最近的自我监督方法使用了大规模的图像文本数据集来学习强大的表示，这些表示无需填补即可将其转移到许多任务。这些方法通常假定其图像与其（简短）字幕之间存在一对一的对应关系。但是，许多任务需要有关多个图像和长文本叙述的推理，例如描述带有视觉摘要的新闻文章。因此，我们探索了一个新颖的环境，其目标是学习一个自我监督的视觉语言表示，该表示对改变文本长度和图像数量是可靠的。此外，与假设字幕的先前工作不同，我们假设图像仅包含与文本的宽松说明对应关系。为了探索这个问题，我们介绍了一个大规模的多模式数据集，其中包含31m文章，22m图像和1M视频。我们表明，对具有多个图像的更长叙述，最新的图像文本对齐方法并不强大。最后，我们介绍了一个直观的基线，该基线在GoodNews数据集上在零摄像集检索上胜过10％。

我们介绍了空间本地化叙述中的视频中的任务。我们的方法的关键是能够学会在与随附的叙述的视频中的大型视频中对自我监督进行空间地定位与自我监督的互动。为实现这一目标，我们提出了一种多层跨模型关注网络，可以在培训期间有效优化对比损失。我们介绍了一种分割的策略，可以通过视觉和自然语言方式计算和中间模态注意力之间的交替，这允许通过直接对比两种方式的表示来实现有效的培训。我们展示了我们对HOWTO100M教学数据集的自我训练的方法的有效性，并在YouCook2 DataSet中的本地化描述交互的新收集数据集上进行评估。我们展示了我们的方法优于替代基准，包括浅薄的共同关注和完全跨越的关注。我们还将我们的方法应用于在Flickr30k上的弱监管下的图像中的接地短语，并显示堆叠多个注意层是有效的，并且当与对区域丢失相结合时，在召回召回和指向时达到最先进的艺术状态手准确性。

Although many studies have successfully applied transfer learning to medical image segmentation, very few of them have investigated the selection strategy when multiple source tasks are available for transfer. In this paper, we propose a prior knowledge guided and transferability based framework to select the best source tasks among a collection of brain image segmentation tasks, to improve the transfer learning performance on the given target task. The framework consists of modality analysis, RoI (region of interest) analysis, and transferability estimation, such that the source task selection can be refined step by step. Specifically, we adapt the state-of-the-art analytical transferability estimation metrics to medical image segmentation tasks and further show that their performance can be significantly boosted by filtering candidate source tasks based on modality and RoI characteristics. Our experiments on brain matter, brain tumor, and white matter hyperintensities segmentation datasets reveal that transferring from different tasks under the same modality is often more successful than transferring from the same task under different modalities. Furthermore, within the same modality, transferring from the source task that has stronger RoI shape similarity with the target task can significantly improve the final transfer performance. And such similarity can be captured using the Structural Similarity index in the label space.

Modern deep neural networks have achieved superhuman performance in tasks from image classification to game play. Surprisingly, these various complex systems with massive amounts of parameters exhibit the same remarkable structural properties in their last-layer features and classifiers across canonical datasets. This phenomenon is known as "Neural Collapse," and it was discovered empirically by Papyan et al. \cite{Papyan20}. Recent papers have theoretically shown the global solutions to the training network problem under a simplified "unconstrained feature model" exhibiting this phenomenon. We take a step further and prove the Neural Collapse occurrence for deep linear network for the popular mean squared error (MSE) and cross entropy (CE) loss. Furthermore, we extend our research to imbalanced data for MSE loss and present the first geometric analysis for Neural Collapse under this setting.

In this paper we derive a PAC-Bayesian-Like error bound for a class of stochastic dynamical systems with inputs, namely, for linear time-invariant stochastic state-space models (stochastic LTI systems for short). This class of systems is widely used in control engineering and econometrics, in particular, they represent a special case of recurrent neural networks. In this paper we 1) formalize the learning problem for stochastic LTI systems with inputs, 2) derive a PAC-Bayesian-Like error bound for such systems, 3) discuss various consequences of this error bound.

Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data space results in slow inference speed, which restricts their application in real-time systems. Previous works have explored speeding up by minimizing the number of inference steps but at the cost of sample quality. In this work, to improve the inference speed for DDPM-based TTS model while achieving high sample quality, we propose ResGrad, a lightweight diffusion model which learns to refine the output spectrogram of an existing TTS model (e.g., FastSpeech 2) by predicting the residual between the model output and the corresponding ground-truth speech. ResGrad has several advantages: 1) Compare with other acceleration methods for DDPM which need to synthesize speech from scratch, ResGrad reduces the complexity of task by changing the generation target from ground-truth mel-spectrogram to the residual, resulting into a more lightweight model and thus a smaller real-time factor. 2) ResGrad is employed in the inference process of the existing TTS model in a plug-and-play way, without re-training this model. We verify ResGrad on the single-speaker dataset LJSpeech and two more challenging datasets with multiple speakers (LibriTTS) and high sampling rate (VCTK). Experimental results show that in comparison with other speed-up methods of DDPMs: 1) ResGrad achieves better sample quality with the same inference speed measured by real-time factor; 2) with similar speech quality, ResGrad synthesizes speech faster than baseline methods by more than 10 times. Audio samples are available at https://resgrad1.github.io/.

Deep learning has been widely used for protein engineering. However, it is limited by the lack of sufficient experimental data to train an accurate model for predicting the functional fitness of high-order mutants. Here, we develop SESNet, a supervised deep-learning model to predict the fitness for protein mutants by leveraging both sequence and structure information, and exploiting attention mechanism. Our model integrates local evolutionary context from homologous sequences, the global evolutionary context encoding rich semantic from the universal protein sequence space and the structure information accounting for the microenvironment around each residue in a protein. We show that SESNet outperforms state-of-the-art models for predicting the sequence-function relationship on 26 deep mutational scanning datasets. More importantly, we propose a data augmentation strategy by leveraging the data from unsupervised models to pre-train our model. After that, our model can achieve strikingly high accuracy in prediction of the fitness of protein mutants, especially for the higher order variants (> 4 mutation sites), when finetuned by using only a small number of experimental mutation data (<50). The strategy proposed is of great practical value as the required experimental effort, i.e., producing a few tens of experimental mutation data on a given protein, is generally affordable by an ordinary biochemical group and can be applied on almost any protein.

Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks, and various methods have been proposed for the defense. Among these methods, adversarial training has been drawing increasing attention because of its simplicity and effectiveness. However, the performance of the adversarial training is greatly limited by the architectures of target DNNs, which often makes the resulting DNNs with poor accuracy and unsatisfactory robustness. To address this problem, we propose DSARA to automatically search for the neural architectures that are accurate and robust after adversarial training. In particular, we design a novel cell-based search space specially for adversarial training, which improves the accuracy and the robustness upper bound of the searched architectures by carefully designing the placement of the cells and the proportional relationship of the filter numbers. Then we propose a two-stage search strategy to search for both accurate and robust neural architectures. At the first stage, the architecture parameters are optimized to minimize the adversarial loss, which makes full use of the effectiveness of the adversarial training in enhancing the robustness. At the second stage, the architecture parameters are optimized to minimize both the natural loss and the adversarial loss utilizing the proposed multi-objective adversarial training method, so that the searched neural architectures are both accurate and robust. We evaluate the proposed algorithm under natural data and various adversarial attacks, which reveals the superiority of the proposed method in terms of both accurate and robust architectures. We also conclude that accurate and robust neural architectures tend to deploy very different structures near the input and the output, which has great practical significance on both hand-crafting and automatically designing of accurate and robust neural architectures.

People with diabetes are more likely to develop diabetic retinopathy (DR) than healthy people. However, DR is the leading cause of blindness. At present, the diagnosis of diabetic retinopathy mainly relies on the experienced clinician to recognize the fine features in color fundus images. This is a time-consuming task. Therefore, in this paper, to promote the development of UW-OCTA DR automatic detection, we propose a novel semi-supervised semantic segmentation method for UW-OCTA DR image grade assessment. This method, first, uses the MAE algorithm to perform semi-supervised pre-training on the UW-OCTA DR grade assessment dataset to mine the supervised information in the UW-OCTA images, thereby alleviating the need for labeled data. Secondly, to more fully mine the lesion features of each region in the UW-OCTA image, this paper constructs a cross-algorithm ensemble DR tissue segmentation algorithm by deploying three algorithms with different visual feature processing strategies. The algorithm contains three sub-algorithms, namely pre-trained MAE, ConvNeXt, and SegFormer. Based on the initials of these three sub-algorithms, the algorithm can be named MCS-DRNet. Finally, we use the MCS-DRNet algorithm as an inspector to check and revise the results of the preliminary evaluation of the DR grade evaluation algorithm. The experimental results show that the mean dice similarity coefficient of MCS-DRNet v1 and v2 are 0.5161 and 0.5544, respectively. The quadratic weighted kappa of the DR grading evaluation is 0.7559. Our code will be released soon.

Neural Radiance Field (NeRF) is a powerful tool to faithfully generate novel views for scenes with only sparse captured images. Despite its strong capability for representing 3D scenes and their appearance, its editing ability is very limited. In this paper, we propose a simple but effective extension of vanilla NeRF, named PaletteNeRF, to enable efficient color editing on NeRF-represented scenes. Motivated by recent palette-based image decomposition works, we approximate each pixel color as a sum of palette colors modulated by additive weights. Instead of predicting pixel colors as in vanilla NeRFs, our method predicts additive weights. The underlying NeRF backbone could also be replaced with more recent NeRF models such as KiloNeRF to achieve real-time editing. Experimental results demonstrate that our method achieves efficient, view-consistent, and artifact-free color editing on a wide range of NeRF-represented scenes.