Few-shot learning (FSL) aims to address the data-scarce problem. A standard FSL framework is composed of two components: (1) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). (2) Meta-test. Apply the trained FEM
to acquire the novel datas features and recognize them. FSL relies heavily on the design of the FEM. However, various FEMs have distinct emphases. For example, several may focus more attention on the contour information, whereas others may lay particular emphasis on the texture information. The single-head feature is only a one-sided representation of the sample. Besides the negative influence of cross-domain (e.g., the trained FEM can not adapt to the novel class flawlessly), the distribution of novel data may have a certain degree of deviation compared with the ground truth distribution, which is dubbed as distribution-shift-problem (DSP). To address the DSP, we propose Multi-Head Feature Collaboration (MHFC) algorithm, which attempts to project the multi-head features (e.g., multiple features extracted from a variety of FEMs) to a unified space and fuse them to capture more discriminative information. Typically, first, we introduce a subspace learning method to transform the multi-head features to aligned low-dimensional representations. It corrects the DSP via learning the feature with more powerful discrimination and overcomes the problem of inconsistent measurement scales from different head features. Then, we design an attention block to update combination weights for each head feature automatically. It comprehensively considers the contribution of various perspectives and further improves the discrimination of features. We evaluate the proposed method on five benchmark datasets (including cross-domain experiments) and achieve significant improvements of 2.1%-7.8% compared with state-of-the-arts.
Deep neural networks (DNNs) are vulnerable to adversarial noises, which motivates the benchmark of model robustness. Existing benchmarks mainly focus on evaluating the defenses, but there are no comprehensive studies of how architecture design and ge
neral training techniques affect robustness. Comprehensively benchmarking their relationships will be highly beneficial for better understanding and developing robust DNNs. Thus, we propose RobustART, the first comprehensive Robustness investigation benchmark on ImageNet (including open-source toolkit, pre-trained model zoo, datasets, and analyses) regarding ARchitecture design (44 human-designed off-the-shelf architectures and 1200+ networks from neural architecture search) and Training techniques (10+ general techniques, e.g., data augmentation) towards diverse noises (adversarial, natural, and system noises). Extensive experiments revealed and substantiated several insights for the first time, for example: (1) adversarial training largely improves the clean accuracy and all types of robustness for Transformers and MLP-Mixers; (2) with comparable sizes, CNNs > Transformers > MLP-Mixers on robustness against natural and system noises; Transformers > MLP-Mixers > CNNs on adversarial robustness; (3) for some light-weight architectures (e.g., EfficientNet, MobileNetV2, and MobileNetV3), increasing model sizes or using extra training data cannot improve robustness. Our benchmark http://robust.art/ : (1) presents an open-source platform for conducting comprehensive evaluation on diverse robustness types; (2) provides a variety of pre-trained models with different training techniques to facilitate robustness evaluation; (3) proposes a new view to better understand the mechanism towards designing robust DNN architectures, backed up by the analysis. We will continuously contribute to building this ecosystem for the community.
Surface Van Hove singularity (SVHS), defined as the surface states near the Fermi level (EF) in low-dimensional systems, triggers exciting physical phenomena distinct from bulk. We herein explore theoretically the potential role of SVHS in catalysis
taking CO oxidation reaction as prototype over graphene/Ca2N (Gra/Ca2N) heterojunction and Pt2HgSe3 (001) surface. It is demonstrated that both systems with SVHS could serve as an electron bath to promote O2 adsorption and subsequent CO oxidation with low energy barriers of 0.2 ~ 0.6 eV for Gra/Ca2N and Pt2HgSe3 (001) surface. Importantly, the catalytically active sites associated with SVHS are well-defined and uniformly distributed over the whole surface plane, which is superior to the commonly adopted defect or doping strategy, and further the chemical reactivity of SVHS also can be tuned easily via adjusting its position with respect to EF. Our study demonstrates the enabling power of SVHS, and provides novel physical insights into the promising potential role of VHS in designing high-efficiency catalysts.
The method of geometrization arises as an important tool in understanding the entanglement of quantum fields and the behavior of the many-body system. The symplectic structure of the boson operators provide a natural way to geometrize the quantum dyn
amics of the bosonic systems of quadratic Hamiltonians, by recognizing that the time evolution operator corresponds to a real symplectic matrix in $Sp(4,R)$ group. We apply this geometrization scheme to study the quantum dynamics of the spinor Bose-Einstein condensate systems, demonstrating that the quantum dynamics of this system can be represented by trajectories in a six dimensional manifold. It is found that the trajectory is quasi-periodic for coupled bosons. The expectation value of the observables can also be naturally calculated through this approach.
Mobile edge computing (MEC) is proposed to boost high-efficient and time-sensitive 5G applications. However, the microburst may occur even in lightly-loaded scenarios, which leads to the indeterministic service latency (i.e., unpredictable delay or d
elay variation), hence hindering the deployment of MEC. Deterministic IP networking (DIP) has been proposed that can provide bounds on latency, and high reliability in the large-scale networks. Nevertheless, the direct migration of DIP into the MEC network is non-trivial owing to its original design for the Ethernet with homogeneous devices. Meanwhile, DIP also faces the challenges on the network throughput and scheduling flexibility. In this paper, we delve into the adoption of DIP for the MEC networks and some of the relevant aspects. A deterministic MEC (D-MEC) network is proposed to deliver the deterministic service (i.e., providing the MEC service with bounded service latency). In the D-MEC network, two mechanisms, including the cycle mapping and cycle shifting, are designed to enable: (i) seamless and deterministic transmission with heterogeneous underlaid resources; and (ii) traffic shaping on the edges to improve the resource utilization. We also formulate a joint configuration to maximize the network throughput with deterministic QoS guarantees. Extensive simulations verify that the proposed D-MEC network can achieve a deterministic MEC service, even in the highly-loaded scenarios.
A class of binary sequences with period $2p$ is constructed using generalized cyclotomic classes, and their linear complexity, minimal polynomial over ${mathbb{F}_{{q}}}$ as well as 2-adic complexity are determined using Gauss period and group ring t
heory. The results show that the linear complexity of these sequences attains the maximum when $pequiv pm 1(bmod~8)$ and is equal to {$p$+1} when $pequiv pm 3(bmod~8)$ over extension field. Moreover, the 2-adic complexity of these sequences is maximum. According to Berlekamp-Massey(B-M) algorithm and the rational approximation algorithm(RAA), these sequences have quite good cryptographyic properties in the aspect of linear complexity and 2-adic complexity.
Systematic error, which is not determined by chance, often refers to the inaccuracy (involving either the observation or measurement process) inherent to a system. In this paper, we exhibit some long-neglected but frequent-happening adversarial examp
les caused by systematic error. More specifically, we find the trained neural network classifier can be fooled by inconsistent implementations of image decoding and resize. This tiny difference between these implementations often causes an accuracy drop from training to deployment. To benchmark these real-world adversarial examples, we propose ImageNet-S dataset, which enables researchers to measure a classifiers robustness to systematic error. For example, we find a normal ResNet-50 trained on ImageNet can have 1%-5% accuracy difference due to the systematic error. Together our evaluation and dataset may aid future work toward real-world robustness and practical generalization.
The explosive increase of multimodal data makes a great demand in many cross-modal applications that follow the strict prior related assumption. Thus researchers study the definition of cross-modal correlation category and construct various classific
ation systems and predictive models. However, those systems pay more attention to the fine-grained relevant types of cross-modal correlation, ignoring lots of implicit relevant data which are often divided into irrelevant types. Whats worse is that none of previous predictive models manifest the essence of cross-modal correlation according to their definition at the modeling stage. In this paper, we present a comprehensive analysis of the image-text correlation and redefine a new classification system based on implicit association and explicit alignment. To predict the type of image-text correlation, we propose the Association and Alignment Network according to our proposed definition (namely AnANet) which implicitly represents the global discrepancy and commonality between image and text and explicitly captures the cross-modal local relevance. The experimental results on our constructed new image-text correlation dataset show the effectiveness of our model.
We predict a new effect due to the presence of the global vorticity in non-central relativistic heavy-ion collisions, namely a splitting of the elliptic flow parameter $v_2$ at non-zero rapidity. The size of the splitting is proposed as a new observa
ble that can be used to constrain the initial vortical configuration of the produced QCD matter in experiments. The new findings are demonstrated by numerical calculations employing the parton cascade model, Boltzmann Approach of MultiParton Scatterings (BAMPS), for non-central Au + Au collisions at $sqrt{s_{NN}} = 200 GeV$.
Hadwiger conjectured in 1943 that for every integer $t ge 1$, every graph with no $K_t$ minor is $(t-1)$-colorable. Kostochka, and independently Thomason, proved every graph with no $K_t$ minor is $O(t(log t)^{1/2})$-colorable. Recently, Postle impro
ved it to $O(t (log log t)^6)$-colorable. In this paper, we show that every graph with no $K_t$ minor is $O(t (log log t)^{5})$-colorable.
