When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment without relying on human intervention, i.e., a fully self-supervised approach. In our setting, an agent initially learns to explore the environment using a pre-trained off-the-shelf detector to locate objects and associate pseudo-labels. By assuming that pseudo-labels for the same object must be consistent across different views, we learn the exploration policy Look Around to mine hard samples, and we devise a novel mechanism called Disagreement Reconciliation for producing refined pseudo-labels from the consensus among observations. We implement a unified benchmark of the current state-of-the-art and compare our approach with pre-existing exploration policies and perception mechanisms. Our method is shown to outperform existing approaches, improving the object detector by 6.2% in a simulated scenario, a 3.59% advancement over other state-of-the-art methods, and by 9.97% in the real robotic test without relying on ground-truth. Code for the proposed approach and baselines are available at https://iit-pavis.github.io/Look_Around_And_Learn/.
Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation
Sun Yat-Sen University(中山大学);Guangdong Province Key Laboratory of Information Security Technology(广东省信息安全技术重点实验室);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education(教育部机器智能与先进计算重点实验室)
Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale
Shanghai AI Laboratory(上海人工智能实验室);UNC Chapel Hill(北卡罗来纳大学教堂山分校);Fudan University(复旦大学);The University of Adelaide(阿德莱德大学);Nanjing University(南京大学);Shanghai Jiaotong University(上海交通大学)
Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所基础模型研究中心);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);National University of Singapore(新加坡国立大学);Wuhan AI Research(武汉人工智能研究所);Tsinghua University(清华大学)
SelfAI: A self-directed framework for long-horizon scientific discovery
University of Electronic Science and Technology of China(电子科技大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Xian Jiaotong University(西安交通大学);Yale University(耶鲁大学);Washington University in St. Louis(圣路易斯华盛顿大学);Monash University(莫纳什大学)
Curiosity-driven Exploration by Self-supervised Prediction
University of California, Berkeley(加州大学伯克利分校)
在许多现实世界的场景中,代理的外在奖励非常稀少,或者完全不存在。在这种情况下,好奇心可以作为一种内在的奖励信号,使智能体能够探索其环境并学习可能在其以后的生活中有用的技能。我们制定好奇心作为错误的智能体的能力,预测自己的行动的后果,在视觉特征空间学习的自监督逆动力学模型。我们的公式可以扩展到像图像这样的高维连续状态空间,绕过了直接预测像素的困难,并且,关键的是,忽略了环境中不能影响代理的方面。在VizDoom和Super Mario Bros.Three广泛的设置进行了研究:1)稀疏的外部奖励,好奇心允许与环境的交互少得多,以达到目标; 2)探索没有外部奖励,好奇心推动代理更有效地探索;以及3)推广到看不见的场景(例如,相同游戏的新级别),其中从早期经验获得的知识帮助代理比从头开始更快地探索新的地方。演示视频和代码可在www.example.com获得