With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it is still challenging to implement on-device ASR on resource-constrained devices, such as smartphones, smart wearables, and other small home automation devices. In this paper, we propose a series of model architecture adaptions, neural network graph transformations, and numerical optimizations to fit an advanced Conformer based end-to-end streaming ASR system on resource-constrained devices without accuracy degradation. We achieve over 5.26 times faster than realtime (0.19 RTF) speech recognition on small wearables while minimizing energy consumption and achieving state-of-the-art accuracy. The proposed methods are widely applicable to other transformer-based server-free AI applications. In addition, we provide a complete theory on optimal pre-normalizers that numerically stabilize layer normalization in any Lp-norm using any floating point precision.
Recent deep multi-view stereo (MVS) methods have widely incorporated transformers into cascade network for high-resolution depth estimation, achieving impressive results. However, existing transformer-based methods are constrained by their computational costs, preventing their extension to finer stages. In this paper, we propose a novel cross-scale transformer (CT) that processes feature representations at different stages without additional computation. Specifically, we introduce an adaptive matching-aware transformer (AMT) that employs different interactive attention combinations at multiple scales. This combined strategy enables our network to capture intra-image context information and enhance inter-image feature relationships. Besides, we present a dual-feature guided aggregation (DFGA) that embeds the coarse global semantic information into the finer cost volume construction to further strengthen global and local feature awareness. Meanwhile, we design a feature metric loss (FM Loss) that evaluates the feature bias before and after transformation to reduce the impact of feature mismatch on depth estimation. Extensive experiments on DTU dataset and Tanks and Temples (T\&T) benchmark demonstrate that our method achieves state-of-the-art results. Code is available at https://github.com/wscstrive/CT-MVSNet.
Deep learning frameworks (DLFs) have been playing an increasingly important role in this intelligence age since they act as a basic infrastructure for an increasingly wide range of AIbased applications. Meanwhile, as multi-programming-language (MPL) software systems, DLFs are inevitably suffering from bugs caused by the use of multiple programming languages (PLs). Hence, it is of paramount significance to understand the bugs (especially the bugs involving multiple PLs, i.e., MPL bugs) of DLFs, which can provide a foundation for preventing, detecting, and resolving bugs in the development of DLFs. To this end, we manually analyzed 1497 bugs in three MPL DLFs, namely MXNet, PyTorch, and TensorFlow. First, we classified bugs in these DLFs into 12 types (e.g., algorithm design bugs and memory bugs) according to their bug labels and characteristics. Second, we further explored the impacts of different bug types on the development of DLFs, and found that deployment bugs and memory bugs negatively impact the development of DLFs in different aspects the most. Third, we found that 28.6%, 31.4%, and 16.0% of bugs in MXNet, PyTorch, and TensorFlow are MPL bugs, respectively; the PL combination of Python and C/C++ is most used in fixing more than 92% MPL bugs in all DLFs. Finally, the code change complexity of MPL bug fixes is significantly greater than that of single-programming-language (SPL) bug fixes in all the three DLFs, while in PyTorch MPL bug fixes have longer open time and greater communication complexity than SPL bug fixes. These results provide insights for bug management in DLFs.
Soft pneumatic actuators have seen applications in many soft robotic systems, and their pressure-driven nature presents unique challenges and opportunities for controlling their motion. In this work, we present a new concept: designing and controlling pneumatic actuators via end geometry. We demonstrate a novel actuator class, named the folded Pneumatic Artificial Muscle (foldPAM), which features a thin-filmed air pouch that is symmetrically folded on each side. Varying the folded portion of the actuator changes the end constraints and, hence, the force-strain relationships. We investigated this change experimentally by measuring the force-strain relationship of individual foldPAM units with various lengths and amounts of folding. In addition to static-geometry units, an actuated foldPAM device was designed to produce continuous, on-demand adjustment of the end geometry, enabling closed-loop position control while maintaining constant pressure. Experiments with the device indicate that geometry control allows access to different areas on the force-strain plane and that closed-loop geometry control can achieve errors within 0.5% of the actuation range.
Despite the latest prevailing success of deep neural networks (DNNs), several concerns have been raised against their usage, including the lack of intepretability the gap between DNNs and other well-established machine learning models, and the growingly expensive computational costs. A number of recent works [1], [2], [3] explored the alternative to sequentially stacking decision tree/random forest building blocks in a purely feed-forward way, with no need of back propagation. Since decision trees enjoy inherent reasoning transparency, such deep forest models can also facilitate the understanding of the internaldecision making process. This paper further extends the deep forest idea in several important aspects. Firstly, we employ a probabilistic tree whose nodes make probabilistic routing decisions, a.k.a., soft routing, rather than hard binary decisions.Besides enhancing the flexibility, it also enables non-greedy optimization for each tree. Second, we propose an innovative topology learning strategy: every node in the ree now maintains a new learnable hyperparameter indicating the probability that it will be a leaf node. In that way, the tree will jointly optimize both its parameters and the tree topology during training. Experiments on the MNIST dataset demonstrate that our empowered deep forests can achieve better or comparable performance than [1],[3] , with dramatically reduced model complexity. For example,our model with only 1 layer of 15 trees can perform comparably with the model in [3] with 2 layers of 2000 trees each.
Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build a large-scale medical dialogue dataset -- MedDialog -- that contains 1.1 million conversations between patients and doctors and 4 million utterances. To our best knowledge, MedDialog is the largest medical dialogue dataset to date. The dataset is available at https://github.com/UCSD-AI4H/Medical-Dialogue-System
Soft, tip-extending "vine" robots offer a unique mode of inspection and manipulation in highly constrained environments. For practicality, it is desirable that the distal end of the robot can be manipulated freely, while the body remains stationary. However, in previous vine robots, either the shape of the body was fixed after growth with no ability to manipulate the distal end, or the whole body moved together with the tip. Here, we present a concept for shape-locking that enables a vine robot to move only its distal tip, while the body is locked in place. This is achieved using two inextensible, pressurized, tip-extending, chambers that "grow" along the sides of the robot body, preserving curvature in the section where they have been deployed. The length of the locked and free sections can be varied by controlling the extension and retraction of these chambers. We present models describing this shape-locking mechanism and workspace of the robot in both free and constrained environments. We experimentally validate these models, showing an increased dexterous workspace compared to previous vine robots. Our shape-locking concept allows improved performance for vine robots, advancing the field of soft robotics for inspection and manipulation in highly constrained environments.
Several recent works discussed application-driven image restoration neural networks, which are capable of not only removing noise in images but also preserving their semantic-aware details, making them suitable for various high-level computer vision tasks as the pre-processing step. However, such approaches require extra annotations for their high-level vision tasks, in order to train the joint pipeline using hybrid losses. The availability of those annotations is yet often limited to a few image sets, potentially restricting the general applicability of these methods to denoising more unseen and unannotated images. Motivated by that, we propose a segmentation-aware image denoising model dubbed U-SAID, based on a novel unsupervised approach with a pixel-wise uncertainty loss. U-SAID does not need any ground-truth segmentation map, and thus can be applied to any image dataset. It generates denoised images with comparable or even better quality, and the denoised results show stronger robustness for subsequent semantic segmentation tasks, when compared to either its supervised counterpart or classical "application-agnostic" denoisers. Moreover, we demonstrate the superior generalizability of U-SAID in three-folds, by plugging its "universal" denoiser without fine-tuning: (1) denoising unseen types of images; (2) denoising as pre-processing for segmenting unseen noisy images; and (3) denoising for unseen high-level tasks. Extensive experiments demonstrate the effectiveness, robustness and generalizability of the proposed U-SAID over various popular image sets.
Plug-and-play (PnP) is a non-convex framework that integrates modern denoising priors, such as BM3D or deep learning-based denoisers, into ADMM or other proximal algorithms. An advantage of PnP is that one can use pre-trained denoisers when there is not sufficient data for end-to-end training. Although PnP has been recently studied extensively with great empirical success, theoretical analysis addressing even the most basic question of convergence has been insufficient. In this paper, we theoretically establish convergence of PnP-FBS and PnP-ADMM, without using diminishing stepsizes, under a certain Lipschitz condition on the denoisers. We then propose real spectral normalization, a technique for training deep learning-based denoisers to satisfy the proposed Lipschitz condition. Finally, we present experimental results validating the theory.