Searcharxiv⌕ Search

arXiv subjects

Yating Liu

Publications and source records attributed to Yating Liu.

40 records · Page 3Linked to original sources

Geometry Uncertainty Projection Network for Monocular 3D Object Detection

Geometry Projection is a powerful depth estimation method in monocular 3D object detection. It estimates depth dependent on heights, which introduces mathematical priors into the deep model. But projection process also introduces the error amplification problem, in which the error of the estimated height will be amplified and reflected greatly at the output depth. This property leads to uncontrollable depth inferences and also damages the training efficiency. In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages. Specifically, a GUP module is proposed to obtains the geometry-guided uncertainty of the inferred depth, which not only provides high reliable confidence for each depth but also benefits depth learning. Furthermore, at the training stage, we propose a Hierarchical Task Learning strategy to reduce the instability caused by error amplification. This learning algorithm monitors the learning situation of each task by a proposed indicator and adaptively assigns the proper loss weights for different tasks according to their pre-tasks situation. Based on that, each task starts learning only when its pre-tasks are learned well, which can significantly improve the stability and efficiency of the training process. Extensive experiments demonstrate the effectiveness of the proposed method. The overall model can infer more reliable object depth than existing methods and outperforms the state-of-the-art image-based monocular 3D detectors by 3.74% and 4.7% AP40 of the car and pedestrian categories on the KITTI benchmark.

cs.CV↗

Monotone convex order for the McKean-Vlasov processes

In this paper, we establish the monotone convex order between two $\mathbb{R}$-valued McKean-Vlasov processes $X=(X_t)_{t\in [0, T]}$ and $Y=(Y_t)_{t\in [0, T]}$ defined on a filtered probability space $(Ω, \mathcal{F}, (\mathcal{F}_{t})_{t\geq0}, \mathbb{P})$ by \begin{align} &dX_{t}=b(t, X_{t}, μ_{t})dt+σ(t, X_{t}, μ_{t})dB_{t}, \quad X_{0}\in L^{p}(\mathbb{P})\; \text{with}\; p\geq 2,\nonumber\\ &dY_{t}=β(t, Y_{t}, ν_{t})dt+θ(t, \,Y_{t}, ν_{t})\,dB_{t}, \,\quad Y_{0}\in L^{p}(\mathbb{P}), \nonumber \end{align} where $\forall\, t\in [0, T],\: μ_{t}=\mathbb{P}\circ X_{t}^{-1}, \:ν_{t}=\mathbb{P}\circ Y_{t}^{-1}. $ If we make the convexity and monotony assumption (only) on $b$ and $|σ|$ and if $b\leq β$ and $|σ|\leq |θ|$, then the monotone convex order for the initial random variable $X_0\preceq_{\,\text{mcv}} Y_0$ can be propagated to the whole path of processes $X$ and $Y$. That is, if we consider a non-decreasing convex functional $F$ defined on the path space with polynomial growth, we have $\mathbb{E}\, F(X)\leq \mathbb{E}\, F(Y)$; for a non-decreasing convex functional $G$ defined on the product space involving the path space and its marginal distribution space, we have $\mathbb{E}\, G(X, (μ_{t})_{t\in [0, T]})\leq \mathbb{E}\, G(Y, (ν_{t})_{t\in [0, T]})$ under appropriate conditions. The symmetric setting is also valid, that is, if $Y_0\preceq_{\,\text{mcv}} X_0$ and $|θ|\leq |σ|$, then $\mathbb{E}\, F(Y)\leq \mathbb{E}\, F(X)$ and $\mathbb{E}\, G(Y, (ν_{t})_{t\in [0, T]})\leq \mathbb{E}\, G(X, (μ_{t})_{t\in [0, T]})$. The proof is based on several forward and backward dynamic programming principle and the convergence of the truncated Euler scheme of the McKean-Vlasov equation.

math.PR↗

Convergence rate of optimal quantization grids and application to empirical measure

We study the convergence rate of the optimal quantization for a probability measure sequence $(μ_{n})_{n\in\mathbb{N}^{*}}$ on $\mathbb{R}^{d}$ converging in the Wasserstein distance in two aspects: the first one is the convergence rate of optimal quantizer $x^{(n)}\in(\mathbb{R}^{d})^{K}$ of $μ_{n}$ at level $K$; the other one is the convergence rate of the distortion function valued at $x^{(n)}$, called the "performance" of $x^{(n)}$. Moreover, we also study the mean performance of the optimal quantization for the empirical measure of a distribution $μ$ with finite second moment but possibly unbounded support. As an application, we show that the mean performance for the empirical measure of the multidimensional normal distribution $\mathcal{N}(m, Σ)$ and of distributions with hyper-exponential tails behave like $\mathcal{O}(\frac{\log n}{\sqrt{n}})$. This extends the results from [BDL08] obtained for compactly supported distribution. We also derive an upper bound which is sharper in the quantization level $K$ but suboptimal in $n$ by applying results in [FG15].

math.ST↗

Characterization of probability distribution convergence in Wasserstein distance by $L^{p}$-quantization error function

We establish conditions to characterize probability measures by their $L^{p}$-quantization error functions in both $\mathbb{R}^{d}$ and Hilbert settings. This characterization is two-fold: static (identity of two distributions) and dynamic (convergence for the $L^p$-Wasserstein distance). We first propose a criterion on the quantization level $N$, valid for any norm on $\mathbb{R}^{d}$ and any order $p$ based on a geometrical approach involving the Voronoï diagram. Then, we prove that in the $L^2$-case on a (separable) Hilbert space, the condition on the level $N$ can be reduced to $N=2$, which is optimal. More quantization based characterization cases on dimension 1 and a discussion of the completeness of a distance defined by the quantization error function can be found in the end of this paper.

math.PR↗