Previous studies demonstrate DNNs vulnerability to adversarial examples and adversarial training can establish a defense to adversarial examples. In addition, recent studies show that deep neural networks also exhibit vulnerability to parameter corru
ptions. The vulnerability of model parameters is of crucial value to the study of model robustness and generalization. In this work, we introduce the concept of parameter corruption and propose to leverage the loss change indicators for measuring the flatness of the loss basin and the parameter robustness of neural network parameters. On such basis, we analyze parameter corruptions and propose the multi-step adversarial corruption algorithm. To enhance neural networks, we propose the adversarial parameter defense algorithm that minimizes the average risk of multiple adversarial parameter corruptions. Experimental results show that the proposed algorithm can improve both the parameter robustness and accuracy of neural networks.
The properties of nuclei in the ``island of inversion (IOI) around Z=10 and N=20 are the focus of current nuclear physics research. Recent studies showed that $^{28}$F has a negative-parity ground state (g.s.) and thus lies within the southern shore
of the IOI, and $^{29}$F presents a halo structure in its g.s., but it is unclear which effects, such as deformation, shell evolution due to tensor forces, or couplings to the continuum, lead to this situation. We investigate the role of quadrupole deformation and continuum effects on the single-particle (s.p.) structure of $^{28,29,31}$F from a relativistic mean-field (RMF) approach, and show how both phenomena can lead to a negative-parity g.s. in $^{28}$F and halo structures in $^{29,31}$F. We solve the Dirac equation in the complex-momentum (Berggren) representation for a potential with quadrupole deformation at the first order obtained from RMF calculations using the NL3 interaction, and calculate the continuum level densities using the Greens function method. We extract s.p. energies and widths from the continuum level densities to construct Nilsson diagrams, and analyse the evolution of both the widths and occupation probabilities of relevant Nilsson orbitals in $^{28}$F and find that some amount of prolate deformation must be present. In addition, we calculate the density distributions for bound Nilsson orbitals near the Fermi surface in $^{29,31}$F and reveal that for a quadrupole deformation $0.3 leq beta_2 leq 0.45$ (prolate), halo tails appear at large distances. We also demonstrate that while in the spherical case the $pf$ shells are already inverted and close to the neutron emission threshold, a small amount of quadrupole deformation can reduce the gap between $fp$ shells and increase the role of the continuum, ultimately leading to the negative parity in the g.s. of $^{28}$F and the halo structures in $^{29,31}$F.
We study the decay processes of $bar{B}^0 to J/psi bar{K}^{*0} K^0$ and $bar{B}^0 to J/psi f_1(1285)$ to analyse the $f_1(1285)$ resonance. By the calculation within chiral unitary approach where $f_1(1285)$ resonance is dynamically generated from th
e $K^*bar{K}-c.c.$ interaction, we find that the $bar{K}^{*0} K^0$ invariant mass distribution has a clear broad peak. Such broad peak has been understood as the signal of the $f_1(1285)$. Finally, we obtain a theoretical result $R_t=Gamma_{bar{B}^0 to J/psi bar{K}^{*0} K^0}/Gamma_{bar{B}^0 to J/psi f_1(1285)}$ which is expected to be compared with the experimental data.
Recent studies on computer vision mainly focus on natural images that express real-world scenes. They achieve outstanding performance on diverse tasks such as visual question answering. Diagram is a special form of visual expression that frequently a
ppears in the education field and is of great significance for learners to understand multimodal knowledge. Current research on diagrams preliminarily focuses on natural disciplines such as Biology and Geography, whose expressions are still similar to natural images. Another type of diagrams such as from Computer Science is composed of graphics containing complex topologies and relations, and research on this type of diagrams is still blank. The main challenges of graphic diagrams understanding are the rarity of data and the confusion of semantics, which are mainly reflected in the diversity of expressions. In this paper, we construct a novel dataset of graphic diagrams named Computer Science Diagrams (CSDia). It contains more than 1,200 diagrams and exhaustive annotations of objects and relations. Considering the visual noises caused by the various expressions in diagrams, we introduce the topology of diagrams to parse topological structure. After that, we propose Diagram Parsing Net (DPN) to represent the diagram from three branches: topology, visual feature, and text, and apply the model to the diagram classification task to evaluate the ability of diagrams understanding. The results show the effectiveness of the proposed DPN on diagrams understanding.
Clustering is one of the fundamental problems in unsupervised learning. Recent deep learning based methods focus on learning clustering oriented representations. Among those methods, Variational Deep Embedding achieves great success in various cluste
ring tasks by specifying a Gaussian Mixture prior to the latent space. However, VaDE suffers from two problems: 1) it is fragile to the input noise; 2) it ignores the locality information between the neighboring data points. In this paper, we propose a joint learning framework that improves VaDE with a robust embedding discriminator and a local structure constraint, which are both helpful to improve the robustness of our model. Experiment results on various vision and textual datasets demonstrate that our method outperforms the state-of-the-art baseline models in all metrics. Further detailed analysis shows that our proposed model is very robust to the adversarial inputs, which is a desirable property for practical applications.
Many historical people are captured only in old, faded, black and white photos, that have been distorted by the limitations of early cameras and the passage of time. This paper simulates traveling back in time with a modern camera to rephotograph fam
ous subjects. Unlike conventional image restoration filters which apply independent operations like denoising, colorization, and superresolution, we leverage the StyleGAN2 framework to project old photos into the space of modern high-resolution photos, achieving all of these effects in a unified framework. A unique challenge with this approach is capturing the identity and pose of the photos subject and not the many artifacts in low-quality antique photos. Our comparisons to current state-of-the-art restoration filters show significant improvements and compelling results for a variety of important historical people.
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. Unlike th
e ad-hoc priors in classical reconstruction, we use a learning-based prior, i.e., a convolutional neural network trained for single-image depth estimation. At test time, we fine-tune this network to satisfy the geometric constraints of a particular input video, while retaining its ability to synthesize plausible depth details in parts of the video that are less constrained. We show through quantitative validation that our method achieves higher accuracy and a higher degree of geometric consistency than previous monocular reconstruction methods. Visually, our results appear more stable. Our algorithm is able to handle challenging hand-held captured input videos with a moderate degree of dynamic motion. The improved quality of the reconstruction enables several applications, such as scene reconstruction and advanced video-based visual effects.
In this paper, we investigate the inclusive diffractive hadroproduction for $rm eta_{c}$ and $rm eta_{b}$ at the LHC energies. Based on the NRQCD factorization formalism and the resolved-Pomeron model for the quarkonium production mechanism, we estim
ate the rapidity, momentum fraction loss dependence of the cross section. We give prediction ratios for single and central diffractive processes with respect to non diffractive process. These inclusive processes are sensitive to gluon content of Pomeron for small-$x$ and Reggeon for large-$x$, useful to study small and large-$x$ physics and good to test different mechanism for $rm eta_{c}$ and $rm eta_{b}$ production at the LHC. They also serve as the background to related exclusive processes thus should be predicted. Our results demonstrate that the Reggeon contribution of diffractive processes can be sizable, even sometimes dominant over Pomeron, and that its study can be useful to better constrain the Reggeon parton content. The experimental study of Reggeon can be carried out in certain kinematic windows.
This paper introduces the largest and most diverse collection of rectified stereo image pairs to the research community, KeystoneDepth, consisting of tens of thousands of stereographs of historical people, events, objects, and scenes between 1860 and
1963. Leveraging the Keystone-Mast raw scans from the California Museum of Photography, we apply multiple processing steps to produce clean stereo image pairs, complete with calibration data, rectification transforms, and depthmaps. A second contribution is a novel approach for view synthesis that runs at real-time rates on a mobile device, simulating the experience of looking through an open window into these historical scenes. We produce results for thousands of antique stereographs, capturing many important historical moments.
This work discovers the equivalence relation between quadrilateral meshes and meromorphic quartic. Each quad-mesh induces a conformal structure of the surface, and a meromorphic differential, where the configuration of singular vertices correspond to
the configurations the poles and zeros (divisor) of the meroromorphic differential. Due to Riemann surface theory, the configuration of singularities of a quad-mesh satisfies the Abel-Jacobi condition. Inversely, if a satisfies the Abel-Jacobi condition, then there exists a meromorphic quartic differential whose equals to the given one. Furthermore, if the meromorphic quadric differential is with finite, then it also induces a a quad-mesh, the poles and zeros of the meromorphic differential to the singular vertices of the quad-mesh. Besides the theoretic proofs, the computational algorithm for verification of Abel-Jacobi condition is explained in details. Furthermore, constructive algorithm of meromorphic quartic differential on zero surfaces is proposed, which is based on the global algebraic representation of meromorphic. Our experimental results demonstrate the efficiency and efficacy of the algorithm. This opens up a direction for quad-mesh generation using algebraic geometric approach.
