arXiv subjects

Bo Liu

Publications and source records attributed to Bo Liu.

At least 505 records · Page 28Linked to original sources

arXiv2021

OOWL500: Overcoming Dataset Collection Bias in the Wild

The hypothesis that image datasets gathered online "in the wild" can produce biased object recognizers, e.g. preferring professional photography or certain viewing angles, is studied. A new "in the lab" data collection infrastructure is proposed consisting of a drone which captures images as it circles around objects. Crucially, the control provided by this setup and the natural camera shake inherent to flight mitigate many biases. It's inexpensive and easily replicable nature may also potentially lead to a scalable data collection effort by the vision community. The procedure's usefulness is demonstrated by creating a dataset of Objects Obtained With fLight (OOWL). Denoted as OOWL500, it contains 120,000 images of 500 objects and is the largest "in the lab" image dataset available when both number of classes and objects per class are considered. Furthermore, it has enabled several of new insights on object recognition. First, a novel adversarial attack strategy is proposed, where image perturbations are defined in terms of semantic properties such as camera shake and pose. Indeed, experiments have shown that ImageNet has considerable amounts of pose and professional photography bias. Second, it is used to show that the augmentation of in the wild datasets, such as ImageNet, with in the lab data, such as OOWL500, can significantly decrease these biases, leading to object recognizers of improved generalization. Third, the dataset is used to study questions on "best procedures" for dataset collection. It is revealed that data augmentation with synthetic images does not suffice to eliminate in the wild datasets biases, and that camera shake and pose diversity play a more important role in object recognition robustness than previously thought.

cs.CV↗

arXiv2021

APPLI: Adaptive Planner Parameter Learning From Interventions

While classical autonomous navigation systems can typically move robots from one point to another safely and in a collision-free manner, these systems may fail or produce suboptimal behavior in certain scenarios. The current practice in such scenarios is to manually re-tune the system's parameters, e.g. max speed, sampling rate, inflation radius, to optimize performance. This practice requires expert knowledge and may jeopardize performance in the originally good scenarios. Meanwhile, it is relatively easy for a human to identify those failure or suboptimal cases and provide a teleoperated intervention to correct the failure or suboptimal behavior. In this work, we seek to learn from those human interventions to improve navigation performance. In particular, we propose Adaptive Planner Parameter Learning from Interventions (APPLI), in which multiple sets of navigation parameters are learned during training and applied based on a confidence measure to the underlying navigation system during deployment. In our physical experiments, the robot achieves better performance compared to the planner with static default parameters, and even dynamic parameters learned from a full human demonstration. We also show APPLI's generalizability in another unseen physical test course, and a suite of 300 simulated navigation environments.

cs.RO↗

arXiv2021

Airborne Quantum Key Distribution with Boundary Layer Effects

Airborne quantum key distribution (QKD) is now becoming a flexible bond between terrestrial fiber and satellite, which is an efficient solution to establish a mobile, on-demand, and real-time coverage quantum network. Furthermore, When the aircraft is flying at a high speed, usually larger than 0.3 Ma, the produced boundary layer will impair the performance of aircraft-based QKD. The boundary layer would introduce random wavefront aberration, jitter and extra intensity attenuation to the transmitted photons. However, previous airborne QKD implementations only considered the influences from atmospheric turbulence and molecular scattering, but ignored the boundary layer effects. In this article, we propose a detailed performance evaluation scheme of airborne QKD with boundary layer effects and estimate the overall photon transmission efficiency, quantum bit error rate and final secure key rate. Through simulations and modeling, in our proposed airborne QKD scenario, the boundary layer would introduce 3.5dB loss to the transmitted photons and decrease 70.7% of the secure key rate, which shows that the aero-optical effects caused by the boundary layer can not be ignored. With tolerated quantum bit error rate set to 10%, the suggested quantum communication azimuth angle between the aircraft and the ground station is within 60 degrees. Moreover, the optimal beacon laser module and adaptive optics module are suggested to be employed to improve the performance of airborne QKD system. Our detailed airborne QKD evaluation study can be performed to the future airborne quantum communication designs.

quant-ph↗

arXiv2021

TDM: Trustworthy Decision-Making via Interpretability Enhancement

Human-robot interactive decision-making is increasingly becoming ubiquitous, and trust is an influential factor in determining the reliance on autonomy. However, it is not reasonable to trust systems that are beyond our comprehension, and typical machine learning and data-driven decision-making are black-box paradigms that impede interpretability. Therefore, it is critical to establish computational trustworthy decision-making mechanisms enhanced by interpretability-aware strategies. To this end, we propose a Trustworthy Decision-Making (TDM) framework, which integrates symbolic planning into sequential decision-making. The framework learns interpretable subtasks that result in a complex, higher-level composite task that can be formally evaluated using the proposed trust metric. TDM enables the subtask-level interpretability by design and converges to an optimal symbolic plan from the learned subtasks. Moreover, a TDM-based algorithm is introduced to demonstrate the unification of symbolic planning with other sequential-decision making algorithms, reaping the benefits of both. Experimental results validate the effectiveness of trust-score-based planning while improving the interpretability of subtasks.

cs.LG↗

arXiv2021

Enantio-specific state transfer for symmetric-top chiral molecules

We study the enantio-specific state transfer in a four-level model for symmetric-top chiral molecules. Such a model is formed by coupling the electric-dipole transitions among four appropriate working states with three electromagnetic fields. It includes two cyclic three-level substructures, where the overall phases differ by $π$ with enantiomers and reflect the chirality dependence of the molecule. Based on this four-level model, two dynamic ways are proposed to achieve the approximately perfect enantio-specific state transfer for symmetric-top chiral molecules.

quant-ph↗

arXiv2021

Continuous-time Gaussian Process Trajectory Generation for Multi-robot Formation via Probabilistic Inference

In this paper, we extend a famous motion planning approach GPMP2 to multi-robot cases, yielding a novel centralized trajectory generation method for the multi-robot formation. A sparse Gaussian Process model is employed to represent the continuous-time trajectories of all robots as a limited number of states, which improves computational efficiency due to the sparsity. We add constraints to guarantee collision avoidance between individuals as well as formation maintenance, then all constraints and kinematics are formulated on a factor graph. By introducing a global planner, our proposed method can generate trajectories efficiently for a team of robots which have to get through a width-varying area by adaptive formation change. Finally, we provide the implementation of an incremental replanning algorithm to demonstrate the online operation potential of our proposed framework. The experiments in simulation and real world illustrate the feasibility, efficiency and scalability of our approach.

cs.RO↗

arXiv2021

Fedlearn-Algo: A flexible open-source privacy-preserving machine learning platform

In this paper, we present Fedlearn-Algo, an open-source privacy preserving machine learning platform. We use this platform to demonstrate our research and development results on privacy preserving machine learning algorithms. As the first batch of novel FL algorithm examples, we release vertical federated kernel binary classification model and vertical federated random forest model. They have been tested to be more efficient than existing vertical federated learning models in our practice. Besides the novel FL algorithm examples, we also release a machine communication module. The uniform data transfer interface supports transferring widely used data formats between machines. We will maintain this platform by adding more functional modules and algorithm examples. The code is available at https://github.com/fedlearnAI/fedlearn-algo.

cs.LG↗

arXiv2021

First observation of laser-beam interaction in a dipole magnet

As a new-generation light source, free-electron lasers (FELs) provide high-brightness X-ray pulses at the angstrom-femtosecond space and time scales. The fundamental physics behind the FEL is the interaction between an electromagnetic wave and a relativistic electron beam in an undulator, which consists of hundreds or thousands of dipole magnets with an alternating magnetic field. Here, we report the first observation of the laser-beam interaction in a pure dipole magnet, in which the electron beam energy modulation with 40-keV amplitude and 266-nm period is measured. We demonstrate that such an energy modulation can be used to launch a seeded FEL, that is, lasing at the sixth harmonic of the seed laser in a high-gain harmonic generation scheme. The results reveal the most basic process of the FEL lasing and open up a new direction for the study and exploitation of laser-beam interactions.

physics.acc-ph↗

arXiv2021

A model for optimizing quantum key distribution with continuous-wave pumped entangled-photon sources

Quantum Key Distribution (QKD) allows unconditionally secure communication based on the laws of quantum mechanics rather then assumptions about computational hardness. Optimizing the operation parameters of a given QKD implementation is indispensable in order to achieve high secure key rates. So far, there exists no model that accurately describes entanglement-based QKD with continuous-wave pump lasers. For the first time, we analyze the underlying mechanisms for QKD with temporally uniform pair-creation probabilities and develop a simple but accurate model to calculate optimal trade-offs for maximal secure key rates. In particular, we find an optimization strategy of the source brightness for given losses and detection-time resolution. All experimental parameters utilized by the model can be inferred directly in standard QKD implementations, and no additional assessment of device performance is required. Comparison with experimental data shows the validity of our model. Our results yield a tool to determine optimal operation parameters for already existing QKD systems, to plan a full QKD implementation from scratch, and to determine fundamental key rate and distance limits of given connections.

quant-ph↗

arXiv2021

The performance of IHEP-NDL LGAD sensors after neutron irradiation

The performances of Low Gain Avalanche diode (LGAD) sensors from a neutron irradiation campaign with fluences of 0.8 x 10^15, 15 x 10^15 and 2.5 x 10^15 neq/cm2 are reported in this article. These LGAD sensors are developed by the Institute of High Energy Physics, Chinese Academy of Sciences and the Novel Device Laboratory for the High Granularity Timing Detector of the High Luminosity Large Hadron Collider. The timing resolution and collected charge of the LGAD sensors were measured with electrons from a beta source. After irradiation with a fluence of 2.5 x 10^15 neq/cm2, the collected charge decreases from 40 fC to 7 fC, the signal-to-noise ratio deteriorates from 48 to 12, and the timing resolution increases from 29 ps to 39 ps.

physics.ins-det↗

arXiv2021

Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation

Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis. In this paper, we aim to provide an insight into spatial manipulation modules. Firstly, we find that the smaller the rotational degree of freedom (RDF) of objects is, the more easily these objects are handled by these DNNs. Then, we investigate the effect of the popular T-Net module and find that it could not reduce the RDF of objects. Motivated by the above two issues, we propose a rotation transformation network for point cloud analysis, called RTN, which could reduce the RDF of input 3D objects to 0. The RTN could be seamlessly inserted into many existing DNNs for point cloud analysis. Extensive experimental results on 3D point cloud classification and segmentation tasks demonstrate that the proposed RTN could improve the performances of several state-of-the-art methods significantly.

cs.CV↗

arXiv2021

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures. Our method works in a steepest descent fashion, which iteratively finds the best network within a functional neighborhood of the original network that includes a diverse set of candidate network structures. By using Taylor approximation, the optimal network structure in the neighborhood can be found with a greedy selection procedure. We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures that avoid catastrophic forgetting in continual learning. Empirically, firefly descent achieves promising results on both neural architecture search and continual learning. In particular, on a challenging continual image classification task, it learns networks that are smaller in size but have higher average accuracy than those learned by the state-of-the-art methods.

cs.LG↗

arXiv2021

Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training

Out-of-scope intent detection is of practical importance in task-oriented dialogue systems. Since the distribution of outlier utterances is arbitrary and unknown in the training stage, existing methods commonly rely on strong assumptions on data distribution such as mixture of Gaussians to make inference, resulting in either complex multi-step training procedures or hand-crafted rules such as confidence threshold selection for outlier detection. In this paper, we propose a simple yet effective method to train an out-of-scope intent classifier in a fully end-to-end manner by simulating the test scenario in training, which requires no assumption on data distribution and no additional post-processing or threshold setting. Specifically, we construct a set of pseudo outliers in the training stage, by generating synthetic outliers using inliner features via self-supervision and sampling out-of-scope sentences from easily available open-domain datasets. The pseudo outliers are used to train a discriminative classifier that can be directly applied to and generalize well on the test task. We evaluate our method extensively on four benchmark dialogue datasets and observe significant improvements over state-of-the-art approaches. Our code has been released at https://github.com/liam0949/DCLOOS.

cs.CL↗

arXiv2021

Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images

Instance segmentation is of great importance for many biological applications, such as study of neural cell interactions, plant phenotyping, and quantitatively measuring how cells react to drug treatment. In this paper, we propose a novel box-based instance segmentation method. Box-based instance segmentation methods capture objects via bounding boxes and then perform individual segmentation within each bounding box region. However, existing methods can hardly differentiate the target from its neighboring objects within the same bounding box region due to their similar textures and low-contrast boundaries. To deal with this problem, in this paper, we propose an object-guided instance segmentation method. Our method first detects the center points of the objects, from which the bounding box parameters are then predicted. To perform segmentation, an object-guided coarse-to-fine segmentation branch is built along with the detection branch. The segmentation branch reuses the object features as guidance to separate target object from the neighboring ones within the same bounding box region. To further improve the segmentation quality, we design an auxiliary feature refinement module that densely samples and refines point-wise features in the boundary regions. Experimental results on three biological image datasets demonstrate the advantages of our method. The code will be available at https://github.com/yijingru/ObjGuided-Instance-Segmentation.

cs.CV↗

arXiv2021

Team Orienteering Coverage Planning with Uncertain Reward

Many municipalities and large organizations have fleets of vehicles that need to be coordinated for tasks such as garbage collection or infrastructure inspection. Motivated by this need, this paper focuses on the common subproblem in which a team of vehicles needs to plan coordinated routes to patrol an area over iterations while minimizing temporally and spatially dependent costs. In particular, at a specific location (e.g., a vertex on a graph), we assume the cost grows linearly in expectation with an unknown rate, and the cost is reset to zero whenever any vehicle visits the vertex (representing the robot servicing the vertex). We formulate this problem in graph terminology and call it Team Orienteering Coverage Planning with Uncertain Reward (TOCPUR). We propose to solve TOCPUR by simultaneously estimating the accumulated cost at every vertex on the graph and solving a novel variant of the Team Orienteering Problem (TOP) iteratively, which we call the Team Orienteering Coverage Problem (TOCP). We provide the first mixed integer programming formulation for the TOCP, as a significant adaptation of the original TOP. We introduce a new benchmark consisting of hundreds of randomly generated graphs for comparing different methods. We show the proposed solution outperforms both the exact TOP solution and a greedy algorithm. In addition, we provide a demo of our method on a team of three physical robots in a real-world environment.

cs.RO↗

arXiv2021

Equivariant eta forms and equivariant differential $K$-theory

In this paper, for a compact Lie group action,we prove the anomaly formula and the functoriality of the equivariant Bismut-Cheeger eta forms with perturbation operators when the equivariant family index vanishes. In order to prove them, we extend the Melrose-Piazza spectral section and its main properties to the equivariant case and introduce the equivariant version of the Dai-Zhang higher spectral flow for arbitrary dimensional fibers.Using these results, we construct a new analytic model of the equivariant differential K-theory for compact manifolds when the group action has finite stabilizers only,which modifies the Bunck-Schick model of the differential K-theory. This model could also be regarded as an analytic model of the differential K-theory for compact orbifolds. Especially, we answer a question proposed by Bunke and Schick about the well-definedness of the push-forward map.

math.DG↗

arXiv2021

Sparse Pose Trajectory Completion

We propose a method to learn, even using a dataset where objects appear only in sparsely sampled views (e.g. Pix3D), the ability to synthesize a pose trajectory for an arbitrary reference image. This is achieved with a cross-modal pose trajectory transfer mechanism. First, a domain transfer function is trained to predict, from an RGB image of the object, its 2D depth map. Then, a set of image views is generated by learning to simulate object rotation in the depth space. Finally, the generated poses are mapped from this latent space into a set of corresponding RGB images using a learned identity preserving transform. This results in a dense pose trajectory of the object in image space. For each object type (e.g., a specific Ikea chair model), a 3D CAD model is used to render a full pose trajectory of 2D depth maps. In the absence of dense pose sampling in image space, these latent space trajectories provide cross-modal guidance for learning. The learned pose trajectories can be transferred to unseen examples, effectively synthesizing all object views in image space. Our method is evaluated on the Pix3D and ShapeNet datasets, in the setting of novel view synthesis under sparse pose supervision, demonstrating substantial improvements over recent art.

cs.CV↗

arXiv2021

Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition

The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered. While training with class-balanced sampling has been shown effective for this problem, it is known to over-fit to few-shot classes. It is hypothesized that this is due to the repeated sampling of examples and can be addressed by feature space augmentation. A new feature augmentation strategy, EMANATE, based on back-tracking of features across epochs during training, is proposed. It is shown that, unlike class-balanced sampling, this is an adversarial augmentation strategy. A new sampling procedure, Breadcrumb, is then introduced to implement adversarial class-balanced sampling without extra computation. Experiments on three popular long-tailed recognition datasets show that Breadcrumb training produces classifiers that outperform existing solutions to the problem.

cs.CV↗