no code implementations • 9 Apr 2024 • YanJie Li, Weijun Li, Lina Yu, Min Wu, Jingyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng
However, its performance is very dependent on the training data and performs poorly on data outside the training set, which leads to poor noise robustness and Versatility of such methods.
no code implementations • 28 Feb 2024 • YanJie Li, Jingyi Liu, Weijun Li, Lina Yu, Min Wu, Wenqiang Li, Meilan Hao, Su Wei, Yusong Deng
The SR problem is solved as a pure multimodal problem, and contrastive learning is also introduced in the training process for modal alignment to facilitate later modal feature fusion.
1 code implementation • 25 Jan 2024 • Min Wu, Weijun Li, Lina Yu, Wenqiang Li, Jingyi Liu, YanJie Li, Meilan Hao
Therefore, a greedy pruning algorithm is proposed to prune the network into a subnetwork while ensuring the accuracy of data fitting.
no code implementations • 24 Jan 2024 • YanJie Li, Weijun Li, Lina Yu, Min Wu, Jingyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng
To optimize the trade-off between efficiency and versatility, we introduce SR-GPT, a novel algorithm for symbolic regression that integrates Monte Carlo Tree Search (MCTS) with a Generative Pre-Trained Transformer (GPT).
no code implementations • 3 Jan 2024 • YanJie Li, Weijun Li, Lina Yu, Min Wu, Jinyi Liu, Wenqiang Li, Meilan Hao
1, The type of activation function is single and relatively fixed, which leads to poor "unit representation ability" of the network, and it is often used to solve simple problems with very complex networks; 2, the network structure is not adaptive, it is easy to cause network structure redundant or insufficient.
no code implementations • 13 Nov 2023 • YanJie Li, Weijun Li, Lina Yu, Min Wu, Jinyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng
To address these issues, we propose MetaSymNet, a novel neural network that dynamically adjusts its structure in real-time, allowing for both expansion and contraction.
no code implementations • 1 Oct 2023 • YanJie Li, Bin Xie, Songtao Guo, Yuanyuan Yang, Bin Xiao
Lots of papers have emerged to investigate the robustness and safety of deep learning models against adversarial attacks.
no code implementations • 24 Sep 2023 • Wenqiang Li, Weijun Li, Lina Yu, Min Wu, Jingyi Liu, YanJie Li
Instead of searching for expressions within a large search space, we explore DySymNet with various structures and optimize them to identify expressions that better-fitting the data.
no code implementations • 10 Aug 2023 • YanJie Li, Mingxing Duan, Xuelong Dai, Bin Xiao
In the first stage, we extract multi-scale style embeddings by a pyramid-like network and identity embeddings by a pretrained FR model and propose a novel Attention-guided Adaptive Instance Normalization layer (AAIN) to merge them via background-patch cross-attention maps.
no code implementations • CVPR 2023 • YanJie Li, Yiquan Li, Xuelong Dai, Songtao Guo, Bin Xiao
2D face recognition has been proven insecure for physical adversarial attacks.
1 code implementation • 25 Nov 2021 • Sen yang, Zhicheng Wang, Ze Chen, YanJie Li, Shoukui Zhang, Zhibin Quan, Shu-Tao Xia, Yiping Bao, Erjin Zhou, Wankou Yang
This paper presents a new method to solve keypoint detection and instance association by using Transformer.
Ranked #10 on Multi-Person Pose Estimation on MS COCO
1 code implementation • 17 Nov 2021 • Xuelong Dai, YanJie Li, Hua Dai, Bin Xiao
The unrestricted adversarial attack loss is incorporated in the special adversarial training of GAN, which enables the generator to generate the adversarial examples to spoof the target network.
3 code implementations • 7 Jul 2021 • YanJie Li, Sen yang, Peidong Liu, Shoukui Zhang, Yunxiao Wang, Zhicheng Wang, Wankou Yang, Shu-Tao Xia
The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance.
1 code implementation • ICCV 2021 • YanJie Li, Shoukui Zhang, Zhicheng Wang, Sen yang, Wankou Yang, Shu-Tao Xia, Erjin Zhou
Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints.
no code implementations • 6 Mar 2021 • Yiming Li, YanJie Li, Yalei Lv, Yong Jiang, Shu-Tao Xia
Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data.
no code implementations • 28 Sep 2016 • Guangliang Du, Minmin Wang, Canlin Zhou, Shuchun Si, Hui Li, Zhenkun Lei, YanJie Li
In this paper, we proposed an improved method, which eliminates the system calibration and determination in Zhang's method, meanwhile does not need to use the low frequency fringe pattern.
no code implementations • 7 Jun 2016 • Minmin Wang, Guangliang Du, Canlin Zhou, Chaorui Zhang, Shuchun Si, Hui Li, Zhenkun Lei, YanJie Li
We proposed a method for enhanced high dynamic range 3D shape measurement based on generalized phase-shifting algorithm, which combines the complementary technique of inverted and regular fringe patterns with generalized phase-shifting algorithm.