We present a fast and accurate analytical method for fluorescence lifetime imaging microscopy (FLIM) using the extreme learning machine (ELM). We used extensive metrics to evaluate ELM and existing algorithms. First, we compared these algorithms using synthetic datasets. Results indicate that ELM can obtain higher fidelity, even in low-photon conditions. Afterwards, we used ELM to retrieve lifetime components from human prostate cancer cells loaded with gold nanosensors, showing that ELM also outperforms the iterative fitting and non-fitting algorithms. By comparing ELM with a computational efficient neural network, ELM achieves comparable accuracy with less training and inference time. As there is no back-propagation process for ELM during the training phase, the training speed is much higher than existing neural network approaches. The proposed strategy is promising for edge computing with online training.
Autonomous exploration is one of the important parts to achieve the autonomous operation of Unmanned Aerial Vehicles (UAVs). To improve the efficiency of the exploration process, a fast and autonomous exploration planner (FAEP) is proposed in this paper. We firstly design a novel frontiers exploration sequence generation method to obtain a more reasonable exploration path, which considers not only the flight-level but frontier-level factors into TSP. According to the exploration sequence and the distribution of frontiers, a two-stage heading planning strategy is proposed to cover more frontiers by heading change during an exploration journey. To improve the stability of path searching, a guided kinodynamic path searching based on a guiding path is devised. In addition, a dynamic start point selection method for replanning is also adopted to increase the fluency of flight. We present sufficient benchmark and real-world experiments. Experimental results show the superiority of the proposed exploration planner compared with typical and state-of-the-art methods.
Alleviating the delayed feedback problem is of crucial importance for the conversion rate(CVR) prediction in online advertising. Previous delayed feedback modeling methods using an observation window to balance the trade-off between waiting for accurate labels and consuming fresh feedback. Moreover, to estimate CVR upon the freshly observed but biased distribution with fake negatives, the importance sampling is widely used to reduce the distribution bias. While effective, we argue that previous approaches falsely treat fake negative samples as real negative during the importance weighting and have not fully utilized the observed positive samples, leading to suboptimal performance. In this work, we propose a new method, DElayed Feedback modeling with UnbiaSed Estimation, (DEFUSE), which aim to respectively correct the importance weights of the immediate positive, the fake negative, the real negative, and the delay positive samples at finer granularity. Specifically, we propose a two-step optimization approach that first infers the probability of fake negatives among observed negatives before applying importance sampling. To fully exploit the ground-truth immediate positives from the observed distribution, we further develop a bi-distribution modeling framework to jointly model the unbiased immediate positives and the biased delay conversions. Experimental results on both public and our industrial datasets validate the superiority of DEFUSE. Codes are available at https://github.com/ychen216/DEFUSE.git.
Graph Structure Learning (GSL) recently has attracted considerable attentions in its capacity of optimizing graph structure as well as learning suitable parameters of Graph Neural Networks (GNNs) simultaneously. Current GSL methods mainly learn an optimal graph structure (final view) from single or multiple information sources (basic views), however the theoretical guidance on what is the optimal graph structure is still unexplored. In essence, an optimal graph structure should only contain the information about tasks while compress redundant noise as much as possible, which is defined as "minimal sufficient structure", so as to maintain the accurancy and robustness. How to obtain such structure in a principled way? In this paper, we theoretically prove that if we optimize basic views and final view based on mutual information, and keep their performance on labels simultaneously, the final view will be a minimal sufficient structure. With this guidance, we propose a Compact GSL architecture by MI compression, named CoGSL. Specifically, two basic views are extracted from original graph as two inputs of the model, which are refinedly reestimated by a view estimator. Then, we propose an adaptive technique to fuse estimated views into the final view. Furthermore, we maintain the performance of estimated views and the final view and reduce the mutual information of every two views. To comprehensively evaluate the performance of CoGSL, we conduct extensive experiments on several datasets under clean and attacked conditions, which demonstrate the effectiveness and robustness of CoGSL.
Unlike other metaheuristics, differential Evolution (DE) employs a crossover operation filtering variables to be mutated, which contributes to its successful applications in a variety of complicated optimization problems. However, the underlying working principles of the crossover operation is not yet fully understood. In this paper, we try to reveal the influence of the binomial crossover by performing a theoretical comparison between the $(1+1)EA$ and its variants, the $(1+1)EA_{C}$ and the $(1+1)EA_{CM}$. Generally, the introduction of the binomial crossover contributes to the enhancement of the exploration ability as well as degradation of the exploitation ability, and under some conditions, leads to the dominance of the transition matrix for binary optimization problems. As a result, both the $(1+1)EA_{C}$ and the $(1+1)EA_{CM}$ outperform the $(1+1)EA$ on the unimodal OneMax problem, but do not always dominate it on the Deceptive problem. Finally, we perform exploration analysis by investigating probabilities to transfer from non-optimal statuses to the optimal status of the Deceptive problem, inspired by which adaptive strategies are proposed to improve the ability of global exploration. It suggests that incorporation of the binomial crossover could be a feasible strategy to improve the performances of randomized search heuristics.
Contrastive Learning (CL) is one of the most popular self-supervised learning frameworks for graph representation learning, which trains a Graph Neural Network (GNN) by discriminating positive and negative node pairs. However, there are two challenges for CL on graphs. On the one hand, traditional CL methods will unavoidably introduce semantic errors since they will treat some semantically similar nodes as negative pairs. On the other hand, most of the existing CL methods ignore the multiplexity nature of the real-world graphs, where nodes are connected by various relations and each relation represents a view of the graph. To address these challenges, we propose a novel Graph Multi-View Prototypical (Graph-MVP) framework to extract node embeddings on multiplex graphs. Firstly, we introduce a Graph Prototypical Contrastive Learning (Graph-PCL) framework to capture both node-level and semantic-level information for each view of multiplex graphs. Graph-PCL captures the node-level information by a simple yet effective data transformation technique. It captures the semantic-level information by an Expectation-Maximization (EM) algorithm, which alternatively performs clustering over node embeddings and parameter updating for GNN. Next, we introduce Graph-MVP based on Graph-PCL to jointly model different views of the multiplex graphs. Our key insight behind Graph-MVP is that different view-specific embeddings of the same node should have similar underlying semantic, based on which we propose two versions of Graph-MVP: Graph-MVP_hard and Graph-MVP_soft to align embeddings across views. Finally, we evaluate the proposed Graph-PCL and Graph-MVP on a variety of real-world datasets and downstream tasks. The experimental results demonstrate the effectiveness of the proposed Graph-PCL and Graph-MVP frameworks.
A photonic approach for radio-frequency (RF) self-interference cancellation (SIC) incorporated in an in-band full-duplex radio-over-fiber system is proposed. A dual-polarization binary phase-shift keying modulator is used for dual-polarization multiplexing at the central office (CO). A local oscillator signal and an intermediate-frequency signal carrying the downlink data are single-sideband modulated on the two polarization directions of the modulator, respectively. The optical signal is then transmitted to the remote unit, where the optical signals in the two polarization directions are split into two parts. One part is detected to generate the up-converted downlink RF signal, and the other part is re-modulated by the uplink RF signal and the self-interference, which is then transmitted back to the CO for the signal down-conversion and SIC via the optical domain signal adjustment and balanced detection. The functions of SIC, frequency up-conversion, down-conversion, and fiber transmission with dispersion immunity are all incorporated in the system. An experiment is performed. Cancellation depths of more than 39 dB for the single-tone signal and more than 20 dB for the 20-MBaud 16 quadrature amplitude modulation signal are achieved in the back-to-back case. The performance of the system does not have a significant decline when a section of 4.1-km optical fiber is incorporated.
Autonomous parking technology is a key concept within autonomous driving research. This paper will propose an imaginative autonomous parking algorithm to solve issues concerned with parking. The proposed algorithm consists of three parts: an imaginative model for anticipating results before parking, an improved rapid-exploring random tree (RRT) for planning a feasible trajectory from a given start point to a parking lot, and a path smoothing module for optimizing the efficiency of parking tasks. Our algorithm is based on a real kinematic vehicle model; which makes it more suitable for algorithm application on real autonomous cars. Furthermore, due to the introduction of the imagination mechanism, the processing speed of our algorithm is ten times faster than that of traditional methods, permitting the realization of real-time planning simultaneously. In order to evaluate the algorithm's effectiveness, we have compared our algorithm with traditional RRT, within three different parking scenarios. Ultimately, results show that our algorithm is more stable than traditional RRT and performs better in terms of efficiency and quality.
Based on the framework of the quantum-inspired evolutionary algorithm, a cuckoo quantum evolutionary algorithm (CQEA) is proposed for solving the graph coloring problem (GCP). To reduce iterations for the search of the chromatic number, the initial quantum population is generated by random initialization assisted by inheritance. Moreover, improvement of global exploration is achieved by incorporating the cuckoo search strategy, and a local search operation, as well as a perturbance strategy, is developed to enhance its performance on GCPs. Numerical results demonstrate that CQEA operates with strong exploration and exploitation abilities, and is competitive to the compared state-of-the-art heuristic algorithms.
This report describes Megvii-3D team's approach towards CVPR 2021 Image Matching Workshop.