arXiv subjects

Yue He

Publications and source records attributed to Yue He.

At least 55 records · Page 3Linked to original sources

arXiv2022

Repainting and Imitating Learning for Lane Detection

Current lane detection methods are struggling with the invisibility lane issue caused by heavy shadows, severe road mark degradation, and serious vehicle occlusion. As a result, discriminative lane features can be barely learned by the network despite elaborate designs due to the inherent invisibility of lanes in the wild. In this paper, we target at finding an enhanced feature space where the lane features are distinctive while maintaining a similar distribution of lanes in the wild. To achieve this, we propose a novel Repainting and Imitating Learning (RIL) framework containing a pair of teacher and student without any extra data or extra laborious labeling. Specifically, in the repainting step, an enhanced ideal virtual lane dataset is built in which only the lane regions are repainted while non-lane regions are kept unchanged, maintaining the similar distribution of lanes in the wild. The teacher model learns enhanced discriminative representation based on the virtual data and serves as the guidance for a student model to imitate. In the imitating learning step, through the scale-fusing distillation module, the student network is encouraged to generate features that mimic the teacher model both on the same scale and cross scales. Furthermore, the coupled adversarial module builds the bridge to connect not only teacher and student models but also virtual and real data, adjusting the imitating learning process dynamically. Note that our method introduces no extra time cost during inference and can be plug-and-play in various cutting-edge lane detection networks. Experimental results prove the effectiveness of the RIL framework both on CULane and TuSimple for four modern lane detection methods. The code and model will be available soon.

cs.CV↗

arXiv2022

SoccerNet 2022 Challenges Results

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on https://www.soccer-net.org. Baselines and development kits are available on https://github.com/SoccerNet.

cs.CV↗

arXiv2022

StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning

3D scene stylization aims at generating stylized images of the scene from arbitrary novel views following a given set of style examples, while ensuring consistency when rendered from different views. Directly applying methods for image or video stylization to 3D scenes cannot achieve such consistency. Thanks to recently proposed neural radiance fields (NeRF), we are able to represent a 3D scene in a consistent way. Consistent 3D scene stylization can be effectively achieved by stylizing the corresponding NeRF. However, there is a significant domain gap between style examples which are 2D images and NeRF which is an implicit volumetric representation. To address this problem, we propose a novel mutual learning framework for 3D scene stylization that combines a 2D image stylization network and NeRF to fuse the stylization ability of 2D stylization network with the 3D consistency of NeRF. We first pre-train a standard NeRF of the 3D scene to be stylized and replace its color prediction module with a style network to obtain a stylized NeRF. It is followed by distilling the prior knowledge of spatial consistency from NeRF to the 2D stylization network through an introduced consistency loss. We also introduce a mimic loss to supervise the mutual learning of the NeRF style module and fine-tune the 2D stylization decoder. In order to further make our model handle ambiguities of 2D stylization results, we introduce learnable latent codes that obey the probability distributions conditioned on the style. They are attached to training samples as conditional inputs to better learn the style module in our novel stylized NeRF. Experimental results demonstrate that our method is superior to existing approaches in both visual quality and long-range consistency.

cs.GR↗

arXiv2022

NICO++: Towards Better Benchmarking for Domain Generalization

Despite the remarkable performance that modern deep neural networks have achieved on independent and identically distributed (I.I.D.) data, they can crash under distribution shifts. Most current evaluation methods for domain generalization (DG) adopt the leave-one-out strategy as a compromise on the limited number of domains. We propose a large-scale benchmark with extensive labeled domains named NICO++ along with more rational evaluation methods for comprehensively evaluating DG algorithms. To evaluate DG datasets, we propose two metrics to quantify covariate shift and concept shift, respectively. Two novel generalization bounds from the perspective of data construction are proposed to prove that limited concept shift and significant covariate shift favor the evaluation capability for generalization. Through extensive experiments, NICO++ shows its superior evaluation capability compared with current DG datasets and its contribution in alleviating unfairness caused by the leak of oracle knowledge in model selection.

cs.CV↗

arXiv2022

Uncertainty quantification and estimation in differential dynamic microscopy

Differential dynamic microscopy (DDM) is a form of video image analysis that combines the sensitivity of scattering and the direct visualization benefits of microscopy. DDM is broadly useful in determining dynamical properties including the intermediate scattering function for many spatiotemporally correlated systems. Despite its straightforward analysis, DDM has not been fully adopted as a routine characterization tool, largely due to computational cost and lack of algorithmic robustness. We present statistical analysis that quantifies the noise, reduces the computational order and enhances the robustness of DDM analysis. We propagate the image noise through the Fourier analysis, which allows us to comprehensively study the bias in different estimators of model parameters, and we derive a different way to detect whether the bias is negligible. Furthermore, through use of Gaussian process regression (GPR), we find that predictive samples of the image structure function require only around 0.5%-5% of the Fourier transforms of the observed quantities. This vastly reduces computational cost, while preserving information of the quantities of interest, such as quantiles of the image scattering function, for subsequent analysis. The approach, which we call DDM with uncertainty quantification (DDM-UQ), is validated using both simulations and experiments with respect to accuracy and computational efficiency, as compared with conventional DDM and multiple particle tracking. Overall, we propose that DDM-UQ lays the foundation for important new applications of DDM, as well as to high-throughput characterization. We implement the fast computation tool in a new, publicly available MATLAB software package.

cond-mat.soft↗

arXiv2022

CausPref: Causal Preference Learning for Out-of-Distribution Recommendation

In spite of the tremendous development of recommender system owing to the progressive capability of machine learning recently, the current recommender system is still vulnerable to the distribution shift of users and items in realistic scenarios, leading to the sharp decline of performance in testing environments. It is even more severe in many common applications where only the implicit feedback from sparse data is available. Hence, it is crucial to promote the performance stability of recommendation method in different environments. In this work, we first make a thorough analysis of implicit recommendation problem from the viewpoint of out-of-distribution (OOD) generalization. Then under the guidance of our theoretical analysis, we propose to incorporate the recommendation-specific DAG learner into a novel causal preference-based recommendation framework named CausPref, mainly consisting of causal learning of invariant user preference and anti-preference negative sampling to deal with implicit feedback. Extensive experimental results from real-world datasets clearly demonstrate that our approach surpasses the benchmark models significantly under types of out-of-distribution settings, and show its impressive interpretability.

cs.LG↗

arXiv2021

Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition

Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual semantics within and between character instances, making them not generalize well to arbitrary shape scene text. To address this issue, we make the first attempt to perform textual reasoning based on visual semantics in this paper. Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity. Then, these subgraphs are sequentially connected by their root nodes and merged into a complete graph. Based on this graph, we devise a graph convolutional network for textual reasoning (GTR) by supervising it with a cross-entropy loss. GTR can be easily plugged in representative STR models to improve their performance owing to better textual reasoning. Specifically, we construct our model, namely S-GTR, by paralleling GTR to the language model in a segmentation-based STR baseline, which can effectively exploit the visual-linguistic complementarity via mutual learning. S-GTR sets new state-of-the-art on six challenging STR benchmarks and generalizes well to multi-linguistic datasets. Code is available at https://github.com/adeline-cs/GTR.

cs.CV↗

arXiv2021

Good Practices and A Strong Baseline for Traffic Anomaly Detection

The detection of traffic anomalies is a critical component of the intelligent city transportation management system. Previous works have proposed a variety of notable insights and taken a step forward in this field, however, dealing with the complex traffic environment remains a challenge. Moreover, the lack of high-quality data and the complexity of the traffic scene, motivate us to study this problem from a hand-crafted perspective. In this paper, we propose a straightforward and efficient framework that includes pre-processing, a dynamic track module, and post-processing. With video stabilization, background modeling, and vehicle detection, the pro-processing phase aims to generate candidate anomalies. The dynamic tracking module seeks and locates the start time of anomalies by utilizing vehicle motion patterns and spatiotemporal status. Finally, we use post-processing to fine-tune the temporal boundary of anomalies. Not surprisingly, our proposed framework was ranked $1^{st}$ in the NVIDIA AI CITY 2021 leaderboard for traffic anomaly detection. The code is available at: https://github.com/Endeavour10020/AICity2021-Anomaly-Detection .

cs.CV↗

arXiv2021

Deep Stable Learning for Out-Of-Distribution Generalization

Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise. Therefore, eliminating the impact of distribution shifts between training and testing data is crucial for building performance-promising deep models. Conventional methods assume either the known heterogeneity of training data (e.g. domain labels) or the approximately equal capacities of different domains. In this paper, we consider a more challenging case where neither of the above assumptions holds. We propose to address this problem by removing the dependencies between features via learning weights for training samples, which helps deep models get rid of spurious correlations and, in turn, concentrate more on the true connection between discriminative features and labels. Extensive experiments clearly demonstrate the effectiveness of our method on multiple distribution generalization benchmarks compared with state-of-the-art counterparts. Through extensive experiments on distribution generalization benchmarks including PACS, VLCS, MNIST-M, and NICO, we show the effectiveness of our method compared with state-of-the-art counterparts.

cs.LG↗

arXiv2019

Towards Non-I.I.D. Image Classification: A Dataset and Baselines

I.I.D. hypothesis between training and testing data is the basis of numerous image classification methods. Such property can hardly be guaranteed in practice where the Non-IIDness is common, causing instable performances of these models. In literature, however, the Non-I.I.D. image classification problem is largely understudied. A key reason is lacking of a well-designed dataset to support related research. In this paper, we construct and release a Non-I.I.D. image dataset called NICO, which uses contexts to create Non-IIDness consciously. Compared to other datasets, extended analyses prove NICO can support various Non-I.I.D. situations with sufficient flexibility. Meanwhile, we propose a baseline model with ConvNet structure for General Non-I.I.D. image classification, where distribution of testing data is unknown but different from training data. The experimental results demonstrate that NICO can well support the training of ConvNet model from scratch, and a batch balancing module can help ConvNets to perform better in Non-I.I.D. settings.

cs.CV↗

arXiv2019

One-shot Face Reenactment

To enable realistic shape (e.g. pose and expression) transfer, existing face reenactment methods rely on a set of target faces for learning subject-specific traits. However, in real-world scenario end-users often only have one target face at hand, rendering existing methods inapplicable. In this work, we bridge this gap by proposing a novel one-shot face reenactment learning framework. Our key insight is that the one-shot learner should be able to disentangle and compose appearance and shape information for effective modeling. Specifically, the target face appearance and the source face shape are first projected into latent spaces with their corresponding encoders. Then these two latent spaces are associated by learning a shared decoder that aggregates multi-level features to produce the final reenactment results. To further improve the synthesizing quality on mustache and hair regions, we additionally propose FusionNet which combines the strengths of our learned decoder and the traditional warping method. Extensive experiments show that our one-shot face reenactment system achieves superior transfer fidelity as well as identity preserving capability than alternatives. More remarkably, our approach trained with only one target image per subject achieves competitive results to those using a set of target images, demonstrating the practical merit of this work. Code, models and an additional set of reenacted faces have been publicly released at the project page.

cs.CV↗

arXiv2019

Shafer-Fink type inequalities for arc lemniscate functions

In this paper, we investigate the monotonicity and inequalities for some functions involving the arc lemniscate and the hyperbolic arc lemniscate functions. In particular, sharp Shafer-Fink type inequalities for the arc lemniscate and the hyperbolic arc lemniscate functions are proved.

math.CA↗

arXiv2019

Effects and side-effects of plasmonic photothermal therapy in brain tissue

Heat generated from plasmonic nanoparticles can be utilized in plasmonic photothermal therapy. A combination of near-infrared laser and metallic nanoparticles are compelling for the treatment of brain cancer, due to their efficient light-to-heat conversion and bio-compatibility. However, one of the challenges of plasmonic photothermal therapy is to minimize the damage of the surrounding brain tissue. The adjacent tissue can be damaged as the results of either absorption of laser light, thermal conductivity, nanoparticles diffusing from the tumor, or a combination hereof. Hence, we still lack the full understanding about the light-tissue interaction and, in particular, the thermal response. We tested the temperature change in three different porcine cerebral tissues, i.e., the stem, the cerebrum, and the cerebellum, under laser treatment. We find that the different tissues have differential optical and thermal properties and confirm the enhancement of heating from adding plasmonic nanoparticles. Furthermore, we measure the loss of laser intensity through the different cerebral tissues and stress the importance of correct analysis of the local environment of a brain tumor.

physics.med-ph↗

arXiv2017

Merge or Not? Learning to Group Faces via Imitation Learning

Given a large number of unlabeled face images, face grouping aims at clustering the images into individual identities present in the data. This task remains a challenging problem despite the remarkable capability of deep learning approaches in learning face representation. In particular, grouping results can still be egregious given profile faces and a large number of uninteresting faces and noisy detections. Often, a user needs to correct the erroneous grouping manually. In this study, we formulate a novel face grouping framework that learns clustering strategy from ground-truth simulated behavior. This is achieved through imitation learning (a.k.a apprenticeship learning or learning by watching) via inverse reinforcement learning (IRL). In contrast to existing clustering approaches that group instances by similarity, our framework makes sequential decision to dynamically decide when to merge two face instances/groups driven by short- and long-term rewards. Extensive experiments on three benchmark datasets show that our framework outperforms unsupervised and supervised baselines.

cs.CV↗

arXiv2014

Proof of the Pólya conjecture

In this paper, we study lower bounds for higher eigenvalues of the Dirichlet eigenvalue problem of the Laplacian on a bounded domain $Ω$ in $\mathbb{R}^n$. It is well known that the $k$-th Dirichlet eigenvalue $λ_k$ obeys the Weyl asymptotic formula, that is, \[ λ_k\sim\frac{4π^2}{(ω_n\mathrm{vol}Ω)^\frac{2}{n}}k^\frac{2}{n}\qquad\hbox{as}\quad k\rightarrow\infty, \] where $\mathrm{vol}Ω$ is the volume of $Ω$. In view of the above formula, Pólya conjectured that \[ λ_k\gs\frac{4π^2}{(ω_n\mathrm{vol}Ω)^\frac{2}{n}}k^\frac{2}{n}\qquad\hbox{for}\quad k\in\mathbb{N}. \] This is the well-known conjecture of Pólya. Studies on this topic have a long history with much work.In particular, one of the more remarkable achievements in recent tens years has been achieved by Li and Yau [Comm. Math. Phys. 88 (1983), 309--318]. They solved partially the conjecture of Pólya with a slight difference by a factor $n/(n+2)$. Here, following the argument of Li and Yau on the whole, we shall thoroughly solve the above conjecture.

math.DG↗

arXiv2014

On sharp lower bound of the spectral gap for a Schrödinger operator and some related results

In this paper, we give an easy proof of the main results of Andrews and Clutterbuck's paper [J. Amer. Math. Soc. 24 (2011), no. 3, 899--916], which gives both a sharp lower bound for the spectral gap of a Schröinger operator and a sharp modulus of concavity for the logarithm of the corresponding first eigenfunction. We arrive directly at same estimates by the `double coordinate' approach and asymptotic behavior of parabolic flows. Although using the techniques appeared in the above paper, we partly simplify the method and argument. This maybe help to provide an easy way for estimating spectral gap. Besides, we also get a new lower bound of spectral gap for a class of Schödinger operator.

math.AP↗

arXiv2012

Sharp estimate of lower bound for the first eigenvalue in the Laplacian operator on compact Riemannian manifolds

The aim of this paper is give a simple proof of some results in \cite{Jun Ling-2006-IJM} and \cite{JunLing-2007-AGAG}, which are very deep studies in the sharp lower bound of the first eigenvalue in the Laplacian operator on compact Riemannian manifolds with nonnegative Ricci curvature. We also get a result about lower bound of the first Neumann eigenvalue in a special case. Indeed, our estimate of lower bound in the this case is optimal. Although the methods used in here due to \cite{Jun Ling-2006-IJM} (or \cite{JunLing-2007-AGAG}) on the whole, to some extent we can tackle the singularity of test functions and also simplify greatly much calculation in these references. Maybe this provides another way to estimate eigenvalues.

math.DG↗

arXiv2008

Transonic Potential Flows in A Convergent--Divergent Approximate Nozzle

In this paper we prove existence, uniqueness and regularity of certain perturbed (subsonic--supersonic) transonic potential flows in a two-dimensional Riemannian manifold with "convergent-divergent" metric, which is an approximate model of the de Laval nozzle in aerodynamics. The result indicates that transonic flows obtained by quasi-one-dimensional flow model in fluid dynamics are stable with respect to the perturbation of the velocity potential function at the entry (i.e., tangential velocity along the entry) of the nozzle. The proof is based upon linear theory of elliptic-hyperbolic mixed type equations in physical space and a nonlinear iteration method.

math.AP↗