arXiv subjects

Ling Cai

Publications and source records attributed to Ling Cai.

22 records · Page 2Linked to original sources

arXiv2019

Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs

Recently, several studies have explored methods for using KG embedding to answer logical queries. These approaches either treat embedding learning and query answering as two separated learning tasks, or fail to deal with the variability of contributions from different query paths. We proposed to leverage a graph attention mechanism to handle the unequal contribution of different query paths. However, commonly used graph attention assumes that the center node embedding is provided, which is unavailable in this task since the center node is to be predicted. To solve this problem we propose a multi-head attention-based end-to-end logical query answering model, called Contextual Graph Attention model(CGA), which uses an initial neighborhood aggregation layer to generate the center embedding, and the whole model is trained jointly on the original KG structure as well as the sampled query-answer pairs. We also introduce two new datasets, DB18 and WikiGeo19, which are rather large in size compared to the existing datasets and contain many more relation types, and use them to evaluate the performance of the proposed model. Our result shows that the proposed CGA with fewer learnable parameters consistently outperforms the baseline models on both datasets as well as Bio dataset.

cs.LG↗

arXiv2019

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask R-CNN, DetNet) to alleviate the problem arising from scale variation across object instances. Although these object detectors with feature pyramids achieve encouraging results, they have some limitations due to that they only simply construct the feature pyramid according to the inherent multi-scale, pyramidal architecture of the backbones which are actually designed for object classification task. Newly, in this work, we present a method called Multi-Level Feature Pyramid Network (MLFPN) to construct more effective feature pyramids for detecting objects of different scales. First, we fuse multi-level features (i.e. multiple layers) extracted by backbone as the base feature. Second, we feed the base feature into a block of alternating joint Thinned U-shape Modules and Feature Fusion Modules and exploit the decoder layers of each u-shape module as the features for detecting objects. Finally, we gather up the decoder layers with equivalent scales (sizes) to develop a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels. To evaluate the effectiveness of the proposed MLFPN, we design and train a powerful end-to-end one-stage object detector we call M2Det by integrating it into the architecture of SSD, which gets better detection performance than state-of-the-art one-stage detectors. Specifically, on MS-COCO benchmark, M2Det achieves AP of 41.0 at speed of 11.8 FPS with single-scale inference strategy and AP of 44.2 with multi-scale inference strategy, which is the new state-of-the-art results among one-stage detectors. The code will be made available on \url{https://github.com/qijiezhao/M2Det.

cs.CV↗

arXiv2018

CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving

The ability to detect small objects and the speed of the object detector are very important for the application of autonomous driving, and in this paper, we propose an effective yet efficient one-stage detector, which gained the second place in the Road Object Detection competition of CVPR2018 workshop - Workshop of Autonomous Driving(WAD). The proposed detector inherits the architecture of SSD and introduces a novel Comprehensive Feature Enhancement(CFE) module into it. Experimental results on this competition dataset as well as the MSCOCO dataset demonstrate that the proposed detector (named CFENet) performs much better than the original SSD and the state-of-the-art method RefineDet especially for small objects, while keeping high efficiency close to the original SSD. Specifically, the single scale version of the proposed detector can run at the speed of 21 fps, while the multi-scale version with larger input size achieves the mAP 29.69, ranking second on the leaderboard

cs.CV↗

arXiv2018

Piezoelectric Polar Nano Regions and Relaxation-Coupled Resonances in Relaxor Ferroelectrics

\indent It is a generally accepted fact that the unique dielectric properties of relaxor ferroelectrics are related to the formation of polar nanoregion (PNRs). Less well recognized is the corollary that, because they are polar and therefore lack inversion symmetry, PNRs are also piezoelectric at the nanoscale and can therefore behave as nanoresonators. Using the particular relaxor ferroelectric K$_{\tt1-x}$Li$_{\tt x}$TaO$_{\tt 3}$ (KLT), we show that, when electrically excited into oscillation, these piezoelectric nanoresonators can drive macroscopic electro-mechanical resonances. Unexpectedly however, pairs of coupled resonances are observed, with one of the two exhibiting a characteristic Fano-like lineshape. The complex resonance spectra can be described equally well by two alternative but complementary models both involving two resonances coupled through a relaxation: a purely classical one based on two coupled damped harmonic oscillators and a semi-classical based on two discrete excitations coupled to each other through a continuum. Together, they provide complementary perspectives on the underlying physics of the system. Both reproduce the rapid evolution of the resonance spectrum across three wide temperature ranges, including a phase transition range. In the high temperature range, the coupling between modes is due to the collective $π$ relaxation of the lithium ions within PNRs and in the phase transition range to "heterophase relaxation" of the surrounding lattice between its high temperature cubic and low temperature tetragonal phases. The coupling is suppressed in the intermediate range of the collective $π/2$ relaxation of the lithium ions. Incidentally, the measured dielectric spectra are shown to bear a surprising but justifiable resemblance to the optical spectra of certain atomic vapors that exhibit electromagnetically induced transparency.

cond-mat.mes-hall↗