Traditional fine-grained image classification generally requires abundant labeled samples to deal with the low inter-class variance but high intra-class variance problem. However, in many scenarios we may have limited samples for some novel sub-categ
ories, leading to the fine-grained few shot learning (FG-FSL) setting. To address this challenging task, we propose a novel method named foreground object transformation (FOT), which is composed of a foreground object extractor and a posture transformation generator. The former aims to remove image background, which tends to increase the difficulty of fine-grained image classification as it amplifies the intra-class variance while reduces inter-class variance. The latter transforms the posture of the foreground object to generate additional samples for the novel sub-category. As a data augmentation method, FOT can be conveniently applied to any existing few shot learning algorithm and greatly improve its performance on FG-FSL tasks. In particular, in combination with FOT, simple fine-tuning baseline methods can be competitive with the state-of-the-art methods both in inductive setting and transductive setting. Moreover, FOT can further boost the performances of latest excellent methods and bring them up to the new state-of-the-art. In addition, we also show the effectiveness of FOT on general FSL tasks.
The realization of spin-orbit coupling (SOC) in ultracold atoms has triggered an intensive exploring of topological superfluids in the degenerate Fermi gases based on mean-field theory, which has not yet been reported in experiments. Here, we demonst
rate the topological phase transitions in the system via the numerically exact quantum Monte Carlo method. Without prior assumptions, our unbiased real-space calculation shows that spin-orbit coupling can stabilize an unconventional pairing in the weak SOC regime, in which the Fulde-Ferrell-Larkin-Ovchinnikov pairing coexists with the Bardeen-Cooper-Schrieffer pairing. Furthermore, we use the jumps in the spin polarization at the time-reversal invariant momenta to qualify the topological phase transition, where we find the critical exponent deviated from the mean-field theory. Our results pave the way for the searching of unconventional pairing and topological superfluids with degenerate Fermi gases.
Mitotic count is the most important morphological feature of breast cancer grading. Many deep learning-based methods have been proposed but suffer from domain shift. In this work, we construct a Fourier-based segmentation model for mitosis detection
to address the problem. Swapping the low-frequency spectrum of source and target images is shown effective to alleviate the discrepancy between different scanners. Our Fourier-based segmentation method can achieve F1 with 0.7456 on the preliminary test set.
We put forth, theoretically and experimentally, the possibility of drastically cooling down (purifying) thermal ensembles (baths) of solid-state spins via a sequence of projective measurements of a probe spin that couples to the bath in an arbitrary
fashion. If the measurement intervals are chosen to correspond to the anti-Zeno regime of the probe-bath exchange, then a short sequence of measurements with selected outcomes is found to have an appreciable success probability. Such a sequence is shown to condition the bath evolution so that it can dramatically enhance the bath-state purity and yield a low-entropy steady state of the bath. This purified bath state persists after the measurements and can be chosen, on-demand, to allow for Zeno- or anti-Zeno- like evolution of quantum systems coupled to the purified bath. The experimental setup for observing these effects consists of a Nitrogen Vacancy (NV) center in diamond at low temperature that acts as a probe of the surrounding nuclear spin bath. The NV single-shot measurements are induced by optical fields at microsecond intervals.
The Nielsen-Ninomiya Theorem has set up a ground rule for the minimal number of the topological points in a Brillouin zone. Notably, in the 2D Brillouin zone, chiral symmetry and space-time inversion symmetry can properly define topological invariant
s as charges characterizing the stability of the nodal points so that the non-zero charges protect these points. Due to the charge neutralization, the Nielsen-Ninomiya Theorem requires at least two stable topological points in the entire Brillouin zone. However, additional crystalline symmetries might duplicate the points. In this regard, for the wallpaper groups with crystalline symmetries, the minimal number of the nodal points in the Brillouin zone might be more than two. In this work, we determine the minimal numbers of the nodal points for the wallpaper groups in chiral-symmetric and space-time-inversion-symmetric systems separately and provide examples for new topological materials, such as topological nodal time-reversal-symmetric superconductors and Dirac semimetals. This generalized Nielsen-Ninomiya Theorem serves as a guide to search for 2D topological nodal materials. Furthermore, we show the Nielsen-Ninomiya Theorem can be extended to 2D non-Hermitian systems hosting topologically protected exceptional points and Fermi points for the 17 wallpaper groups.
The topological nodal-line semimetals (NLSMs) possess a loop of Dirac nodes in the k space with linear dispersion, different from the point nodes in Dirac/Weyl semimetals. While the quantum transport associated with the topologically nontrivial Dirac
fermions has been investigated extensively, features uniquely associated with the extended nodal lines remain to be demonstrated. Here, we investigate the quantum oscillations (QOs) in the nodal-line semimetal ZrSiS, with the electron transport along the c axis, and magnetic field rotating in the ab plane. The extremal orbits identified through the field orientation dependence of the QOs interlock with the nodal line, leading to a nonzero Berry phase. Most importantly, the Berry phase shows a significant dependence on the magnetic field orientation, which we argue to be due to the finite spin-orbit coupling gap. Our results demonstrate the importance of the spin-orbit coupling and the nodal-line dispersion in understanding the quantum transport of NLSMs.
The 2D heatmap representation has dominated human pose estimation for years due to its high performance. However, heatmap-based approaches have some drawbacks: 1) The performance drops dramatically in the low-resolution images, which are frequently e
ncountered in real-world scenarios. 2) To improve the localization precision, multiple upsample layers may be needed to recover the feature map resolution from low to high, which are computationally expensive. 3) Extra coordinate refinement is usually necessary to reduce the quantization error of downscaled heatmaps. To address these issues, we propose a textbf{Sim}ple yet promising textbf{D}isentangled textbf{R}epresentation for keypoint coordinate (emph{SimDR}), reformulating human keypoint localization as a task of classification. In detail, we propose to disentangle the representation of horizontal and vertical coordinates for keypoint location, leading to a more efficient scheme without extra upsampling and refinement. Comprehensive experiments conducted over COCO dataset show that the proposed emph{heatmap-free} methods outperform emph{heatmap-based} counterparts in all tested input resolutions, especially in lower resolutions by a large margin. Code will be made publicly available at url{https://github.com/leeyegy/SimDR}.
As a critical component for online advertising and marking, click-through rate (CTR) prediction has draw lots of attentions from both industry and academia field. Recently, the deep learning has become the mainstream methodological choice for CTR. De
spite of sustainable efforts have been made, existing approaches still pose several challenges. On the one hand, high-order interaction between the features is under-explored. On the other hand, high-order interactions may neglect the semantic information from the low-order fields. In this paper, we proposed a novel prediction method, named FINT, that employs the Field-aware INTeraction layer which captures high-order feature interactions while retaining the low-order field information. To empirically investigate the effectiveness and robustness of the FINT, we perform extensive experiments on the three realistic databases: KDD2012, Criteo and Avazu. The obtained results demonstrate that the FINT can significantly improve the performance compared to the existing methods, without increasing the amount of computation required. Moreover, the proposed method brought about 2.72% increase to the advertising revenue of a big online video app through A/B testing. To better promote the research in CTR field, we released our code as well as reference implementation at: https://github.com/zhishan01/FINT.
We report the results of a multi-year spectroscopic and photometric monitoring campaign of two luminous quasars, PG~0923+201 and PG~1001+291, both located at the high-luminosity end of the broad-line region (BLR) size-luminosity relation with optical
luminosities above $10^{45}~{rm erg~s^{-1}}$. PG~0923+201 is for the first time monitored, and PG~1001+291 was previously monitored but our campaign has a much longer temporal baseline. We detect time lags of variations of the broad H$beta$, H$gamma$, Fe {sc ii} lines with respect to those of the 5100~{AA} continuum. The velocity-resolved delay map of H$beta$ in PG~0923+201 indicates a complicated structure with a mix of Keplerian disk-like motion and outflow, and the map of H$beta$ in PG~1001+291 shows a signature of Keplerian disk-like motion. Assuming a virial factor of $f_{rm BLR}=1$ and FWHM line widths, we measure the black hole mass to be $118_{-16}^{+11}times 10^7 M_{odot}$ for PG~0923+201 and $3.33_{-0.54}^{+0.62}times 10^7 M_{odot}$ for PG~1001+291. Their respective accretion rates are estimated to be $0.21_{-0.07}^{+0.06} times L_{rm Edd},c^{-2}$ and $679_{-227}^{+259}times L_{rm Edd},c^{-2}$, indicating that PG~0923+201 is a sub-Eddington accretor and PG~1001+291 is a super-Eddington accretor. While the H$beta$ time lag of PG~0923+201 agrees with the size-luminosity relation, the time lag of PG~1001+291 shows a significant deviation, confirming that in high-luminosity AGN the BLR size depends on both luminosity and Eddington ratio. Black hole mass estimates from single AGN spectra will be over-estimated at high luminosities and redshifts if this effect is not taken into account.
Skin effect, experimentally discovered in one dimension, describes the physical phenomenon that on an open chain, an extensive number of eigenstates of a non-Hermitian hamiltonian are localized at the end(s) of the chain. Here in two and higher dimen
sions, we establish a theorem that the skin effect exists, if and only if periodic-boundary spectrum of the hamiltonian covers a finite area on the complex plane. This theorem establishes the universality of the effect, because the above condition is satisfied in almost every generic non-Hermitian hamiltonian, and, unlike in one dimension, is compatible with all spatial symmetries. We propose two new types of skin effect in two and higher dimensions: the corner-skin effect where all eigenstates are localized at one corner of the system, and the geometry-dependent-skin effect where skin modes disappear for systems of a particular shape, but appear on generic polygons. An immediate corollary of our theorem is that any non-Hermitian system having exceptional points (lines) in two (three) dimensions exhibits skin effect, making this phenomenon accessible to experiments in photonic crystals, Weyl semimetals, and Kondo insulators.
