Common image-to-image translation methods rely on joint training over data from both source and target domains. This excludes cases where domain data is private (e.g., in a federated setting), and often means that a new model has to be trained for a new pair of domains. We present Dual Diffusion Implicit Bridges (DDIBs), an image translation method based on diffusion models, that circumvents training on domain pairs. DDIBs allow translations between arbitrary pairs of source-target domains, given independently trained diffusion models on the respective domains. Image translation with DDIBs is a two-step process: DDIBs first obtain latent encodings for source images with the source diffusion model, and next decode such encodings using the target model to construct target images. Moreover, DDIBs enable cycle-consistency by default and is theoretically connected to optimal transport. Experimentally, we apply DDIBs on a variety of synthetic and high-resolution image datasets, demonstrating their utility in example-guided color transfer, image-to-image translation as well as their connections to optimal transport methods.
Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a similar but real-world domain for learning semantic segmentation. We propose a semantically consistent image-to-image translation method in combination with a consistency regularisation method for UDA. We overcome previous limitations on transferring synthetic images to real looking images. We leverage pseudo-labels in order to learn a generative image-to-image translation model that receives additional feedback from semantic labels on both domains. Our method outperforms state-of-the-art methods that combine image-to-image translation and semi-supervised learning on relevant domain adaptation benchmarks, i.e., on GTA5 to Cityscapes and SYNTHIA to Cityscapes.
A self-driving car must be able to reliably handle adverse weather conditions (e.g., snowy) to operate safely. In this paper, we investigate the idea of turning sensor inputs (i.e., images) captured in an adverse condition into a benign one (i.e., sunny), upon which the downstream tasks (e.g., semantic segmentation) can attain high accuracy. Prior work primarily formulates this as an unpaired image-to-image translation problem due to the lack of paired images captured under the exact same camera poses and semantic layouts. While perfectly-aligned images are not available, one can easily obtain coarsely-paired images. For instance, many people drive the same routes daily in both good and adverse weather; thus, images captured at close-by GPS locations can form a pair. Though data from repeated traversals are unlikely to capture the same foreground objects, we posit that they provide rich contextual information to supervise the image translation model. To this end, we propose a novel training objective leveraging coarsely-aligned image pairs. We show that our coarsely-aligned training scheme leads to a better image translation quality and improved downstream tasks, such as semantic segmentation, monocular depth estimation, and visual localization.
The ability to classify images accurately and efficiently is dependent on having access to large labeled datasets and testing on data from the same domain that the model is trained on. Classification becomes more challenging when dealing with new data from a different domain, where collecting a large labeled dataset and training a new classifier from scratch is time-consuming, expensive, and sometimes infeasible or impossible. Cross-domain classification frameworks were developed to handle this data domain shift problem by utilizing unsupervised image-to-image (UI2I) translation models to translate an input image from the unlabeled domain to the labeled domain. The problem with these unsupervised models lies in their unsupervised nature. For lack of annotations, it is not possible to use the traditional supervised metrics to evaluate these translation models to pick the best-saved checkpoint model. In this paper, we introduce a new method called Pseudo Supervised Metrics that was designed specifically to support cross-domain classification applications contrary to other typically used metrics such as the FID which was designed to evaluate the model in terms of the quality of the generated image from a human-eye perspective. We show that our metric not only outperforms unsupervised metrics such as the FID, but is also highly correlated with the true supervised metrics, robust, and explainable. Furthermore, we demonstrate that it can be used as a standard metric for future research in this field by applying it to a critical real-world problem (the boiling crisis problem).
Endoscopic ultrasound (EUS) imaging has a trade-off between resolution and penetration depth. By considering the in-vivo characteristics of human organs, it is necessary to provide clinicians with appropriate hardware specifications for precise diagnosis. Recently, super-resolution (SR) ultrasound imaging studies, including the SR task in deep learning fields, have been reported for enhancing ultrasound images. However, most of those studies did not consider ultrasound imaging natures, but rather they were conventional SR techniques based on downsampling of ultrasound images. In this study, we propose a novel deep learning-based high-resolution in-depth imaging probe capable of offering low- and high-frequency ultrasound image pairs. We developed an attachable dual-element EUS probe with customized low- and high-frequency ultrasound transducers under small hardware constraints. We also designed a special geared structure to enable the same image plane. The proposed system was evaluated with a wire phantom and a tissue-mimicking phantom. After the evaluation, 442 ultrasound image pairs from the tissue-mimicking phantom were acquired. We then applied several deep learning models to obtain synthetic high-resolution in-depth images, thus demonstrating the feasibility of our approach for clinical unmet needs. Furthermore, we quantitatively and qualitatively analyzed the results to find a suitable deep-learning model for our task. The obtained results demonstrate that our proposed dual-element EUS probe with an image-to-image translation network has the potential to provide synthetic high-frequency ultrasound images deep inside tissues.
Deep neural networks are commonly used for automated medical image segmentation, but models will frequently struggle to generalize well across different imaging modalities. This issue is particularly problematic due to the limited availability of annotated data, making it difficult to deploy these models on a larger scale. To overcome these challenges, we propose a new semi-supervised training strategy called MoDATTS. Our approach is designed for accurate cross-modality 3D tumor segmentation on unpaired bi-modal datasets. An image-to-image translation strategy between imaging modalities is used to produce annotated pseudo-target volumes and improve generalization to the unannotated target modality. We also use powerful vision transformer architectures and introduce an iterative self-training procedure to further close the domain gap between modalities. MoDATTS additionally allows the possibility to extend the training to unannotated target data by exploiting image-level labels with an unsupervised objective that encourages the model to perform 3D diseased-to-healthy translation by disentangling tumors from the background. The proposed model achieves superior performance compared to other methods from participating teams in the CrossMoDA 2022 challenge, as evidenced by its reported top Dice score of 0.87+/-0.04 for the VS segmentation. MoDATTS also yields consistent improvements in Dice scores over baselines on a cross-modality brain tumor segmentation task composed of four different contrasts from the BraTS 2020 challenge dataset, where 95% of a target supervised model performance is reached. We report that 99% and 100% of this maximum performance can be attained if 20% and 50% of the target data is additionally annotated, which further demonstrates that MoDATTS can be leveraged to reduce the annotation burden.
Recent image-to-image translation works have been transferred from supervised to unsupervised settings due to the expensive cost of capturing or labeling large amounts of paired data. However, current unsupervised methods using the cycle-consistency constraint may not find the desired mapping, especially for difficult translation tasks. On the other hand, a small number of paired data are usually accessible. We therefore introduce a general framework for semi-supervised image translation. Unlike previous works, our main idea is to learn the translation over the latent feature space instead of the image space. Thanks to the low dimensional feature space, it is easier to find the desired mapping function, resulting in improved quality of translation results as well as the stability of the translation model. Empirically we show that using feature translation generates better results, even using a few bits of paired data. Experimental comparisons with state-of-the-art approaches demonstrate the effectiveness of the proposed framework on a variety of challenging image-to-image translation tasks
Generative Adversarial Networks (GAN) have emerged as a formidable AI tool to generate realistic outputs based on training datasets. However, the challenge of exerting control over the generation process of GANs remains a significant hurdle. In this paper, we propose a novel methodology to address this issue by integrating a reinforcement learning (RL) agent with a latent-space GAN (l-GAN), thereby facilitating the generation of desired outputs. More specifically, we have developed an actor-critic RL agent with a meticulously designed reward policy, enabling it to acquire proficiency in navigating the latent space of the l-GAN and generating outputs based on specified tasks. To substantiate the efficacy of our approach, we have conducted a series of experiments employing the MNIST dataset, including arithmetic addition as an illustrative task. The outcomes of these experiments serve to validate our methodology. Our pioneering integration of an RL agent with a GAN model represents a novel advancement, holding great potential for enhancing generative networks in the future.
Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a similar but real-world domain for learning semantic segmentation. We propose a semantically consistent image-to-image translation method in combination with a consistency regularisation method for UDA. We overcome previous limitations on transferring synthetic images to real looking images. We leverage pseudo-labels in order to learn a generative image-to-image translation model that receives additional feedback from semantic labels on both domains. Our method outperforms state-of-the-art methods that combine image-to-image translation and semi-supervised learning on relevant domain adaption benchmarks, i.e., on GTA5 to Cityscapes and SYNTHIA to Cityscapes.
Training a model-free deep reinforcement learning model to solve image-to-image translation is difficult since it involves high-dimensional continuous state and action spaces. In this paper, we draw inspiration from the recent success of the maximum entropy reinforcement learning framework designed for challenging continuous control problems to develop stochastic policies over high dimensional continuous spaces including image representation, generation, and control simultaneously. Central to this method is the Stochastic Actor-Executor-Critic (SAEC) which is an off-policy actor-critic model with an additional executor to generate realistic images. Specifically, the actor focuses on the high-level representation and control policy by a stochastic latent action, as well as explicitly directs the executor to generate low-level actions to manipulate the state. Experiments on several image-to-image translation tasks have demonstrated the effectiveness and robustness of the proposed SAEC when facing high-dimensional continuous space problems.