no code implementations • 28 Jun 2023 • Wenjing Huang, Shikui Tu, Lei Xu
Diffusion models have showcased their remarkable capability to synthesize diverse and high-quality images, sparking interest in their application for real image editing.
1 code implementation • 30 Nov 2022 • Sicong Zang, Shikui Tu, Lei Xu
The cropped sketch patches are linked according to their global semantics or local geometric shapes, namely the synonymous proximity, by computing the cosine similarity between the captured patch embeddings.
1 code implementation • 24 Mar 2022 • Wenjing Huang, Shikui Tu, Lei Xu
To strike a balance between the reconstruction capacity and the control flexibility, the encoder is designed as a multi-head structure to yield embeddings for reconstruction and control, respectively: a high-dimensional tensor with spatial properties for consistent reconstruction and four low-dimensional facial component embeddings for semantic face editing.
no code implementations • 3 Aug 2021 • Peiying Li, Shikui Tu, Lei Xu
Current face recognition tasks are usually carried out on high-quality face images, but in reality, most face images are captured under unconstrained or poor conditions, e. g., by video surveillance.
no code implementations • AAAI 2021 • Kaixuan Zhao, Shikui Tu, Lei Xu
Existing deep learning methods for graph matching(GM) problems usually considered affinity learningto assist combinatorial optimization in a feedforward pipeline, and parameter learning is executed by back-propagating the gradients of the matching loss.
Ranked #17 on Graph Matching on PASCAL VOC (matching accuracy metric)
no code implementations • 14 May 2020 • Zhihao Xing, Shikui Tu, Lei Xu
We present a self-learning approach that combines deep reinforcement learning and Monte Carlo tree search to solve the traveling salesman problem.
no code implementations • 25 Sep 2019 • Zhihao Xing, Shikui Tu
We present a graph neural network assisted Monte Carlo Tree Search approach for the classical traveling salesman problem (TSP).
no code implementations • 25 Sep 2019 • Wenjing Huang, Shikui Tu, Lei Xu
In the inference time, when given an input, we will start a search process in the latent space which aims to find the closest reconstruction to the given image on the distribution of normal data.
no code implementations • 12 Apr 2019 • Wenjing Huang, Shikui Tu, Lei Xu
Proposed in 1991, Least Mean Square Error Reconstruction for self-organizing network, shortly Lmser, was a further development of the traditional auto-encoder (AE) by folding the architecture with respect to the central coding layer and thus leading to the features of symmetric weights and neurons, as well as jointly supervised and unsupervised learning.
no code implementations • 7 Jan 2019 • Xiaojie Gao, Shikui Tu, Lei Xu
By uniting the advantages in A* search algorithm with Monte Carlo tree search, we come up with a new algorithm named A* tree search in which best information is returned to guide next search.
no code implementations • 21 Nov 2018 • Minchao Li, Shikui Tu, Lei Xu
Neural style transfer has been demonstrated to be powerful in creating artistic image with help of Convolutional Neural Networks (CNN).
no code implementations • 13 Sep 2017 • Yajing Chen, Shikui Tu, Yuqi Yi, Lei Xu
Moreover, the combination of CNN encoder and removal of KL-divergence, i. e., the sketch-pix2seq model, had better performance in learning and generating sketches of multiple categories and showed promising results in creativity tasks.