arXiv subjects

Wentao Wang

Publications and source records attributed to Wentao Wang.

70 records · Page 4Linked to original sources

arXiv2022

Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization

Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection, especially for high-precision detection with high IoU (e.g. 0.75). Instead, we propose to model the rotated objects as Gaussian distributions. A direct advantage is that our new regression loss regarding the distance between two Gaussians e.g. Kullback-Leibler Divergence (KLD), can well align the actual detection performance metric, which is not well addressed in existing methods. Moreover, the two bottlenecks i.e. boundary discontinuity and square-like problem also disappear. We also propose an efficient Gaussian metric-based label assignment strategy to further boost the performance. Interestingly, by analyzing the BBox parameters' gradients under our Gaussian-based KLD loss, we show that these parameters are dynamically updated with interpretable physical meaning, which help explain the effectiveness of our approach, especially for high-precision detection. We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation, and experimental results on twelve public datasets (2-D/3-D, aerial/text/face images) with various base detectors show its superiority.

cs.CV↗

arXiv2022

Enhancing Adversarial Training with Feature Separability

Deep Neural Network (DNN) are vulnerable to adversarial attacks. As a countermeasure, adversarial training aims to achieve robustness based on the min-max optimization problem and it has shown to be one of the most effective defense strategies. However, in this work, we found that compared with natural training, adversarial training fails to learn better feature representations for either clean or adversarial samples, which can be one reason why adversarial training tends to have severe overfitting issues and less satisfied generalize performance. Specifically, we observe two major shortcomings of the features learned by existing adversarial training methods:(1) low intra-class feature similarity; and (2) conservative inter-classes feature variance. To overcome these shortcomings, we introduce a new concept of adversarial training graph (ATG) with which the proposed adversarial training with feature separability (ATFS) enables to coherently boost the intra-class feature similarity and increase inter-class feature variance. Through comprehensive experiments, we demonstrate that the proposed ATFS framework significantly improves both clean and robust performance.

cs.CV↗

arXiv2022

Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem. Specifically, the rotated bounding box is converted to a 2-D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance (GWD) which can be learned efficiently by gradient back-propagation. GWD can still be informative for learning even there is no overlapping between two rotating bounding boxes which is often the case for small object detection. Thanks to its three unique properties, GWD can also elegantly solve the boundary discontinuity and square-like problem regardless how the bounding box is defined. Experiments on five datasets using different detectors show the effectiveness of our approach. Codes are available at https://github.com/yangxue0827/RotationDetection and https://github.com/open-mmlab/mmrotate.

cs.CV↗

arXiv2022

Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence

Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-precision detection due to the limitation of current regression loss design, especially for objects with large aspect ratios. Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection. We show that one essential challenge is how to modulate the coupled parameters in the rotation regression loss, as such the estimated parameters can influence to each other during the dynamic joint optimization, in an adaptive and synergetic way. Specifically, we first convert the rotated bounding box into a 2-D Gaussian distribution, and then calculate the Kullback-Leibler Divergence (KLD) between the Gaussian distributions as the regression loss. By analyzing the gradient of each parameter, we show that KLD (and its derivatives) can dynamically adjust the parameter gradients according to the characteristics of the object. It will adjust the importance (gradient weight) of the angle parameter according to the aspect ratio. This mechanism can be vital for high-precision detection as a slight angle error would cause a serious accuracy drop for large aspect ratios objects. More importantly, we have proved that KLD is scale invariant. We further show that the KLD loss can be degenerated into the popular $l_{n}$-norm loss for horizontal detection. Experimental results on seven datasets using different detectors show its consistent superiority, and codes are available at https://github.com/yangxue0827/RotationDetection and https://github.com/open-mmlab/mmrotate.

cs.CV↗

arXiv2021

Imbalanced Adversarial Training with Reweighting

Adversarial training has been empirically proven to be one of the most effective and reliable defense methods against adversarial attacks. However, almost all existing studies about adversarial training are focused on balanced datasets, where each class has an equal amount of training examples. Research on adversarial training with imbalanced training datasets is rather limited. As the initial effort to investigate this problem, we reveal the facts that adversarially trained models present two distinguished behaviors from naturally trained models in imbalanced datasets: (1) Compared to natural training, adversarially trained models can suffer much worse performance on under-represented classes, when the training dataset is extremely imbalanced. (2) Traditional reweighting strategies may lose efficacy to deal with the imbalance issue for adversarial training. For example, upweighting the under-represented classes will drastically hurt the model's performance on well-represented classes, and as a result, finding an optimal reweighting value can be tremendously challenging. In this paper, to further understand our observations, we theoretically show that the poor data separability is one key reason causing this strong tension between under-represented and well-represented classes. Motivated by this finding, we propose Separable Reweighted Adversarial Training (SRAT) to facilitate adversarial training under imbalanced scenarios, by learning more separable features for different classes. Extensive experiments on various datasets verify the effectiveness of the proposed framework.

cs.LG↗

arXiv2021

Towards the Memorization Effect of Neural Networks in Adversarial Training

Recent studies suggest that ``memorization'' is one important factor for overparameterized deep neural networks (DNNs) to achieve optimal performance. Specifically, the perfectly fitted DNNs can memorize the labels of many atypical samples, generalize their memorization to correctly classify test atypical samples and enjoy better test performance. While, DNNs which are optimized via adversarial training algorithms can also achieve perfect training performance by memorizing the labels of atypical samples, as well as the adversarially perturbed atypical samples. However, adversarially trained models always suffer from poor generalization, with both relatively low clean accuracy and robustness on the test set. In this work, we study the effect of memorization in adversarial trained DNNs and disclose two important findings: (a) Memorizing atypical samples is only effective to improve DNN's accuracy on clean atypical samples, but hardly improve their adversarial robustness and (b) Memorizing certain atypical samples will even hurt the DNN's performance on typical samples. Based on these two findings, we propose Benign Adversarial Training (BAT) which can facilitate adversarial training to avoid fitting ``harmful'' atypical samples and fit as more ``benign'' atypical samples as possible. In our experiments, we validate the effectiveness of BAT, and show it can achieve better clean accuracy vs. robustness trade-off than baseline methods, in benchmark datasets such as CIFAR100 and Tiny~ImageNet.

cs.LG↗

arXiv2021

Dense Label Encoding for Boundary Discontinuity Free Rotation Detection

Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc. Differing from the dominant regression-based approaches for orientation estimation, this paper explores a relatively less-studied methodology based on classification. The hope is to inherently dismiss the boundary discontinuity issue as encountered by the regression-based detectors. We propose new techniques to push its frontier in two aspects: i) new encoding mechanism: the design of two Densely Coded Labels (DCL) for angle classification, to replace the Sparsely Coded Label (SCL) in existing classification-based detectors, leading to three times training speed increase as empirically observed across benchmarks, further with notable improvement in detection accuracy; ii) loss re-weighting: we propose Angle Distance and Aspect Ratio Sensitive Weighting (ADARSW), which improves the detection accuracy especially for square-like objects, by making DCL-based detectors sensitive to angular distance and object's aspect ratio. Extensive experiments and visual analysis on large-scale public datasets for aerial images i.e. DOTA, UCAS-AOD, HRSC2016, as well as scene text dataset ICDAR2015 and MLT, show the effectiveness of our approach. The source code is available at https://github.com/Thinklab-SJTU/DCL_RetinaNet_Tensorflow and is also integrated in our open source rotation detection benchmark: https://github.com/yangxue0827/RotationDetection.

cs.CV↗

arXiv2020

An Artificial Intelligence-Driven Agent for Real-Time Head-and-Neck IMRT Plan Generation using Conditional Generative Adversarial Network (cGAN)

Purpose: To develop an Artificial Intelligence (AI) agent for fully-automated rapid head and neck (H&N) IMRT plan generation without time-consuming inverse planning.$$$$ Methods: This AI agent was trained using a conditional Generative Adversarial Network architecture. The generator, PyraNet, is a novel Deep Learning network that implements 28 classic ResNet blocks in pyramid-like concatenations. The discriminator is a customized 4-layer DenseNet. The AI agent first generates customized 2D projections at 9 template beam angles from 3D CT volume and structures of a patient. These projections are then stacked as 4D inputs of PyraNet, from which 9 radiation fluence maps are generated simultaneously. Finally, the predicted fluence maps are imported into a commercial treatment planning system (TPS) for plan integrity checks. The AI agent was built and tested upon 231 oropharyngeal plans from a TPS plan library. Only the primary plans in the sequential boost regime were studied. A customized Harr wavelet loss was adopted for fluence map comparison. Isodose distributions in test AI plans and TPS plans were qualitatively evaluated. Key dosimetric metrics were statistically compared.$$$$ Results: All test AI plans were successfully generated. Isodose gradients outside of PTV in AI plans were comparable with TPS plans. After PTV coverage normalization, $D_{mean}$ of parotids and oral cavity in AI plans and TPS plans were comparable without statistical significance. AI plans achieved comparable $D_{max}$ at 0.01cc of brainstem and cord+5mm without clinically relevant differences, but body $D_{max}$ was higher than the TPS plan results. The AI agent needs ~3s per case to predict fluence maps.$$$$ Conclusions: The developed AI agent can generate H&N IMRT plans with satisfying dosimetry quality. With rapid and fully automated implementation, it holds great potential for clinical applications.

physics.med-ph↗

arXiv2020

Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning

Dialogue systems play an increasingly important role in various aspects of our daily life. It is evident from recent research that dialogue systems trained on human conversation data are biased. In particular, they can produce responses that reflect people's gender prejudice. Many debiasing methods have been developed for various NLP tasks, such as word embedding. However, they are not directly applicable to dialogue systems because they are likely to force dialogue models to generate similar responses for different genders. This greatly degrades the diversity of the generated responses and immensely hurts the performance of the dialogue models. In this paper, we propose a novel adversarial learning framework Debiased-Chat to train dialogue models free from gender bias while keeping their performance. Extensive experiments on two real-world conversation datasets show that our framework significantly reduces gender bias in dialogue models while maintaining the response quality. The implementation of the proposed framework is released.

cs.CL↗

arXiv2020

Data-to-Text Generation with Style Imitation

Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, sentence structures). More traditional systems use templates to determine the realization of text. Yet manual or automatic construction of high-quality templates is difficult, and a template acting as hard constraints could harm content fidelity when it does not match the record perfectly. We study a new way of stylistic control by using existing sentences as soft templates. That is, the model learns to imitate the writing style of any given exemplar sentence, with automatic adaptions to faithfully describe the content record. The problem is challenging due to the lack of parallel data. We develop a neural approach that includes a hybrid attention-copy mechanism, learns with weak supervisions, and is enhanced with a new content coverage constraint. We conduct experiments in restaurants and sports domains. Results show our approach achieves stronger performance than a range of comparison methods. Our approach balances well between content fidelity and style control given exemplars that match the records to varying degrees.

cs.CL↗

arXiv2020

Representation Learning from Limited Educational Data with Crowdsourced Labels

Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing representation learning approaches often require a large number of consistent and noise-free labels. However, due to various reasons such as budget constraints and privacy concerns, labels are very limited in many real-world scenarios. Directly applying standard representation learning approaches on small labeled data sets will easily run into over-fitting problems and lead to sub-optimal solutions. Even worse, in some domains such as education, the limited labels are usually annotated by multiple workers with diverse expertise, which yields noises and inconsistency in such crowdsourcing settings. In this paper, we propose a novel framework which aims to learn effective representations from limited data with crowdsourced labels. Specifically, we design a grouping based deep neural network to learn embeddings from a limited number of training samples and present a Bayesian confidence estimator to capture the inconsistency among crowdsourced labels. Furthermore, to expedite the training process, we develop a hard example selection procedure to adaptively pick up training examples that are misclassified by the model. Extensive experiments conducted on three real-world data sets demonstrate the superiority of our framework on learning representations from limited data with crowdsourced labels, comparing with various state-of-the-art baselines. In addition, we provide a comprehensive analysis on each of the main components of our proposed framework and also introduce the promising results it achieved in our real production to fully understand the proposed framework.

cs.LG↗

arXiv2019

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation

We introduce Texar, an open-source toolkit aiming to support the broad set of text generation tasks that transform any inputs into natural language, such as machine translation, summarization, dialog, content manipulation, and so forth. With the design goals of modularity, versatility, and extensibility in mind, Texar extracts common patterns underlying the diverse tasks and methodologies, creates a library of highly reusable modules, and allows arbitrary model architectures and algorithmic paradigms. In Texar, model architecture, inference, and learning processes are properly decomposed. Modules at a high concept level can be freely assembled and plugged in/swapped out. The toolkit also supports a rich set of large-scale pretrained models. Texar is thus particularly suitable for researchers and practitioners to do fast prototyping and experimentation. The versatile toolkit also fosters technique sharing across different text generation tasks. Texar supports both TensorFlow and PyTorch, and is released under Apache License 2.0 at https://www.texar.io.

cs.CL↗

arXiv2018

Growth of Thin Oxidation-Resistive Crystalline Si Nanostructures on Graphene

We report the growth of Si nanostructures, either as thin films or nanoparticles, on graphene substrates. The Si nanostructures are shown to be single crystalline, air stable and oxidation resistive, as indicated by the observation of a single crystalline Si Raman mode at around 520 cm-1, a STM image of an ordered surface structure under ambient condition, and a Schottky junction with graphite. Ultra-thin silicon regions exhibit silicene-like behavior, including a Raman mode at around 550 cm-1, a triangular lattice structure in STM that has distinctly different lattice spacing from that of either graphene or thicker Si, and metallic conductivity of up to 500 times higher than that of graphite. This work suggests a bottom-up approach to forming a Si nanostructure array on a large scale patterned graphene substrate for fabricating nanoscale Si electronic devices.

cond-mat.mtrl-sci↗

arXiv2017

Ptychography intensity interferometry imaging

Intensity interferometry (II) exploits the second-order correlation to acquire the spatial frequency information of an object, which has been used to observe distant stars since 1950s. However, due to unreliability of employed imaging reconstruction algorithms, II can only image simple and sparse objects such as double stars. We here develop a method that overcomes this unreliability problem and enables imaging complex objects by combing II and a ptychography iterative algorithm. Different from previous ptychography iterative-type algorithms that work only for diffractive objects using coherence light sources, our method obtains the objects spatial spectrum from the second-order correlation of intensity fluctuation by using an incoherent source, which therefore largely simplifies the imaging process. Furthermore, by introducing loose supports in the ptychography algorithm, a high-quality image can be recovered without knowing the precise size and position of the scanning illumination, which is a strong requirement for traditional ptychography iterative algorithm.

eess.IV↗

arXiv2017

Enhanced betatron radiation by steering a low-energy-spread electron beam in a deflected laser-driven plasma wiggler

Laser wakefield accelerators (LWFA) hold great potential to produce high-quality high-energy electron beams (e beams) and simultaneously bright x-ray sources via betatron radiation, which are very promising for pump-probe study in ultrafast science. However, in order to obtain a high-quality e beam, electron injection and acceleration should be carefully manipulated, where a large oscillation amplitude has to be avoided and thus the emitted x-ray yield is limited. Here, we report a new scheme to experimentally enhance betatron radiation significantly both in photon yield and photon energy by separating electron injection and acceleration from manipulation of the e-beam transverse oscillation in the wake via introducing a slanted thin plasma refraction slab. Particle-in-cell simulations indicate that the e-beam transverse oscillation amplitude can be increased by more than 10 folds, after being steered into the deflected laser-driven wakefield due to refraction at the slab's boundaries. Spectral broadening of the x-rays can be suppressed owing to the small variation in the peak energy of the low-energy-spread e beam in a plasma wiggler regime. We demonstrate that the high-quality e-beam generation, refracting and wiggling can act as a whole to realize the concurrence of monoenergetic e beam and bright x-rays in a compact LWFA.

physics.plasm-ph↗

arXiv2014

The second-order interference of two independent single-mode He-Ne lasers

The second-order spatial and temporal interference patterns with two independent single-mode He-Ne lasers are observed in a Hong-Ou-Mandel interferometer. Two-photon interference in Feynman's path integral theory is employed to interpret the experimental results. The conditions to observe the second-order interference pattern with two independent single-mode continuous wave lasers are discussed. It is concluded that two-photon interference exists for not only identical photons, but also photons with different spectrums if the detection system can not distinguish them in principle. The second-order temporal beating with two independent lasers can be employed to measure the coherence time and frequency of one laser if the properties of the other laser were known.

physics.optics↗