From Contexts to Locality: Ultra-high Resolution Image Segmentation via Locality-aware Contextual Correlation

Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resolution image segmentation pipeline, in which an ultra-high resolution image is partitioned into regular patches for local segmentation and then the local results are merged into a high-resolution semantic mask. In particular, we introduce a novel locality-aware contextual correlation based segmentation model to process local patches, where the relevance between local patch and its various contexts are jointly and complementarily utilized to handle the semantic regions with large variations. Additionally, we present a contextual semantics refinement network that associates the local segmentation result with its contextual semantics, and thus is endowed with the ability of reducing boundary artifacts and refining mask contours during the generation of final high-resolution mask. Furthermore, in comprehensive experiments, we demonstrate that our model outperforms other state-of-the-art methods in public benchmarks. Our released codes are available at https://github.com/liqiokkk/FCtL.

Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densities

In the context of the global coronavirus pandemic, different deep learning solutions for infected subject detection using chest X-ray images have been proposed. However, deep learning models usually need large labelled datasets to be effective. Semi-supervised deep learning is an attractive alternative, where unlabelled data is leveraged to improve the overall models accuracy. However, in real-world usage settings, an unlabelled dataset might present a different distribution than the labelled dataset (i.e. the labelled dataset was sampled from a target clinic and the unlabelled dataset from a source clinic). This results in a distribution mismatch between the unlabelled and labelled datasets. In this work, we assess the impact of the distribution mismatch between the labelled and the unlabelled datasets, for a semi-supervised model trained with chest X-ray images, for COVID-19 detection. Under strong distribution mismatch conditions, we found an accuracy hit of almost 30%, suggesting that the unlabelled dataset distribution has a strong influence in the behaviour of the model. Therefore, we propose a straightforward approach to diminish the impact of such distribution mismatch. Our proposed method uses a density approximation of the feature space. It is built upon the target dataset to filter out the observations in the source unlabelled dataset that might harm the accuracy of the semi-supervised model. It assumes that a small labelled source dataset is available together with a larger source unlabelled dataset. Our proposed method does not require any model training, it is simple and computationally cheap. We compare our proposed method against two popular state of the art out-of-distribution data detectors, which are also cheap and simple to implement. In our tests, our method yielded accuracy gains of up to 32%, when compared to the previous state of the art methods.

A remark on ill-posedness

Norm inflation implies certain discontinuous dependence of the solution on the initial value. The well-posedness of the mild solution means the existence and uniqueness of the fixed points of the corresponding integral equation. For ${rm BMO}^{-1}$, Auscher-Dubois-Tchamitchian proved that Koch-Tatarus solution is stable. In this paper, we construct a non-Gauss flow function to show that, for classic Navier-Stokes equations, wellposedness and norm inflation may have no conflict and stability may have meaning different to $L^{infty}(({rm BMO}^{-1})^{n})$.

Measurement of undulator section wakefield at the SXFEL test facility

In free electron laser facilities, almost every kind of device will generate wakefield when an electron beam passes through it. Most of the wakefields are undesired and have a negative effect on the electron beam, which means a decrease of FEL performance. As for the SXFEL test facility, the sophisticated layout and the cumulative effect of such a long undulator section lead to an obvious wakefield, which is strong enough that can not be ignored. Based on two deflecting cavities at the entrance and the exit of the undulator section with corresponding profile monitors, we measured the wakefield of the undulator section. In this paper, we give the theoretical and simulation results of resistive wall wakefields which agree well with each other. In addition, the experimental and the simulation results of the overall undulator wakefield are given showing small difference. In order to explore the impact of this wakefield on FEL lasing, we give the simulation results of FEL with and without wakefield for comparison. There is almost no impact on 44 nm FEL in stage-1 of cascaded EEHG-HGHG mode, while the impact on 8.8 nm FEL in stage-2 becomes critical decreasing the pulse energy and peak power by 42% and 27% and broadening the bandwidth.

A Multiobjective State Transition Algorithm Based on Decomposition

Aggregation functions largely determine the convergence and diversity performance of multi-objective evolutionary algorithms in decomposition methods. Nevertheless, the traditional Tchebycheff function does not consider the matching relationship between the weight vectors and candidate solutions. In this paper, the concept of matching degree is proposed which employs vectorial angles between weight vectors and candidate solutions. Based on the matching degree, a new modified Tchebycheff aggregation function is proposed, which integrates matching degree into the Tchebycheff aggregation function. Moreover, the proposed decomposition method has the same functionality with the Tchebycheff aggregation function. Based on the proposed decomposition approach, a new multiobjective optimization algorithm named decomposition-based multi-objective state transition algorithm is proposed. Relevant experimental results show that the proposed algorithm is highly competitive in comparison with other state-of-the-art multiobjetive optimization algorithms.

The diverse nature of small-scale turbulence

The self-similar Richardson cascade admits two logically possible scenarios of small-scale turbulence at high Reynolds numbers. In the first scenario, eddies population densities vary as a function of eddies scales. As a result, one or a few eddy types dominate at small scales, and small-scale turbulence lacks diversity. In the second scenario, eddies population densities are scale-invariant across the inertial range, resulting in small-scale diversity. That is, there are as many types of eddies at the small scales as at the large scales. In this letter, we measure eddies population densities in three-dimensional isotropic turbulence and determine the nature of small-scale turbulence. The result shows that eddies population densities are scale-invariant.

On the vertex-degree based invariants of digraphs

Let $D=(V,A)$ be a digraphs without isolated vertices. A vertex-degree based invariant $I(D)$ related to a real function $varphi$ of $D$ is defined as a summation over all arcs, $I(D) = frac{1}{2}sum_{uvin A}{varphi(d_u^+,d_v^-)}$, where $d_u^+$ (resp. $d_u^-$) denotes the out-degree (resp. in-degree) of a vertex $u$. In this paper, we give the extremal values and extremal digraphs of $I(D)$ over all digraphs with $n$ non-isolated vertices. Applying these results, we obtain the extremal values of some vertex-degree based topological indices of digraphs, such as the Randi{c} index, the Zagreb index, the sum-connectivity index, the $GA$ index, the $ABC$ index and the harmonic index, and the corresponding extremal digraphs.

Fast and Efficient Locomotion via Learned Gait Transitions

We focus on the problem of developing energy efficient controllers for quadrupedal robots. Animals can actively switch gaits at different speeds to lower their energy consumption. In this paper, we devise a hierarchical learning framework, in which distinctive locomotion gaits and natural gait transitions emerge automatically with a simple reward of energy minimization. We use reinforcement learning to train a high-level gait policy that specifies gait patterns of each foot, while the low-level whole-body controller optimizes the motor commands so that the robot can walk at a desired velocity using that gait pattern. We test our learning framework on a quadruped robot and demonstrate automatic gait transitions, from walking to trotting and to fly-trotting, as the robot increases its speed. We show that the learned hierarchical controller consumes much less energy across a wide range of locomotion speed than baseline controllers.

Covariant Quantum Error Correcting Codes via Reference Frames

Error correcting codes with a universal set of transversal gates are the desiderata of realising quantum computing. Such codes, however, are ruled out by the Eastin-Knill theorem. Moreover, it also rules out codes which are covariant with respect to the action of transversal unitary operations forming continuous symmetries. In this work, starting from an arbitrary code, we construct approximate codes which are covariant with respect to local $SU(d)$ symmetries using quantum reference frames. We show that our codes are capable of efficiently correcting different types of erasure errors. When only a small fraction of the $n$ qudits upon which the code is built are erased, our covariant code has an error that scales as $1/n^2$, which is reminiscent of the Heisenberg limit of quantum metrology. When every qudit has a chance of being erased, our covariant code has an error that scales as $1/n$. We show that the error scaling is optimal in both cases. Our approach has implications for fault-tolerant quantum computing, reference frame error correction, and the AdS-CFT duality.

Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning

Learning adaptable policies is crucial for robots to operate autonomously in our complex and quickly changing world. In this work, we present a new meta-learning method that allows robots to quickly adapt to changes in dynamics. In contrast to gradient-based meta-learning algorithms that rely on second-order gradient estimation, we introduce a more noise-tolerant Batch Hill-Climbing adaptation operator and combine it with meta-learning based on evolutionary strategies. Our method significantly improves adaptation to changes in dynamics in high noise settings, which are common in robotics applications. We validate our approach on a quadruped robot that learns to walk while subject to changes in dynamics. We observe that our method significantly outperforms prior gradient-based approaches, enabling the robot to adapt its policy to changes based on less than 3 minutes of real data.