Knowledge-Guided Object Discovery with Acquired Deep Impressions

被引:0
|
作者
Yuan, Jinyang [1 ]
Li, Bin [1 ]
Xue, Xiangyang [1 ]
机构
[1] Fudan Univ, Sch Comp Sci, Shanghai Key Lab Intelligent Informat Proc, Shanghai, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a framework called Acquired Deep Impressions (ADI) which continuously learns knowledge of objects as "impressions" for compositional scene understanding. In this framework, the model first acquires knowledge from scene images containing a single object in a supervised manner, and then continues to learn from novel multi-object scene images which may contain objects that have not been seen before without any further supervision, under the guidance of the learned knowledge as humans do. By memorizing impressions of objects into parameters of neural networks and applying the generative replay strategy, the learned knowledge can be reused to generate images with pseudo-annotations and in turn assist the learning of novel scenes. The proposed ADI framework focuses on the acquisition and utilization of knowledge, and is complementary to existing deep generative models proposed for compositional scene representation. We adapt a base model to make it fall within the ADI framework and conduct experiments on two types of datasets. Empirical results suggest that the proposed framework is able to effectively utilize the acquired impressions and improve the scene decomposition performance.
引用
收藏
页码:10798 / 10806
页数:9
相关论文
共 50 条
  • [1] Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation
    Chen, Xiaocong
    Huang, Chaoran
    Yao, Lina
    Wang, Xianzhi
    Liu, Wei
    Zhang, Wenjie
    [J]. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [2] KURL: A Knowledge-Guided Reinforcement Learning Model for Active Object Tracking
    Liu, Xin
    Tan, Jie
    Ren, Xiaoguang
    Ren, Weiya
    Dai, Huadong
    [J]. ASIAN CONFERENCE ON MACHINE LEARNING, VOL 222, 2023, 222
  • [3] Knowledge-Guided Paraphrase Identification
    Wang, Haoyu
    Ma, Fenglong
    Wang, Yaqing
    Gao, Jing
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 843 - 853
  • [4] Interactive Knowledge-Guided Learning
    Nordsieck, Richard
    Haehner, Joerg
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON AUTONOMIC COMPUTING AND SELF-ORGANIZING SYSTEMS COMPANION (ACSOS-C 2020), 2020, : 237 - 239
  • [5] Category Knowledge-Guided Parameter Calibration for Few-Shot Object Detection
    Chen, Chaofan
    Yang, Xiaoshan
    Zhang, Jinpeng
    Dong, Bo
    Xu, Changsheng
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 1092 - 1107
  • [6] Accelerating deep reinforcement learning via knowledge-guided policy network
    Yu, Yuanqiang
    Zhang, Peng
    Zhao, Kai
    Zheng, Yan
    Hao, Jianye
    [J]. AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2023, 37 (01)
  • [7] Knowledge-guided deep learning models of drug toxicity improve interpretation
    Hao, Yun
    Romano, Joseph D.
    Moore, Jason H.
    [J]. PATTERNS, 2022, 3 (09):
  • [8] Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation
    Ning, Guanghan
    Zhang, Zhi
    He, Zhiquan
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 20 (05) : 1246 - 1259
  • [9] Accelerating deep reinforcement learning via knowledge-guided policy network
    Yuanqiang Yu
    Peng Zhang
    Kai Zhao
    Yan Zheng
    Jianye Hao
    [J]. Autonomous Agents and Multi-Agent Systems, 2023, 37
  • [10] GeFuNet: A knowledge-guided deep network for the infrared and visible image fusion
    Su, Weijian
    Huang, Yongdong
    Li, Qiufu
    Zuo, Fengyuan
    [J]. INFRARED PHYSICS & TECHNOLOGY, 2022, 127