arXiv subjects

Xiaoliang Cheng

Publications and source records attributed to Xiaoliang Cheng.

5 recordsLinked to original sources

arXiv2021

DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation

Binary grid mask representation is broadly used in instance segmentation. A representative instantiation is Mask R-CNN which predicts masks on a $28\times 28$ binary grid. Generally, a low-resolution grid is not sufficient to capture the details, while a high-resolution grid dramatically increases the training complexity. In this paper, we propose a new mask representation by applying the discrete cosine transform(DCT) to encode the high-resolution binary grid mask into a compact vector. Our method, termed DCT-Mask, could be easily integrated into most pixel-based instance segmentation methods. Without any bells and whistles, DCT-Mask yields significant gains on different frameworks, backbones, datasets, and training schedules. It does not require any pre-processing or pre-training, and almost no harm to the running speed. Especially, for higher-quality annotations and more complex backbones, our method has a greater improvement. Moreover, we analyze the performance of our method from the perspective of the quality of mask representation. The main reason why DCT-Mask works well is that it obtains a high-quality mask representation with low complexity. Code is available at https://github.com/aliyun/DCT-Mask.git.

cs.CV↗

arXiv2020

Tracklets Predicting Based Adaptive Graph Tracking

Most of the existing tracking methods link the detected boxes to the tracklets using a linear combination of feature cosine distances and box overlap. But the problem of inconsistent features of an object in two different frames still exists. In addition, when extracting features, only appearance information is utilized, neither the location relationship nor the information of the tracklets is considered. We present an accurate and end-to-end learning framework for multi-object tracking, namely \textbf{TPAGT}. It re-extracts the features of the tracklets in the current frame based on motion predicting, which is the key to solve the problem of features inconsistent. The adaptive graph neural network in TPAGT is adopted to fuse locations, appearance, and historical information, and plays an important role in distinguishing different objects. In the training phase, we propose the balanced MSE LOSS to successfully overcome the unbalanced samples. Experiments show that our method reaches state-of-the-art performance. It achieves 76.5\% MOTA on the MOT16 challenge and 76.2\% MOTA on the MOT17 challenge.

cs.CV↗

arXiv2020

Non-relativity of Kähler manifold and complex space forms

We study the non-relativity for two real analytic Kähler manifolds and complex space forms of three types. The first one is a Kähler manifold whose polarization of local Kähler potential is a Nash function in a local coordinate. The second one is the Hartogs domain equpped with two canonical metrics whose polarizations of the Kähler potentials are the diastatic functions.

math.CV↗

arXiv2020

Deep Euler method: solving ODEs by approximating the local truncation error of the Euler method

In this paper, we propose a deep learning-based method, deep Euler method (DEM) to solve ordinary differential equations. DEM significantly improves the accuracy of the Euler method by approximating the local truncation error with deep neural networks which could obtain a high precision solution with a large step size. The deep neural network in DEM is mesh-free during training and shows good generalization in unmeasured regions. DEM could be easily combined with other schemes of numerical methods, such as Runge-Kutta method to obtain better solutions. Furthermore, the error bound and stability of DEM is discussed.

math.NA↗

arXiv2016

Kahler submanifolds and the Umehara algebra

We show that an indefinite Euclidean complex space is not a relative of an indefinite non-flat complex space form. We further study whether two compact Fubini-Study spaces are relatives or not.

math.DG↗