The existence of completely aligned and paired multi-modal neuroimaging data has proved its effectiveness in diagnosis of brain diseases. However, collecting the full set of well-aligned and paired data is expensive or even impractical, since the practical difficulties may include high cost, long time acquisition, image corruption, and privacy issues. A realistic solution is to explore either an unsupervised learning or a semi-supervised learning to synthesize the absent neuroimaging data. In this paper, we are the first one to comprehensively approach cross-modality neuroimage synthesis task from different perspectives, which include the level of the supervision (especially for weakly-supervised and unsupervised), loss function, evaluation metrics, the range of modality synthesis, datasets (aligned, private and public) and the synthesis-based downstream tasks. To begin with, we highlight several opening challenges for cross-modality neuroimage sysnthesis. Then we summarize the architecture of cross-modality synthesis under various of supervision level. In addition, we provide in-depth analysis of how cross-modality neuroimage synthesis can improve the performance of different downstream tasks. Finally, we re-evaluate the open challenges and point out the future directions for the remaining challenges. All resources are available at https://github.com/M-3LAB/awesome-multimodal-brain-image-systhesis

完全排列和配对的多模式神经成像数据的存在证明了其在诊断脑疾病中的有效性。但是，收集完整的一组良好的配对数据是不切实际的，因为实际困难可能包括高成本，长期获取，图像腐败和隐私问题。以前，未配对的神经影像数据（称为泥）通常被视为嘈杂的标签。但是，这种基于嘈杂的标签的方法在严重发生扭曲的数据时无法完成。例如，旋转角度不同。在本文中，我们提出了一种新的联邦自制学习（FEDMED），以用于脑形象合成。制定了仿射变换损失（ATL），以利用严重扭曲的图像，而无需违反医院的隐私立法。然后，我们引入了一种新的数据增强程序，以进行自我监督训练，并将其送入三个辅助头，即辅助旋转，辅助翻译和辅助缩放头。所提出的方法证明了在严重错误和未配对的数据设置下，我们合成结果的质量的高级性能，并且比其他基于GAN的算法更好。提出的方法还减少了对可变形注册的需求，同时鼓励利用未对准和未配对的数据。与其他最先进的方法相比，实验结果验证了我们学习范式的出色表现。

由于计算成本和能耗有限，部署在移动设备中的大多数神经网络模型都很小。然而，微小的神经网络通常很容易攻击。目前的研究证明，较大的模型规模可以提高鲁棒性，但很少的研究侧重于如何增强微小神经网络的稳健性。我们的工作侧重于如何改善微小神经网络的稳健性，而不会严重恶化移动级资源下的清洁准确性。为此，我们提出了一种多目标oneShot网络架构搜索（NAS）算法，以便在对抗准确度，清洁精度和模型尺寸方面获得最佳权衡网络。具体而言，我们基于新的微小块和通道设计一种新的搜索空间，以平衡模型大小和对抗性能。此外，由于SUPERNET显着影响了我们NAS算法中子网的性能，因此我们揭示了对SuperNet如何有助于获得白盒对抗攻击下最好的子网的洞察力。具体地，我们通过分析对抗性可转移性，超空网的宽度以及从头划痕和微调训练子网之间的差异来探索新的对抗性培训范式。最后，我们对第一个非主导的前沿的某些块和通道的层面组合进行了统计分析，这可以作为设计微小神经网络架构以实现对抗性扰动的指导。

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

A step-search sequential quadratic programming method is proposed for solving nonlinear equality constrained stochastic optimization problems. It is assumed that constraint function values and derivatives are available, but only stochastic approximations of the objective function and its associated derivatives can be computed via inexact probabilistic zeroth- and first-order oracles. Under reasonable assumptions, a high-probability bound on the iteration complexity of the algorithm to approximate first-order stationarity is derived. Numerical results on standard nonlinear optimization test problems illustrate the advantages and limitations of our proposed method.

Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency. We believe the insufficient utilization of training signals should be responsible. To alleviate this issue, we introduce a conceptually simple yet learning-efficient MIM training scheme, termed Disjoint Masking with Joint Distillation (DMJD). For disjoint masking (DM), we sequentially sample multiple masked views per image in a mini-batch with the disjoint regulation to raise the usage of tokens for reconstruction in each image while keeping the masking rate of each view. For joint distillation (JD), we adopt a dual branch architecture to respectively predict invisible (masked) and visible (unmasked) tokens with superior learning targets. Rooting in orthogonal perspectives for training efficiency improvement, DM and JD cooperatively accelerate the training convergence yet not sacrificing the model generalization ability. Concretely, DM can train ViT with half of the effective training epochs (3.7 times less time-consuming) to report competitive performance. With JD, our DMJD clearly improves the linear probing classification accuracy over ConvMAE by 5.8%. On fine-grained downstream tasks like semantic segmentation, object detection, etc., our DMJD also presents superior generalization compared with state-of-the-art SSL methods. The code and model will be made public at https://github.com/mx-mark/DMJD.

Considering the computation complexity, we propose a Guided Hybrid Quantization with One-to-one Self-Teaching (GHOST}) framework. More concretely, we first design a structure called guided quantization self-distillation (GQSD), which is an innovative idea for realizing lightweight through the synergy of quantization and distillation. The training process of the quantization model is guided by its full-precision model, which is time-saving and cost-saving without preparing a huge pre-trained model in advance. Second, we put forward a hybrid quantization (HQ) module to obtain the optimal bit width automatically under a constrained condition where a threshold for distribution distance between the center and samples is applied in the weight value search space. Third, in order to improve information transformation, we propose a one-to-one self-teaching (OST) module to give the student network a ability of self-judgment. A switch control machine (SCM) builds a bridge between the student network and teacher network in the same location to help the teacher to reduce wrong guidance and impart vital knowledge to the student. This distillation method allows a model to learn from itself and gain substantial improvement without any additional supervision. Extensive experiments on a multimodal dataset (VEDAI) and single-modality datasets (DOTA, NWPU, and DIOR) show that object detection based on GHOST outperforms the existing detectors. The tiny parameters (<9.7 MB) and Bit-Operations (BOPs) (<2158 G) compared with any remote sensing-based, lightweight or distillation-based algorithms demonstrate the superiority in the lightweight design domain. Our code and model will be released at https://github.com/icey-zhang/GHOST.

Automatic font generation without human experts is a practical and significant problem, especially for some languages that consist of a large number of characters. Existing methods for font generation are often in supervised learning. They require a large number of paired data, which are labor-intensive and expensive to collect. In contrast, common unsupervised image-to-image translation methods are not applicable to font generation, as they often define style as the set of textures and colors. In this work, we propose a robust deformable generative network for unsupervised font generation (abbreviated as DGFont++). We introduce a feature deformation skip connection (FDSC) to learn local patterns and geometric transformations between fonts. The FDSC predicts pairs of displacement maps and employs the predicted maps to apply deformable convolution to the low-level content feature maps. The outputs of FDSC are fed into a mixer to generate final results. Moreover, we introduce contrastive self-supervised learning to learn a robust style representation for fonts by understanding the similarity and dissimilarities of fonts. To distinguish different styles, we train our model with a multi-task discriminator, which ensures that each style can be discriminated independently. In addition to adversarial loss, another two reconstruction losses are adopted to constrain the domain-invariant characteristics between generated images and content images. Taking advantage of FDSC and the adopted loss functions, our model is able to maintain spatial information and generates high-quality character images in an unsupervised manner. Experiments demonstrate that our model is able to generate character images of higher quality than state-of-the-art methods.

Gaze estimation is the fundamental basis for many visual tasks. Yet, the high cost of acquiring gaze datasets with 3D annotations hinders the optimization and application of gaze estimation models. In this work, we propose a novel Head-Eye redirection parametric model based on Neural Radiance Field, which allows dense gaze data generation with view consistency and accurate gaze direction. Moreover, our head-eye redirection parametric model can decouple the face and eyes for separate neural rendering, so it can achieve the purpose of separately controlling the attributes of the face, identity, illumination, and eye gaze direction. Thus diverse 3D-aware gaze datasets could be obtained by manipulating the latent code belonging to different face attributions in an unsupervised manner. Extensive experiments on several benchmarks demonstrate the effectiveness of our method in domain generalization and domain adaptation for gaze estimation tasks.

Diabetic Retinopathy (DR) is a leading cause of vision loss in the world, and early DR detection is necessary to prevent vision loss and support an appropriate treatment. In this work, we leverage interactive machine learning and introduce a joint learning framework, termed DRG-Net, to effectively learn both disease grading and multi-lesion segmentation. Our DRG-Net consists of two modules: (i) DRG-AI-System to classify DR Grading, localize lesion areas, and provide visual explanations; (ii) DRG-Expert-Interaction to receive feedback from user-expert and improve the DRG-AI-System. To deal with sparse data, we utilize transfer learning mechanisms to extract invariant feature representations by using Wasserstein distance and adversarial learning-based entropy minimization. Besides, we propose a novel attention strategy at both low- and high-level features to automatically select the most significant lesion information and provide explainable properties. In terms of human interaction, we further develop DRG-Net as a tool that enables expert users to correct the system's predictions, which may then be used to update the system as a whole. Moreover, thanks to the attention mechanism and loss functions constraint between lesion features and classification features, our approach can be robust given a certain level of noise in the feedback of users. We have benchmarked DRG-Net on the two largest DR datasets, i.e., IDRID and FGADR, and compared it to various state-of-the-art deep learning networks. In addition to outperforming other SOTA approaches, DRG-Net is effectively updated using user feedback, even in a weakly-supervised manner.