Facial Expression Recognition (FER) in the wild is an extremely challenging task. Recently, some Vision Transformers (ViT) have been explored for FER, but most of them perform inferiorly compared to Convolutional Neural Networks (CNN). This is mainly because the new proposed modules are difficult to converge well from scratch due to lacking inductive bias and easy to focus on the occlusion and noisy areas. TransFER, a representative transformer-based method for FER, alleviates this with multi-branch attention dropping but brings excessive computations. On the contrary, we present two attentive pooling (AP) modules to pool noisy features directly. The AP modules include Attentive Patch Pooling (APP) and Attentive Token Pooling (ATP). They aim to guide the model to emphasize the most discriminative features while reducing the impacts of less relevant features. The proposed APP is employed to select the most informative patches on CNN features, and ATP discards unimportant tokens in ViT. Being simple to implement and without learnable parameters, the APP and ATP intuitively reduce the computational cost while boosting the performance by ONLY pursuing the most discriminative features. Qualitative results demonstrate the motivations and effectiveness of our attentive poolings. Besides, quantitative results on six in-the-wild datasets outperform other state-of-the-art methods.

联合学习（FL）是一种机器学习范式，允许分散的客户在不共享其私人数据的情况下进行协作学习。但是，过度的计算和沟通要求对当前的FL框架构成挑战，尤其是在训练大型模型时。为了防止这些问题阻碍FL系统的部署，我们提出了一个轻巧的框架，客户共同学习融合由多个固定预训练的模型生成的表示形式，而不是从SCRATCH培训大型模型。这通过考虑如何从预先训练的模型中捕获更多特定于客户的信息，并共同提高每个客户利用这些现成模型的能力，从而导致我们解决了一个更实用的FL问题。在这项工作中，我们设计了一种联合原型对比度学习（FEDPCL）方法，该方法通过其类原型共享客户的知识，并以原型对比度方式构建特定于客户的表示。共享原型而不是可学习的模型参数可以使每个客户以个性化的方式融合表示表示，同时以紧凑的形式保持共享知识以进行有效的通信。我们在轻量级框架中对拟议的FEDPCL进行了彻底的评估，以测量和可视化其在流行的FL数据集上融合各种预训练模型的能力。

二进制神经网络（BNNS）对现实世界中嵌入式设备显示出巨大的希望。作为实现强大BNN的关键步骤之一，规模因子计算在减少其实价对应物的性能差距方面起着至关重要的作用。然而，现有的BNN忽略了实价重量和尺度因子的固有双线关系，从而导致训练过程不足引起的亚最佳模型。为了解决这个问题，提出了复发性双线性优化，以通过将固有的双线性变量关联到背面传播过程中，以改善BNNS（RBONN）的学习过程。我们的工作是从双线性角度优化BNN的首次尝试。具体而言，我们采用经常​​性优化和密度 - 列表来依次回溯稀疏的实价过滤器，该过滤器将经过充分的训练并基于可控的学习过程达到其性能限制。我们获得了强大的rbonn，在各种模型和数据集上的最先进的BNN上表现出令人印象深刻的性能。特别是，在对象检测的任务下，rbonn具有出色的概括性能。我们的代码在https://github.com/stevetsui/rbonn上进行开源。

知识共享和模型个性化是应对联邦学习（FL）中非IID挑战的重要组成部分。大多数现有的FL方法侧重于两个极端：1）学习共享模型，以使用非IID数据为所有客户提供服务，以及2）为每个客户（即个性化fl）学习个性化模型。有一个权衡解决方案，即群集或集群个性化的FL，旨在将相似的客户聚集到一个集群中，然后在集群中为所有客户学习共享模型。本文是通过将群集群集制定为可以统一现有方法的双层优化框架来重新审视群集的研究。我们提出了一个新的理论分析框架，以通过考虑客户之间的凝聚力来证明融合。此外，我们以一种称为加权聚类联合学习（WECFL）的算法体现了该框架。经验分析验证了理论结果，并证明了在拟议的集群非IID设置下提出的WECFL的有效性。

Uyghur语音常常遇到辅音和元音减少，这可能导致Uyghur自动语音识别（ASR）的性能下降。我们最近提出的基于掩蔽的学习策略，电话遮蔽训练（PMT），减轻了这种现象在Uyghur Asr的影响。尽管PMT实现了显着改进，但由于PMT（音素）和建模单元（字件）的掩模单元之间的粒度不匹配，仍然存在进一步提升的空间。为了提高PMT的性能，我们提出了PMT（PM-MET）的多建模单元训练（MMUT）架构融合。 MUT框架的概念是将编码器分成两个部分，包括声学级表示（AF-TO-PLR）和音素级表示的声学特征序列（PLR-TO-WPLR）。它允许通过基于中间音素的CTC丢失来优化AF-To-PLR，以了解PMT带来的富音素级上下文信息。 UYGHUR ASR上的实验结果表明，该提出的方法显着改善，优于纯PMT（减少24.0至23.7，在Read-Test上，分别在口服检验中的38.4至36.8。我们还使用ESPNET1对960小时的LibrisPeech基准进行实验，该基准测试在没有LM Fusion的所有测试集上实现约10％的相对WER减少，与最新的ESPNET1预先训练的模型相比。

注释的医学图像昂贵，有时甚至无法在一定程度上获得地标检测精度。半监督学习通过利用未标记的数据来了解解剖标志性的人口结构来减轻对大规模注释数据的依赖。全局形状约束是解剖标识的固有属性，为更加一致的伪标签提供了有价值的指导，这些指南在先前的半监督方法中被忽略。在本文中，我们通过完全考虑全局形状约束，提出了一种用于半监控地标检测的模型 - 不可知的形状调节的自我训练框架。具体而言，为了确保伪标签是可靠且保持一致的，基于PCA的形状模型调整伪标签并消除异常。一种新的区域注意力损失，使网络自动关注伪标签周围的结构一致区域。广泛的实验表明，我们的方法优于其他半监督方法，并在三个医学图像数据集中实现了显着的改进。此外，我们的框架是灵活的，可用作集成到最具监控方法的即插即用模块，以进一步提高性能。

Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. However, in contrast to passages or sentences, retrieval on long documents suffers from the scope hypothesis that a long document may cover multiple topics. This maximizes their structure heterogeneity and poses a granular-mismatch issue, leading to an inferior distillation efficacy. In this work, we propose a new learning framework, fine-grained distillation (FGD), for long-document retrievers. While preserving the conventional dense retrieval paradigm, it first produces global-consistent representations crossing different fine granularity and then applies multi-granular aligned distillation merely during training. In experiments, we evaluate our framework on two long-document retrieval benchmarks, which show state-of-the-art performance.

An enhanced geothermal system is essential to provide sustainable and long-term geothermal energy supplies and reduce carbon emissions. Optimal well-control scheme for effective heat extraction and improved heat sweep efficiency plays a significant role in geothermal development. However, the optimization performance of most existing optimization algorithms deteriorates as dimension increases. To solve this issue, a novel surrogate-assisted level-based learning evolutionary search algorithm (SLLES) is proposed for heat extraction optimization of enhanced geothermal system. SLLES consists of classifier-assisted level-based learning pre-screen part and local evolutionary search part. The cooperation of the two parts has realized the balance between the exploration and exploitation during the optimization process. After iteratively sampling from the design space, the robustness and effectiveness of the algorithm are proven to be improved significantly. To the best of our knowledge, the proposed algorithm holds state-of-the-art simulation-involved optimization framework. Comparative experiments have been conducted on benchmark functions, a two-dimensional fractured reservoir and a three-dimensional enhanced geothermal system. The proposed algorithm outperforms other five state-of-the-art surrogate-assisted algorithms on all selected benchmark functions. The results on the two heat extraction cases also demonstrate that SLLES can achieve superior optimization performance compared with traditional evolutionary algorithm and other surrogate-assisted algorithms. This work lays a solid basis for efficient geothermal extraction of enhanced geothermal system and sheds light on the model management strategies of data-driven optimization in the areas of energy exploitation.

Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework of Structure-From-Motion (SfM) simultaneously predict depth and camera relative pose. However, dynamically moving objects in the scene violate the static world assumption, resulting in inaccurate depths of dynamic objects. In this work, we propose a new method to address such dynamic object movements through monocular 3D object detection. Specifically, we first detect 3D objects in the images and build the per-pixel correspondence of the dynamic pixels with the detected object pose while leaving the static pixels corresponding to the rigid background to be modeled with camera motion. In this way, the depth of every pixel can be learned via a meaningful geometry model. Besides, objects are detected as cuboids with absolute scale, which is used to eliminate the scale ambiguity problem inherent in monocular vision. Experiments on the KITTI depth dataset show that our method achieves State-of-The-Art performance for depth estimation. Furthermore, joint training of depth, camera motion and object pose also improves monocular 3D object detection performance. To the best of our knowledge, this is the first work that allows a monocular 3D object detection network to be fine-tuned in a self-supervised manner.

With the success of the prompt-tuning paradigm in Natural Language Processing (NLP), various prompt templates have been proposed to further stimulate specific knowledge for serving downstream tasks, e.g., machine translation, text generation, relation extraction, and so on. Existing prompt templates are mainly shared among all training samples with the information of task description. However, training samples are quite diverse. The sharing task description is unable to stimulate the unique task-related information in each training sample, especially for tasks with the finite-label space. To exploit the unique task-related information, we imitate the human decision process which aims to find the contrastive attributes between the objective factual and their potential counterfactuals. Thus, we propose the \textbf{C}ounterfactual \textbf{C}ontrastive \textbf{Prompt}-Tuning (CCPrompt) approach for many-class classification, e.g., relation classification, topic classification, and entity typing. Compared with simple classification tasks, these tasks have more complex finite-label spaces and are more rigorous for prompts. First of all, we prune the finite label space to construct fact-counterfactual pairs. Then, we exploit the contrastive attributes by projecting training instances onto every fact-counterfactual pair. We further set up global prototypes corresponding with all contrastive attributes for selecting valid contrastive attributes as additional tokens in the prompt template. Finally, a simple Siamese representation learning is employed to enhance the robustness of the model. We conduct experiments on relation classification, topic classification, and entity typing tasks in both fully supervised setting and few-shot setting. The results indicate that our model outperforms former baselines.