Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty functions as part of the learning objective, alongside a standard classification loss, with a hyper-parameter controlling the relative contribution of each term. Nevertheless, these methods share two major drawbacks: 1) the scalar balancing weight is the same for all classes, hindering the ability to address different intrinsic difficulties or imbalance among classes; and 2) the balancing weight is usually fixed without an adaptive strategy, which may prevent from reaching the best compromise between accuracy and calibration, and requires hyper-parameter search for each application. We propose Class Adaptive Label Smoothing (CALS) for calibrating deep networks, which allows to learn class-wise multipliers during training, yielding a powerful alternative to common label smoothing penalties. Our method builds on a general Augmented Lagrangian approach, a well-established technique in constrained optimization, but we introduce several modifications to tailor it for large-scale, class-adaptive training. Comprehensive evaluation and multiple comparisons on a variety of benchmarks, including standard and long-tailed image classification, semantic segmentation, and text classification, demonstrate the superiority of the proposed method. The code is available at https://github.com/by-liu/CALS.

分类一直是对对抗攻击的研究的焦点，但是只有少数著作调查了适合于更密集的预测任务的方法，例如语义分割。这些作品中提出的方法不能准确地解决对抗性分割问题，因此，在愚弄模型所需的扰动的大小方面，它过于充满乐趣。在这里，我们基于近端分裂的近端分裂提出了对这些模型的白色盒子攻击，以产生较小的$ \ ell_1 $，$ \ ell_2 $或$ \ ell_ \ ell_ \ infty $ norms的对抗性扰动。我们的攻击可以通过增强的Lagrangian方法以及自适应约束缩放和掩盖策略来处理非covex最小化框架内的大量约束。我们证明，我们的攻击明显胜过先前提出的攻击，以及我们适应细分的分类攻击，为这项密集的任务提供了第一个全面的基准。我们的结果推动了有关分割任务中鲁棒性评估的当前限制。

最近，深度度量学习（DML）的实质性研究努力集中在设计复杂的成对距离损失，这需要卷积方案来缓解优化，例如样本挖掘或配对加权。分类的标准交叉熵损失在DML中大大忽略了。在表面上，交叉熵可能看起来不相关，与度量学习无关，因为它没有明确地涉及成对距离。但是，我们提供了一个理论分析，将交叉熵链接到几个众所周知的和最近的成对损耗。我们的连接是从两种不同的观点绘制：一个基于明确的优化洞察力;另一个关于标签与学到的相互信息的判别和生成观点。首先，我们明确证明交叉熵是新的成对损耗的上限，其具有类似于各种成对损耗的结构：它最大限度地减少了课堂内距离，同时最大化了阶级间距离。结果，最小化交叉熵可以被视为近似束缚 - 优化（或大大最小化）算法，以最小化该成对丢失。其次，我们表明，更一般地，最小化跨熵实际上是相当于最大化互联信息的相同信息，我们连接多个众所周知的成对损耗。此外，我们表明，各种标准成对损耗可以通过绑定的关系彼此明确地与彼此有关。我们的研究结果表明，交叉熵代表了最大化相互信息的代理 - 作为成对损耗，没有必要进行复杂的样品挖掘启发式。我们对四个标准DML基准测试的实验强烈支持我们的调查结果。我们获得最先进的结果，优于最近和复杂的DML方法。

使用深度学习模型从组织学数据中诊断癌症提出了一些挑战。这些图像中关注区域（ROI）的癌症分级和定位通常依赖于图像和像素级标签，后者需要昂贵的注释过程。深度弱监督的对象定位（WSOL）方法为深度学习模型的低成本培训提供了不同的策略。仅使用图像级注释，可以训练这些方法以对图像进行分类，并为ROI定位进行分类类激活图（CAM）。本文综述了WSOL的​​最先进的DL方法。我们提出了一种分类法，根据模型中的信息流，将这些方法分为自下而上和自上而下的方法。尽管后者的进展有限，但最近的自下而上方法目前通过深层WSOL方法推动了很多进展。早期作品的重点是设计不同的空间合并功能。但是，这些方法达到了有限的定位准确性，并揭示了一个主要限制 - 凸轮的不足激活导致了高假阴性定位。随后的工作旨在减轻此问题并恢复完整的对象。评估和比较了两个具有挑战性的组织学数据集的分类和本地化准确性，对我们的分类学方法进行了评估和比较。总体而言，结果表明定位性能差，特别是对于最初设计用于处理自然图像的通用方法。旨在解决组织学数据挑战的方法产生了良好的结果。但是，所有方法都遭受高假阳性/阴性定位的影响。在组织学中应用深WSOL方法的应用是四个关键的挑战 - 凸轮的激活下/过度激活，对阈值的敏感性和模型选择。

This contribution demonstrates the feasibility of applying Generative Adversarial Networks (GANs) on images of EPAL pallet blocks for dataset enhancement in the context of re-identification. For many industrial applications of re-identification methods, datasets of sufficient volume would otherwise be unattainable in non-laboratory settings. Using a state-of-the-art GAN architecture, namely CycleGAN, images of pallet blocks rotated to their left-hand side were generated from images of visually centered pallet blocks, based on images of rotated pallet blocks that were recorded as part of a previously recorded and published dataset. In this process, the unique chipwood pattern of the pallet block surface structure was retained, only changing the orientation of the pallet block itself. By doing so, synthetic data for re-identification testing and training purposes was generated, in a manner that is distinct from ordinary data augmentation. In total, 1,004 new images of pallet blocks were generated. The quality of the generated images was gauged using a perspective classifier that was trained on the original images and then applied to the synthetic ones, comparing the accuracy between the two sets of images. The classification accuracy was 98% for the original images and 92% for the synthetic images. In addition, the generated images were also used in a re-identification task, in order to re-identify original images based on synthetic ones. The accuracy in this scenario was up to 88% for synthetic images, compared to 96% for original images. Through this evaluation, it is established, whether or not a generated pallet block image closely resembles its original counterpart.

We leverage path differentiability and a recent result on nonsmooth implicit differentiation calculus to give sufficient conditions ensuring that the solution to a monotone inclusion problem will be path differentiable, with formulas for computing its generalized gradient. A direct consequence of our result is that these solutions happen to be differentiable almost everywhere. Our approach is fully compatible with automatic differentiation and comes with assumptions which are easy to check, roughly speaking: semialgebraicity and strong monotonicity. We illustrate the scope of our results by considering three fundamental composite problem settings: strongly convex problems, dual solutions to convex minimization problems and primal-dual solutions to min-max problems.

Within an operational framework, covers used by a steganographer are likely to come from different sensors and different processing pipelines than the ones used by researchers for training their steganalysis models. Thus, a performance gap is unavoidable when it comes to out-of-distributions covers, an extremely frequent scenario called Cover Source Mismatch (CSM). Here, we explore a grid of processing pipelines to study the origins of CSM, to better understand it, and to better tackle it. A set-covering greedy algorithm is used to select representative pipelines minimizing the maximum regret between the representative and the pipelines within the set. Our main contribution is a methodology for generating relevant bases able to tackle operational CSM. Experimental validation highlights that, for a given number of training samples, our set covering selection is a better strategy than selecting random pipelines or using all the available pipelines. Our analysis also shows that parameters as denoising, sharpening, and downsampling are very important to foster diversity. Finally, different benchmarks for classical and wild databases show the good generalization property of the extracted databases. Additional resources are available at github.com/RonyAbecidan/HolisticSteganalysisWithSetCovering.

盲源分离（BSS）算法是无监督的方法，通过允许物理有意义的数据分解，它们是高光谱数据分析的基石。 BSS问题不足，解决方案需要有效的正则化方案，以更好地区分来源并产生可解释的解决方案。为此，我们研究了一种半监督的源分离方法，在这种方法中，我们将预测的交替最小二乘算法与基于学习的正则化方案结合在一起。在本文中，我们专注于通过使用生成模型来限制混合矩阵属于学习的歧管。总而言之，我们表明，这允许具有创新的BSS算法，具有提高的精度，可提供物理上可解释的解决方案。在涉及强噪声，高度相关的光谱和不平衡来源的挑战性场景中，对现实的高光谱天体物理数据进行了测试。结果突出了在减少来源之间的泄漏之前，学到的重大好处，这可以使总体上更好的分解。

本文考虑了在线配置器通常使用的一组替代方案中学习用户偏好的任务。在许多设置中，学习者在过去的互动过程中只有一组选定的替代方案。Fargier等。[2018]提出了一种在这种环境中学习用户偏好模型的方法，该模型对先前选择的替代方案进行了排名尽可能高；以及在这种情况下学习的算法，是一种特定的偏好模型：词典偏好树（LP-Trees）。在本文中，我们研究了与这种方法相关的复杂性理论问题。我们对学习LP-Tree的样本复杂性给出了上限，这在属性数量上是对数。我们还证明，计算最小化经验风险的LP树当仅限于线性LP-Trees的类别时，可以在多项式时间内完成。

我们考虑根据视觉检测自动移动机器人异常的任务。我们对相关类型的视觉异常进行分类，并讨论如何通过无监督的深度学习方法检测到它们。我们提出了一个专门为此任务构建的新型数据集，并在该任务上测试了最先进的方法。我们终于在实际情况下讨论部署。