agnostic latent vector of style-based generator is insufficient to model various and temporally-consistent motions. Hence, we introduce additional time-dependent motion styles to model diverse motion patterns. In addition, a Motion Style Attention modulation mechanism, dubbed as MoStAtt, is proposed to augment frames with vivid dynamics for each specific scale (i.e., layer), which assigns attention score for each motion style w.r.t deconvolution filter weights in the target synthesis layer and softly attends different motion styles for weight modulation. Experimental results show our model achieves state-of-the-art performance on four unconditional $256^2$ video synthesis benchmarks trained with only 3 frames per clip and produces better qualitative results with respect to dynamic motions. Code and videos have been made available at https://github.com/xiaoqian-shen/MoStGAN-V.
Large language models (LLMs) specializing in natural language generation (NLG) have recently started exhibiting promising capabilities across a variety of domains. However, gauging the trustworthiness of responses generated by LLMs remains an open challenge, with limited research on uncertainty quantification (UQ) for NLG. Furthermore, existing literature typically assumes white-box access to language models, which is becoming unrealistic either due to the closed-source nature of the latest LLMs or computational constraints. In this work, we investigate UQ in NLG for *black-box* LLMs. We first differentiate *uncertainty* vs *confidence*: the former refers to the ``dispersion'' of the potential predictions for a fixed input, and the latter refers to the confidence on a particular prediction/generation. We then propose and compare several confidence/uncertainty measures, applying them to *selective NLG* where unreliable results could either be ignored or yielded for further assessment. Experiments were carried out with several popular LLMs on question-answering datasets (for evaluation purposes). Results reveal that a simple measure for the semantic dispersion can be a reliable predictor of the quality of LLM responses, providing valuable insights for practitioners on uncertainty management when adopting LLMs. The code to replicate our experiments is available at https://github.com/zlin7/UQ-NLG.
Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the reverse generation process, without modifying the original denoising diffusion process. However, since the degraded images already include low-frequency information, starting from Gaussian white noise will result in increased sampling steps. We propose Resfusion, a general framework that incorporates the residual term into the diffusion forward process, starting the reverse process directly from the noisy degraded images. The form of our inference process is consistent with the DDPM. We introduced a weighted residual noise, named resnoise, as the prediction target and explicitly provide the quantitative relationship between the residual term and the noise term in resnoise. By leveraging a smooth equivalence transformation, Resfusion determine the optimal acceleration step and maintains the integrity of existing noise schedules, unifying the training and inference processes. The experimental results demonstrate that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps. Furthermore, Resfusion can be easily applied to image generation and emerges with strong versatility. Our code and model are available at https://github.com/nkicsl/Resfusion.
Recently, Vision Language Models (VLMs) have experienced significant advancements, yet these models still face challenges in spatial hierarchical reasoning within indoor scenes. In this study, we introduce ROOT, a VLM-based system designed to enhance the analysis of indoor scenes. Specifically, we first develop an iterative object perception algorithm using GPT-4V to detect object entities within indoor scenes. This is followed by employing vision foundation models to acquire additional meta-information about the scene, such as bounding boxes. Building on this foundational data, we propose a specialized VLM, SceneVLM, which is capable of generating spatial hierarchical scene graphs and providing distance information for objects within indoor environments. This information enhances our understanding of the spatial arrangement of indoor scenes. To train our SceneVLM, we collect over 610,000 images from various public indoor datasets and implement a scene data generation pipeline with a semi-automated technique to establish relationships and estimate distances among indoor objects. By utilizing this enriched data, we conduct various training recipes and finish SceneVLM. Our experiments demonstrate that \rootname facilitates indoor scene understanding and proves effective in diverse downstream applications, such as 3D scene generation and embodied AI. The code will be released at \url{https://github.com/harrytea/ROOT}.
Colloquially speaking, image generation models based upon diffusion processes are frequently said to exhibit "hallucinations," samples that could never occur in the training data. But where do such hallucinations come from? In this paper, we study a particular failure mode in diffusion models, which we term mode interpolation. Specifically, we find that diffusion models smoothly "interpolate" between nearby data modes in the training set, to generate samples that are completely outside the support of the original training distribution; this phenomenon leads diffusion models to generate artifacts that never existed in real data (i.e., hallucinations). We systematically study the reasons for, and the manifestation of this phenomenon. Through experiments on 1D and 2D Gaussians, we show how a discontinuous loss landscape in the diffusion model's decoder leads to a region where any smooth approximation will cause such hallucinations. Through experiments on artificial datasets with various shapes, we show how hallucination leads to the generation of combinations of shapes that never existed. Finally, we show that diffusion models in fact know when they go out of support and hallucinate. This is captured by the high variance in the trajectory of the generated sample towards the final few backward sampling process. Using a simple metric to capture this variance, we can remove over 95% of hallucinations at generation time while retaining 96% of in-support samples. We conclude our exploration by showing the implications of such hallucination (and its removal) on the collapse (and stabilization) of recursive training on synthetic data with experiments on MNIST and 2D Gaussians dataset. We release our code at https://github.com/locuslab/diffusion-model-hallucination.
Ultra-Wide-Field Fluorescein Angiography (UWF-FA) enables precise identification of ocular diseases using sodium fluorescein, which can be potentially harmful. Existing research has developed methods to generate UWF-FA from Ultra-Wide-Field Scanning Laser Ophthalmoscopy (UWF-SLO) to reduce the adverse reactions associated with injections. However, these methods have been less effective in producing high-quality late-phase UWF-FA, particularly in lesion areas and fine details. Two primary challenges hinder the generation of high-quality late-phase UWF-FA: the scarcity of paired UWF-SLO and early/late-phase UWF-FA datasets, and the need for realistic generation at lesion sites and potential blood leakage regions. This study introduces an improved latent diffusion model framework to generate high-quality late-phase UWF-FA from limited paired UWF images. To address the challenges as mentioned earlier, our approach employs a module utilizing Cross-temporal Regional Difference Loss, which encourages the model to focus on the differences between early and late phases. Additionally, we introduce a low-frequency enhanced noise strategy in the diffusion forward process to improve the realism of medical images. To further enhance the mapping capability of the variational autoencoder module, especially with limited datasets, we implement a Gated Convolutional Encoder to extract additional information from conditional images. Our Latent Diffusion Model for Ultra-Wide-Field Late-Phase Fluorescein Angiography (LPUWF-LDM) effectively reconstructs fine details in late-phase UWF-FA and achieves state-of-the-art results compared to other existing methods when working with limited datasets. Our source code is available at: https://github.com/Tinysqua/****.
This paper proposes an end-to-end deep hashing framework with category mask for fast video retrieval. We train our network in a supervised way by fully exploiting inter-class diversity and intra-class identity. Classification loss is optimized to maximize inter-class diversity, while intra-pair is introduced to learn representative intra-class identity. We investigate the binary bits distribution related to categories and find out that the effectiveness of binary bits is highly correlated with data categories, and some bits may degrade classification performance of some categories. We then design hash code generation scheme with category mask to filter out bits with negative contribution. Experimental results demonstrate the proposed method outperforms several state-of-the-arts under various evaluation metrics on public datasets.
Despite the recent emergence of video captioning models, how to generate vivid, fine-grained video descriptions based on the background knowledge (i.e., long and informative commentary about the domain-specific scenes with appropriate reasoning) is still far from being solved, which however has great applications such as automatic sports narrative. In this paper, we present GOAL, a benchmark of over 8.9k soccer video clips, 22k sentences, and 42k knowledge triples for proposing a challenging new task setting as Knowledge-grounded Video Captioning (KGVC). Moreover, we conduct experimental adaption of existing methods to show the difficulty and potential directions for solving this valuable and applicable task. Our data and code are available at https://github.com/THU-KEG/goal.
Diffusion models have emerged as powerful generative tools, rivaling GANs in sample quality and mirroring the likelihood scores of autoregressive models. A subset of these models, exemplified by DDIMs, exhibit an inherent asymmetry: they are trained over $T$ steps but only sample from a subset of $T$ during generation. This selective sampling approach, though optimized for speed, inadvertently misses out on vital information from the unsampled steps, leading to potential compromises in sample quality. To address this issue, we present the S$^{2}$-DMs, which is a new training method by using an innovative $L_{skip}$, meticulously designed to reintegrate the information omitted during the selective sampling phase. The benefits of this approach are manifold: it notably enhances sample quality, is exceptionally simple to implement, requires minimal code modifications, and is flexible enough to be compatible with various sampling algorithms. On the CIFAR10 dataset, models trained using our algorithm showed an improvement of 3.27% to 14.06% over models trained with traditional methods across various sampling algorithms (DDIMs, PNDMs, DEIS) and different numbers of sampling steps (10, 20, ..., 1000). On the CELEBA dataset, the improvement ranged from 8.97% to 27.08%. Access to the code and additional resources is provided in the github.
In this paper, we propose to guide the video caption generation with Part-of-Speech (POS) information, based on a gated fusion of multiple representations of input videos. We construct a novel gated fusion network, with one particularly designed cross-gating (CG) block, to effectively encode and fuse different types of representations, e.g., the motion and content features of an input video. One POS sequence generator relies on this fused representation to predict the global syntactic structure, which is thereafter leveraged to guide the video captioning generation and control the syntax of the generated sentence. Specifically, a gating strategy is proposed to dynamically and adaptively incorporate the global syntactic POS information into the decoder for generating each word. Experimental results on two benchmark datasets, namely MSR-VTT and MSVD, demonstrate that the proposed model can well exploit complementary information from multiple representations, resulting in improved performances. Moreover, the generated global POS information can well capture the global syntactic structure of the sentence, and thus be exploited to control the syntactic structure of the description. Such POS information not only boosts the video captioning performance but also improves the diversity of the generated captions. Our code is at: https://github.com/vsislab/Controllable_XGating.
State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information of training classes and spatial inconsistency between query and support targets. To alleviate these issues, we propose the Prior Guided Feature Enrichment Network (PFENet). It consists of novel designs of (1) a training-free prior mask generation method that not only retains generalization power but also improves model performance and (2) Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks. Extensive experiments on PASCAL-5$^i$ and COCO prove that the proposed prior generation method and FEM both improve the baseline method significantly. Our PFENet also outperforms state-of-the-art methods by a large margin without efficiency loss. It is surprising that our model even generalizes to cases without labeled support samples. Our code is available at https://github.com/Jia-Research-Lab/PFENet/.