no code implementations • 2 Aug 2023 • Yan Ma, Weicong Liang, Bohan Chen, Yiduo Hao, BoJian Hou, Xiangyu Yue, Chao Zhang, Yuhui Yuan
Motivated by the remarkable achievements of DETR-based approaches on COCO object detection and segmentation benchmarks, recent endeavors have been directed towards elevating their performance through self-supervised pre-training of Transformers while preserving a frozen backbone.
no code implementations • 24 Sep 2022 • Kang Xu, Yan Ma, Bingsheng Wei, Wei Li
While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations.
no code implementations • 23 Sep 2022 • Kang Xu, Yan Ma, Wei Li
Our key insight is that dynamic systems with different parameters provide different levels of difficulty for the policy, and the difficulty of behaving well in a system is constantly changing due to the evolution of the policy.
1 code implementation • 4 Aug 2022 • Yuxiao Huang, Yan Ma
A key challenge in Machine Learning is class imbalance, where the sample size of some classes (majority classes) are much higher than that of the other classes (minority classes).
no code implementations • 12 Jan 2022 • Yan Ma, Tianxing Liu, Bingsheng Wei, Yi Liu, Kang Xu, Wei Li
Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation. The evolutionary part in these hybrid methods maintains a population of policy networks. However, existing methods focus on optimizing the parameters of policy network, which is usually high-dimensional and tricky for EA. In this paper, we shift the target of evolution from high-dimensional parameter space to low-dimensional action space. We propose Evolutionary Action Selection-Twin Delayed Deep Deterministic Policy Gradient (EAS-TD3), a novel hybrid method of EA and DRL. In EAS, we focus on optimizing the action chosen by the policy network and attempt to obtain high-quality actions to promote policy learning through an evolutionary algorithm.
2 code implementations • 7 Jul 2020 • Zhengzheng Tu, Yan Ma, Zhun Li, Chenglong Li, Jieming Xu, Yongtao Liu
Salient object detection in complex scenes and environments is a challenging research topic.
no code implementations • 7 Aug 2019 • Zhengzheng Tu, Yan Ma, Chenglong Li, Jin Tang, Bin Luo
To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edge guided feature learning for accurate salient object detection.
1 code implementation • 16 May 2019 • Zhengzheng Tu, Tian Xia, Chenglong Li, Xiaoxiao Wang, Yan Ma, Jin Tang
In this paper, we propose an effective approach for RGB-T image saliency detection.