最近，将变压器结构应用于图像分类任务的视觉变压器（VIV）具有优于卷积神经网络的优势。然而，使用诸如JFT-300M的大型数据集的预先训练的VIT结果的高性能和其对大型数据集的依赖性被解释为由于低地位感应偏差。本文提出了移动的贴片标记（SPT）和地区自我关注（LSA），有效解决了缺乏地区归纳偏差，使其即使在小型数据集上也能从划痕中学习。此外，SPT和LSA是通用且有效的附加模块，可轻松适用于各种VITS。实验结果表明，当SPT和LSA都应用于VITS时，性能在微小的想象中平均提高2.96％，这是一个代表性的小型数据集。特别是，由于所提出的SPT和LSA，Swin Transformer达到了4.08％的压倒性的性能提高。

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Deep neural networks have been successfully adopted to diverse domains including pathology classification based on medical images. However, large-scale and high-quality data to train powerful neural networks are rare in the medical domain as the labeling must be done by qualified experts. Researchers recently tackled this problem with some success by taking advantage of models pre-trained on large-scale general domain data. Specifically, researchers took contrastive image-text encoders (e.g., CLIP) and fine-tuned it with chest X-ray images and paired reports to perform zero-shot pathology classification, thus completely removing the need for pathology-annotated images to train a classification model. Existing studies, however, fine-tuned the pre-trained model with the same contrastive learning objective, and failed to exploit the multi-labeled nature of medical image-report pairs. In this paper, we propose a new fine-tuning strategy based on sentence sampling and positive-pair loss relaxation for improving the downstream zero-shot pathology classification performance, which can be applied to any pre-trained contrastive image-text encoders. Our method consistently showed dramatically improved zero-shot pathology classification performance on four different chest X-ray datasets and 3 different pre-trained models (5.77% average AUROC increase). In particular, fine-tuning CLIP with our method showed much comparable or marginally outperformed to board-certified radiologists (0.619 vs 0.625 in F1 score and 0.530 vs 0.544 in MCC) in zero-shot classification of five prominent diseases from the CheXpert dataset.

Diffusion-based generative models have achieved remarkable success in image generation. Their guidance formulation allows an external model to plug-and-play control the generation process for various tasks without fine-tuning the diffusion model. However, the direct use of publicly available off-the-shelf models for guidance fails due to their poor performance on noisy inputs. For that, the existing practice is to fine-tune the guidance models with labeled data corrupted with noises. In this paper, we argue that this practice has limitations in two aspects: (1) performing on inputs with extremely various noises is too hard for a single model; (2) collecting labeled datasets hinders scaling up for various tasks. To tackle the limitations, we propose a novel strategy that leverages multiple experts where each expert is specialized in a particular noise range and guides the reverse process at its corresponding timesteps. However, as it is infeasible to manage multiple networks and utilize labeled data, we present a practical guidance framework termed Practical Plug-And-Play (PPAP), which leverages parameter-efficient fine-tuning and data-free knowledge transfer. We exhaustively conduct ImageNet class conditional generation experiments to show that our method can successfully guide diffusion with small trainable parameters and no labeled data. Finally, we show that image classifiers, depth estimators, and semantic segmentation models can guide publicly available GLIDE through our framework in a plug-and-play manner.

This paper proposes Mutual Information Regularized Assignment (MIRA), a pseudo-labeling algorithm for unsupervised representation learning inspired by information maximization. We formulate online pseudo-labeling as an optimization problem to find pseudo-labels that maximize the mutual information between the label and data while being close to a given model probability. We derive a fixed-point iteration method and prove its convergence to the optimal solution. In contrast to baselines, MIRA combined with pseudo-label prediction enables a simple yet effective clustering-based representation learning without incorporating extra training techniques or artificial constraints such as sampling strategy, equipartition constraints, etc. With relatively small training epochs, representation learned by MIRA achieves state-of-the-art performance on various downstream tasks, including the linear/k-NN evaluation and transfer learning. Especially, with only 400 epochs, our method applied to ImageNet dataset with ResNet-50 architecture achieves 75.6% linear evaluation accuracy.

具有对比目标的训练前视觉模型已显示出令人鼓舞的结果，这些结果既可以扩展到大型未经切割的数据集，又可以传输到许多下游应用程序。以下一些作品针对提高数据效率，通过添加自学意义来提高数据效率，但是在这些作品中的单个空间上定义了对比度损失（图像文本）对比度损失和内域（图像图像）对比度损失，因此许多可行的可行性监督的组合被忽略了。为了克服这个问题，我们提出了Uniclip，这是对对比语言图像预训练的统一框架。 Uniclip将域间对和域内对的对比损失整合到一个单一的通用空间中。 Uniclip的三个关键组成部分解决了整合不同域之间对比度损失时发生的差异：（1）增强感知功能嵌入，（2）MP-NCE损失和（3）域相似性度量。 Uniclip的表现优于以前的视觉语言预训练方法，在下游任务的各种单模式和多模式上。在我们的实验中，我们表明每个组成的分支都对最终性能有很好的贡献。

在带有频划分双链体（FDD）的常规多用户多用户多输入多输出（MU-MIMO）系统中，尽管高度耦合，但已单独设计了通道采集和预编码器优化过程。本文研究了下行链路MU-MIMO系统的端到端设计，其中包括试点序列，有限的反馈和预编码。为了解决这个问题，我们提出了一个新颖的深度学习（DL）框架，该框架共同优化了用户的反馈信息生成和基础站（BS）的预编码器设计。 MU-MIMO系统中的每个过程都被智能设计的多个深神经网络（DNN）单元所取代。在BS上，神经网络生成试验序列，并帮助用户获得准确的频道状态信息。在每个用户中，频道反馈操作是由单个用户DNN以分布方式进行的。然后，另一个BS DNN从用户那里收集反馈信息，并确定MIMO预编码矩阵。提出了联合培训算法以端到端的方式优化所有DNN单元。此外，还提出了一种可以避免针对可扩展设计的不同网络大小进行重新训练的培训策略。数值结果证明了与经典优化技术和其他常规DNN方案相比，提出的DL框架的有效性。

最近的成功表明，可以通过文本提示来操纵图像，例如，在雨天的晴天，在雨天中被操纵到同一场景中，这是由文本输入“下雨”驱动的雨天。这些方法经常利用基于样式的图像生成器，该生成器利用多模式（文本和图像）嵌入空间。但是，我们观察到，这种文本输入通常在提供和综合丰富的语义提示时被瓶颈瓶颈，例如将大雨与雨雨区分开。为了解决这个问题，我们主张利用另一种方式，声音，在图像操纵中具有显着优势，因为它可以传达出比文本更多样化的语义提示（生动的情感或自然世界的动态表达）。在本文中，我们提出了一种新颖的方法，该方法首先使用声音扩展了图像文本接头嵌入空间，并应用了一种直接的潜在优化方法来根据音频输入（例如雨的声音）操纵给定的图像。我们的广泛实验表明，我们的声音引导的图像操纵方法在语义和视觉上比最先进的文本和声音引导的图像操纵方法产生更合理的操作结果，这通过我们的人类评估进一步证实。我们的下游任务评估还表明，我们学到的图像文本单嵌入空间有效地编码声音输入。

最近的深度学习模型在言语增强方面已经达到了高性能。但是，获得快速和低复杂模型而没有明显的性能降解仍然是一项挑战。以前的知识蒸馏研究对言语增强无法解决这个问题，因为它们的输出蒸馏方法在某些方面不符合语音增强任务。在这项研究中，我们提出了基于特征的蒸馏多视图注意转移（MV-AT），以在时域中获得有效的语音增强模型。基于多视图功能提取模型，MV-AT将教师网络的多视图知识传输到学生网络，而无需其他参数。实验结果表明，所提出的方法始终提高瓦伦蒂尼和深噪声抑制（DNS）数据集的各种规模的学生模型的性能。与基线模型相比，使用我们提出的方法（一种用于有效部署的轻巧模型）分别使用了15.4倍和4.71倍（FLOPS），与具有相似性能的基线模型相比，Many-S-8.1GF分别达到了15.4倍和4.71倍。

预训练的代表是现代深度学习成功的关键要素之一。但是，现有的关于持续学习方法的作品主要集中在从头开始逐步学习学习模型。在本文中，我们探讨了一个替代框架，以逐步学习，我们不断从预训练的表示中微调模型。我们的方法利用了预训练的神经网络的线性化技术来进行简单有效的持续学习。我们表明，这使我们能够设计一个线性模型，其中将二次参数正则方法作为最佳持续学习策略，同时享受神经网络的高性能。我们还表明，所提出的算法使参数正则化方法适用于类新问题。此外，我们还提供了一个理论原因，为什么在接受跨凝结损失训练的神经网络上，现有的参数空间正则化算法（例如EWC表现不佳）。我们表明，提出的方法可以防止忘记，同时在图像分类任务上实现高连续的微调性能。为了证明我们的方法可以应用于一般的持续学习设置，我们评估了我们在数据收入，任务收入和课堂学习问题方面的方法。