许多压缩和加速策略在各个领域的分类任务中取得了出色的结果，例如计算机视觉和语音信号处理。尽管如此，相同的策略在回归任务中产生了未展现的性能，因为这些和分类任务之间的性质不同。在本文中，提出了一种新的签名唯一浮点网络（SEOFP-Net）技术来压缩模型大小并加速语音增强的推理时间，是语音信号处理的回归任务。该方法通过在训练期间量化单精度浮点参数的分数比量来压缩深神经网络（DNN）的语音增强模型的大小。在推理实现之前，略微调整训练SEOFP-NET模型中的所有参数，以通过用整数加法器替换浮点乘法器来加速推理时间。为了概括，SEOFP-NET技术被引入到不同模特架构下的语音信号处理中的不同语音增强任务。实验结果表明，在没有明显降级其语音增强性能的情况下，SEOFP-Net模型的大小可以显着压缩，并且与基线模型相比，推理时间可以加速至1.212x。结果还验证建议的SEOFP-NET可以与其他效率策略合作，以实现模型压缩的协同效果。此外，仅适用于用户学习实验的刚刚明显的差异（JND），以统计分析语音增强对听力的影响。结果表明，听众不能轻松地区分基线模型处理的增强语音信号和所提出的SEOFP网之间。

嵌套辍学是辍学操作的变体，能够根据训练期间的预定义重要性订购网络参数或功能。它已被探索：I。构造嵌套网络：嵌套网是神经网络，可以在测试时间（例如基于计算约束）中立即调整架构的架构。嵌套的辍学者隐含地对网络参数进行排名，生成一组子网络，从而使任何较小的子网络构成较大的子网络的基础。 ii。学习排序表示：应用于生成模型的潜在表示（例如自动编码器）对特征进行排名，从而在尺寸上执行密集表示的明确顺序。但是，在整个训练过程中，辍学率是固定为高参数的。对于嵌套网，当删除网络参数时，性能衰减在人类指定的轨迹中而不是从数据中学到的轨迹中。对于生成模型，特征的重要性被指定为恒定向量，从而限制了表示学习的灵活性。为了解决该问题，我们专注于嵌套辍学的概率对应物。我们提出了一个嵌套掉落（VND）操作，该操作以低成本绘制多维有序掩码的样品，为嵌套掉落的参数提供了有用的梯度。基于这种方法，我们设计了一个贝叶斯嵌套的神经网络，以了解参数分布的顺序知识。我们在不同的生成模型下进一步利用VND来学习有序的潜在分布。在实验中，我们表明所提出的方法在分类任务中的准确性，校准和室外检测方面优于嵌套网络。它还在数据生成任务上胜过相关的生成模型。

This paper expounds the design and control of a new Variable Stiffness Series Elastic Actuator (VSSEA). It is established by employing a modular mechanical design approach that allows us to effectively optimise the stiffness modulation characteristics and power density of the actuator. The proposed VSSEA possesses the following features: i) no limitation in the work-range of output link, ii) a wide range of stiffness modulation (~20Nm/rad to ~1KNm/rad), iii) low-energy-cost stiffness modulation at equilibrium and non-equilibrium positions, iv) compact design and high torque density (~36Nm/kg), and v) high-speed stiffness modulation (~3000Nm/rad/s). Such features can help boost the safety and performance of many advanced robotic systems, e.g., a cobot that physically interacts with unstructured environments and an exoskeleton that provides physical assistance to human users. These features can also enable us to utilise variable stiffness property to attain various regulation and trajectory tracking control tasks only by employing conventional controllers, eliminating the need for synthesising complex motion control systems in compliant actuation. To this end, it is experimentally demonstrated that the proposed VSSEA is capable of precisely tracking desired position and force control references through the use of conventional Proportional-Integral-Derivative (PID) controllers.

Object instance segmentation is a key challenge for indoor robots navigating cluttered environments with many small objects. Limitations in 3D sensing capabilities often make it difficult to detect every possible object. While deep learning approaches may be effective for this problem, manually annotating 3D data for supervised learning is time-consuming. In this work, we explore zero-shot instance segmentation (ZSIS) from RGB-D data to identify unseen objects in a semantic category-agnostic manner. We introduce a zero-shot split for Tabletop Objects Dataset (TOD-Z) to enable this study and present a method that uses annotated objects to learn the ``objectness'' of pixels and generalize to unseen object categories in cluttered indoor environments. Our method, SupeRGB-D, groups pixels into small patches based on geometric cues and learns to merge the patches in a deep agglomerative clustering fashion. SupeRGB-D outperforms existing baselines on unseen objects while achieving similar performance on seen objects. Additionally, it is extremely lightweight (0.4 MB memory requirement) and suitable for mobile and robotic applications. The dataset split and code will be made publicly available upon acceptance.

A self-supervised adaptive low-light video enhancement (SALVE) method is proposed in this work. SALVE first conducts an effective Retinex-based low-light image enhancement on a few key frames of an input low-light video. Next, it learns mappings from the low- to enhanced-light frames via Ridge regression. Finally, it uses these mappings to enhance the remaining frames in the input video. SALVE is a hybrid method that combines components from a traditional Retinex-based image enhancement method and a learning-based method. The former component leads to a robust solution which is easily adaptive to new real-world environments. The latter component offers a fast, computationally inexpensive and temporally consistent solution. We conduct extensive experiments to show the superior performance of SALVE. Our user study shows that 87% of participants prefer SALVE over prior work.

Hyperparameter tuning is critical to the success of federated learning applications. Unfortunately, appropriately selecting hyperparameters is challenging in federated networks. Issues of scale, privacy, and heterogeneity introduce noise in the tuning process and make it difficult to evaluate the performance of various hyperparameters. In this work, we perform the first systematic study on the effect of noisy evaluation in federated hyperparameter tuning. We first identify and rigorously explore key sources of noise, including client subsampling, data and systems heterogeneity, and data privacy. Surprisingly, our results indicate that even small amounts of noise can significantly impact tuning methods-reducing the performance of state-of-the-art approaches to that of naive baselines. To address noisy evaluation in such scenarios, we propose a simple and effective approach that leverages public proxy data to boost the evaluation signal. Our work establishes general challenges, baselines, and best practices for future work in federated hyperparameter tuning.

We present a simple approach which can turn a ViT encoder into an efficient video model, which can seamlessly work with both image and video inputs. By sparsely sampling the inputs, the model is able to do training and inference from both inputs. The model is easily scalable and can be adapted to large-scale pre-trained ViTs without requiring full finetuning. The model achieves SOTA results and the code will be open-sourced.

We propose a novel hematoxylin and eosin (H&E) stain normalization method based on a modified U-Net neural network architecture. Unlike previous deep-learning methods that were often based on generative adversarial networks (GANs), we take a teacher-student approach and use paired datasets generated by a trained CycleGAN to train a U-Net to perform the stain normalization task. Through experiments, we compared our method to two recent competing methods, CycleGAN and StainNet, a lightweight approach also based on the teacher-student model. We found that our method is faster and can process larger images with better quality compared to CycleGAN. We also compared to StainNet and found that our method delivered quantitatively and qualitatively better results.

The increased importance of mobile photography created a need for fast and performant RAW image processing pipelines capable of producing good visual results in spite of the mobile camera sensor limitations. While deep learning-based approaches can efficiently solve this problem, their computational requirements usually remain too large for high-resolution on-device image processing. To address this limitation, we propose a novel PyNET-V2 Mobile CNN architecture designed specifically for edge devices, being able to process RAW 12MP photos directly on mobile phones under 1.5 second and producing high perceptual photo quality. To train and to evaluate the performance of the proposed solution, we use the real-world Fujifilm UltraISP dataset consisting on thousands of RAW-RGB image pairs captured with a professional medium-format 102MP Fujifilm camera and a popular Sony mobile camera sensor. The results demonstrate that the PyNET-V2 Mobile model can substantially surpass the quality of tradition ISP pipelines, while outperforming the previously introduced neural network-based solutions designed for fast image processing. Furthermore, we show that the proposed architecture is also compatible with the latest mobile AI accelerators such as NPUs or APUs that can be used to further reduce the latency of the model to as little as 0.5 second. The dataset, code and pre-trained models used in this paper are available on the project website: https://github.com/gmalivenko/PyNET-v2

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.