弱监督的对象本地化（WSOL）旨在学习仅使用图像级类别标签编码对象位置的表示形式。但是，许多物体可以在不同水平的粒度标记。它是动物，鸟还是大角的猫头鹰？我们应该使用哪些图像级标签？在本文中，我们研究了标签粒度在WSOL中的作用。为了促进这项调查，我们引入了Inatloc500，这是一个新的用于WSOL的大规模细粒基准数据集。令人惊讶的是，我们发现选择正确的训练标签粒度比选择最佳的WSOL算法提供了更大的性能。我们还表明，更改标签粒度可以显着提高数据效率。

Optical coherence tomography (OCT) captures cross-sectional data and is used for the screening, monitoring, and treatment planning of retinal diseases. Technological developments to increase the speed of acquisition often results in systems with a narrower spectral bandwidth, and hence a lower axial resolution. Traditionally, image-processing-based techniques have been utilized to reconstruct subsampled OCT data and more recently, deep-learning-based methods have been explored. In this study, we simulate reduced axial scan (A-scan) resolution by Gaussian windowing in the spectral domain and investigate the use of a learning-based approach for image feature reconstruction. In anticipation of the reduced resolution that accompanies wide-field OCT systems, we build upon super-resolution techniques to explore methods to better aid clinicians in their decision-making to improve patient outcomes, by reconstructing lost features using a pixel-to-pixel approach with an altered super-resolution generative adversarial network (SRGAN) architecture.

Springs can provide force at zero net energy cost by recycling negative mechanical work to benefit motor-driven robots or spring-augmented humans. However, humans have limited force and range of motion, and motors have a limited ability to produce force. These limits constrain how much energy a conventional spring can store and, consequently, how much assistance a spring can provide. In this paper, we introduce an approach to accumulating negative work in assistive springs over several motion cycles. We show that, by utilizing a novel floating spring mechanism, the weight of a human or robot can be used to iteratively increase spring compression, irrespective of the potential energy stored by the spring. Decoupling the force required to compress a spring from the energy stored by a spring advances prior works, and could enable spring-driven robots and humans to perform physically demanding tasks without the use of large actuators.

Previous work has shown that a neural network with the rectified linear unit (ReLU) activation function leads to a convex polyhedral decomposition of the input space. These decompositions can be represented by a dual graph with vertices corresponding to polyhedra and edges corresponding to polyhedra sharing a facet, which is a subgraph of a Hamming graph. This paper illustrates how one can utilize the dual graph to detect and analyze adversarial attacks in the context of digital images. When an image passes through a network containing ReLU nodes, the firing or non-firing at a node can be encoded as a bit ($1$ for ReLU activation, $0$ for ReLU non-activation). The sequence of all bit activations identifies the image with a bit vector, which identifies it with a polyhedron in the decomposition and, in turn, identifies it with a vertex in the dual graph. We identify ReLU bits that are discriminators between non-adversarial and adversarial images and examine how well collections of these discriminators can ensemble vote to build an adversarial image detector. Specifically, we examine the similarities and differences of ReLU bit vectors for adversarial images, and their non-adversarial counterparts, using a pre-trained ResNet-50 architecture. While this paper focuses on adversarial digital images, ResNet-50 architecture, and the ReLU activation function, our methods extend to other network architectures, activation functions, and types of datasets.

We address the problem of synthesizing novel views from a monocular video depicting a complex dynamic scene. State-of-the-art methods based on temporally varying Neural Radiance Fields (aka dynamic NeRFs) have shown impressive results on this task. However, for long videos with complex object motions and uncontrolled camera trajectories, these methods can produce blurry or inaccurate renderings, hampering their use in real-world applications. Instead of encoding the entire dynamic scene within the weights of an MLP, we present a new approach that addresses these limitations by adopting a volumetric image-based rendering framework that synthesizes new viewpoints by aggregating features from nearby views in a scene-motion-aware manner. Our system retains the advantages of prior methods in its ability to model complex scenes and view-dependent effects, but also enables synthesizing photo-realistic novel views from long videos featuring complex scene dynamics with unconstrained camera trajectories. We demonstrate significant improvements over state-of-the-art methods on dynamic scene datasets, and also apply our approach to in-the-wild videos with challenging camera and object motion, where prior methods fail to produce high-quality renderings. Our project webpage is at dynibar.github.io.

Artificial intelligence methods including deep neural networks (DNN) can provide rapid molecular classification of tumors from routine histology with accuracy that matches or exceeds human pathologists. Discerning how neural networks make their predictions remains a significant challenge, but explainability tools help provide insights into what models have learned when corresponding histologic features are poorly defined. Here, we present a method for improving explainability of DNN models using synthetic histology generated by a conditional generative adversarial network (cGAN). We show that cGANs generate high-quality synthetic histology images that can be leveraged for explaining DNN models trained to classify molecularly-subtyped tumors, exposing histologic features associated with molecular state. Fine-tuning synthetic histology through class and layer blending illustrates nuanced morphologic differences between tumor subtypes. Finally, we demonstrate the use of synthetic histology for augmenting pathologist-in-training education, showing that these intuitive visualizations can reinforce and improve understanding of histologic manifestations of tumor biology.

The de facto standard of dynamic histogram binning for radiomic feature extraction leads to an elevated sensitivity to fluctuations in annotated regions. This may impact the majority of radiomic studies published recently and contribute to issues regarding poor reproducibility of radiomic-based machine learning that has led to significant efforts for data harmonization; however, we believe the issues highlighted here are comparatively neglected, but often remedied by choosing static binning. The field of radiomics has improved through the development of community standards and open-source libraries such as PyRadiomics. But differences in image acquisition, systematic differences between observers' annotations, and preprocessing steps still pose challenges. These can change the distribution of voxels altering extracted features and can be exacerbated with dynamic binning.

事实证明，诸如层归一化（LN）和批处理（BN）之类的方法可有效改善复发性神经网络（RNN）的训练。但是，现有方法仅在一个特定的时间步骤中仅使用瞬时信息进行归一化，而归一化的结果是具有时间无关分布的预反应状态。该实现无法解释RNN的输入和体系结构中固有的某些时间差异。由于这些网络跨时间步骤共享权重，因此也可能需要考虑标准化方案中时间步长之间的连接。在本文中，我们提出了一种称为“分类时间归一化”（ATN）的归一化方法，该方法保留了来自多个连续时间步骤的信息，并使用它们归一化。这种设置使我们能够将更长的时间依赖项引入传统的归一化方法，而无需引入任何新的可训练参数。我们介绍了梯度传播的理论推导，并证明了权重缩放不变属性。我们将ATN应用于LN的实验表明，对各种任务（例如添加，复制和DENOISE问题和语言建模问题）表现出一致的改进。

在原始文本中训练的语言模型（LMS）无法直接访问物理世界。 Gordon和Van Durme（2013）指出，LMS因此可能会遭受报告偏见的困扰：文本很少报告常见事实，而是关注情况的异常方面。如果LMS仅接受文本语料库的培训，并天真地记住当地的同时出现统计数据，那么他们自然会学会对物理世界的偏见。虽然先前的研究反复验证了较小尺度的LM（例如Roberta，GPT-2）放大了报告偏差，但在模型扩展时，这种趋势是否继续。我们从较大语言模型（LLM）（例如Palm和GPT-3）中从颜色的角度研究报告偏见。具体而言，我们查询llms对物体的典型颜色，这是一种简单的感知扎根的物理常识。令人惊讶的是，我们发现LLM在确定对象的典型颜色和更紧密地跟踪人类判断方面的表现明显优于较小的LMS，而不是过于适应文本中存储的表面图案。这表明，仅凭语言的大型语言模型就能克服以局部共发生为特征的某些类型的报告偏差。

我们引入了一种新的文化学习范式，以测量在推理过程中学习新颖单词的大型语言模型（LLMS）。特别是，我们通过用一个合成但合理的词代替关键概念词来重写Winograd风格的共同参考分辨率问题，该词必须理解该模型以完成任务。解决此任务需要模型来利用提示中给出的新单词的字典定义。这个基准介绍了单词获取，这是折磨llms已知的历时降解的一个重要方面。由于LLM在训练的那一刻及时被冻结，因此通常无法反映语言随着时间的变化方式。我们表明，与原始Winograd任务相比，LLM的准确性在我们的基准测试中从根本上降低，从而确定了当前模型的局限性，并提供了基准来衡量LLMS的未来改善LLMS进行内在学习的能力。