Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand. Existing ISP designs always adopt a fixed architecture, e.g., several sequential modules connected in
a rigid order. Such a fixed ISP architecture may be suboptimal for real-world applications, where camera sensors, scenes and tasks are diverse. In this study, we propose a novel Reconfigurable ISP (ReconfigISP) whose architecture and parameters can be automatically tailored to specific data and tasks. In particular, we implement several ISP modules, and enable backpropagation for each module by training a differentiable proxy, hence allowing us to leverage the popular differentiable neural architecture search and effectively search for the optimal ISP architecture. A proxy tuning mechanism is adopted to maintain the accuracy of proxy networks in all cases. Extensive experiments conducted on image restoration and object detection, with different sensors, light conditions and efficiency constraints, validate the effectiveness of ReconfigISP. Only hundreds of parameters need tuning for every task.
Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between languages
hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
The weak antilocalization (WAL) effect is known as a quantum correction to the classical conductivity, which never appeared in two-dimensional magnets. In this work, we reported the observation of a WAL effect in the van der Waals ferromagnet Fe5-xGe
Te2 with a Curie temperature Tc ~ 270 K, which can even reach as high as ~ 120 K. The WAL effect could be well described by the Hikami-Larkin-Nagaoka and Maekawa-Fukuyama theories in the presence of strong spin-orbit coupling (SOC). Moreover, A crossover from a peak to dip behavior around 60 K in both the magnetoresistance and magnetoconductance was observed, which could be ascribed to a rare example of temperature driven Lifshitz transition as indicated by the angle-resolved photoemission spectroscopy measurements and first principles calculations. The reflective magnetic circular dichroism measurements indicate a possible spin reorientation that kills the WAL effect above 120 K. Our findings present a rare example of WAL effect in two-dimensional ferromagnet and also a magnetotransport fingerprint of the strong SOC in Fe5-xGeTe2. The results would be instructive for understanding the interaction Hamiltonian for such high Tc itinerant ferromagnetism as well as be helpful for the design of next-generation room temperature spintronic or twistronic devices.
Communication has been seen as a significant bottleneck in industrial applications over large-scale networks. To alleviate the communication burden, sign-based optimization algorithms have gained popularity recently in both industrial and academic co
mmunities, which is shown to be closely related to adaptive gradient methods, such as Adam. Along this line, this paper investigates faster convergence for a variant of sign-based gradient descent, called scaled signGD, in three cases: 1) the objective function is strongly convex; 2) the objective function is nonconvex but satisfies the Polyak-Lojasiewicz (PL) inequality; 3) the gradient is stochastic, called scaled signGD in this case. For the first two cases, it can be shown that the scaled signGD converges at a linear rate. For case 3), the algorithm is shown to converge linearly to a neighborhood of the optimal value when a constant learning rate is employed, and the algorithm converges at a rate of $O(1/k)$ when using a diminishing learning rate, where $k$ is the iteration number. The results are also extended to the distributed setting by majority vote in a parameter-server framework. Finally, numerical experiments on logistic regression are performed to corroborate the theoretical findings.
The neutrino band above 10 PeV remains one of the last multi-messenger windows to be opened, a challenge that several groups tackle. One of the proposed instruments is Trinity, a system of air-shower imaging telescopes to detect Earth-skimming neutri
nos with energies from $10^6$ GeV to $10^{10}$ GeV. We present updated sensitivity calculations demonstrating Trinitys capability of not only detecting the IceCube measured diffuse astrophysical neutrino flux but doing so in an energy band that overlaps with IceCubes. Trinity will distinguish between different cutoff scenarios of the astrophysical neutrino flux, which will help identify their sources. We also discuss Trinitys sensitivity to transient sources on timescales from hours to years.
It was recently proposed that the intensity ratios of several extreme ultraviolet spectral lines from the Fe X ion can be used to measure the solar coronal magnetic field based on the magnetic-field-inducedtransition (MIT) theory. To verify the suita
bility of this method, we performed forward modelingwith a three-dimensional radiation magnetohydrodynamic model of a solar active region. Intensities of several spectral lines from Fe X were synthesized from the model. Based on the MIT theory, intensity ratios of the MIT line Fe X 257 A to several other Fe X lines were used to derive the magnetic field strengths, which were then compared with the field strengths in the model. We also developed a new method to simultaneously estimate the coronal density and temperature from the Fe X 174/175 and 184/345 A line ratios. Using these estimates, we demonstrated that the MIT technique can provide reasonably accurate measurements of the coronal magnetic field in both on-disk and off-limb solar observations. Our investigation suggests that a spectrometer that can simultaneously observe the Fe X 174, 175, 184, 257, and 345 A lines and allow an accurate radiometric calibration for these lines is highly desired to achieve reliable measurements of the coronal magnetic field. We have also evaluatedthe impact of the uncertainty in the Fe X 3p4 3d 4D5/2 and 4D7/2 energy difference on the magnetic field measurements.
A variety is finitely based if it has a finite basis of identities. A minimal non-finitely based variety is called limit. A monoid is aperiodic if all its subgoups are trivial. Limit varieties of aperiodic monoids have been studied by Jackson, Lee, Z
hang and Luo, Gusev and Sapir. In particular, Gusev and Sapir have recently reduced the problem of classifying all limit varieties of aperiodic monoids to the two tasks. One of them is to classify limit varieties of monoids satisfying $xsxt approx xsxtx$. In this paper, we completely solve this task. In particular, we exhibit the first example of a limit variety of monoids with countably infinitely many subvarieties. In view of the result by Jackson and Lee, the smallest known monoid generating a variety with continuum many subvarieties is of order six. It follows from the result by Edmunds et al. that if there exists a smaller example, then up to isomorphism and anti-isomorphism, it must be a unique monoid $P_2^1$ of order five. Our main result implies that the variety generated by $P_2^1$ contains only finitely based subvarieties and so has only countably many of them.
In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging transfer learning across modalities
, tasks and languages. First, we leverage general-purpose multilingual modules pretrained with large amounts of unlabelled and labelled data. We further enable knowledge transfer from the text task to the speech task by training two tasks jointly. Finally, our multilingual model is finetuned on speech translation task-specific data to achieve the best translation results. Experimental results show our system outperforms the reported systems, including both end-to-end and cascaded based approaches, by a large margin. In some translation directions, our speech translation results evaluated on the public Multilingual TEDx test set are even comparable with the ones from a strong text-to-text translation system, which uses the oracle speech transcripts as input.
Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation model along with an auxiliary text to text translation task. We conduc
t a detailed analysis to understand the impact of the auxiliary task on the primary task within the multitask learning framework. Our analysis confirms that multitask learning tends to generate similar decoder representations from different modalities and preserve more information from the pretrained text translation modules. We observe minimal negative transfer effect between the two tasks and sharing more parameters is helpful to transfer knowledge from the text task to the speech task. The analysis also reveals that the modality representation difference at the top decoder layers is still not negligible, and those layers are critical for the translation quality. Inspired by these findings, we propose three methods to improve translation quality. First, a parameter sharing and initialization strategy is proposed to enhance information sharing between the tasks. Second, a novel attention-based regularization is proposed for the encoders and pulls the representations from different modalities closer. Third, an online knowledge distillation is proposed to enhance the knowledge transfer from the text to the speech task. Our experiments show that the proposed approach improves translation performance by more than 2 BLEU over a strong baseline and achieves state-of-the-art results on the textsc{MuST-C} English-German, English-French and English-Spanish language pairs.
Mobile edge computing (MEC) has recently become a prevailing technique to alleviate the intensive computation burden in Internet of Things (IoT) networks. However, the limited device battery capacity and stringent spectrum resource significantly rest
rict the data processing performance of MEC-enabled IoT networks. To address the two performance limitations, we consider in this paper an MEC-enabled IoT system with an energy harvesting (EH) wireless device (WD) which opportunistically accesses the licensed spectrum of an overlaid primary communication link for task offloading. We aim to maximize the long-term average sensing rate of the WD subject to quality of service (QoS) requirement of primary link, average power constraint of MEC server (MS) and data queue stability of both MS and WD. We formulate the problem as a multi-stage stochastic optimization and propose an online algorithm named PLySE that applies the perturbed Lyapunov optimization technique to decompose the original problem into per-slot deterministic optimization problems. For each per-slot problem, we derive the closed-form optimal solution of data sensing and processing control to facilitate low-complexity real-time implementation. Interestingly, our analysis finds that the optimal solution exhibits an threshold-based structure. Simulation results collaborate with our analysis and demonstrate more than 46.7% data sensing rate improvement of the proposed PLySE over representative benchmark methods.
