Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks. However, the agent's decision-making process is generally not transparent. The lack of interpretability hinders the applicability of RL in safety-critical scenarios. While several methods have attempted to interpret vision-based RL, most come without detailed explanation for the agent's behavior. In this paper, we propose a self-supervised interpretable framework, which can discover interpretable features to enable easy understanding of RL agents even for non-experts. Specifically, a self-supervised interpretable network (SSINet) is employed to produce fine-grained attention masks for highlighting task-relevant information, which constitutes most evidence for the agent's decisions. We verify and evaluate our method on several Atari 2600 games as well as Duckietown, which is a challenging self-driving car simulator environment. The results show that our method renders empirical evidences about how the agent makes decisions and why the agent performs well or badly, especially when transferred to novel scenes. Overall, our method provides valuable insight into the internal decision-making process of vision-based RL. In addition, our method does not use any external labelled data, and thus demonstrates the possibility to learn high-quality mask through a self-supervised manner, which may shed light on new paradigms for label-free vision learning such as self-supervised segmentation and detection.
DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation
Princeton University(普林斯顿大学);The Chinese University of Hong Kong(香港中文大学);Microsoft(微软);UCLA(加州大学洛杉矶分校);Beth Israel Deaconess Medical Center(贝斯以色列女执事医疗中心);Microsoft Research New England(微软新英格兰研究院);VSCO
Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences(中国科学院脑科学与智能技术卓越创新中心);University of California at Merced(加州大学默塞德分校)
Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)
Worcester Polytechnic Institute(伍斯特理工学院)
为了学习可区分的模式,最近的大多数车辆重新识别(ReID)工作都在努力重新开发官方基准以提供各种监督,这需要大量的人力。在本文中,我们寻求实现类似的目标,但不涉及更多的人力。为此,我们引入了一个新的框架,它成功地编码几何局部特征和全局表示来区分车辆实例,仅通过官方ID标签的监督进行优化。具体来说,鉴于我们的洞察力,ReID中的对象共享相似的几何特征,我们建议借用自监督表示学习,以促进几何特征发现。为了浓缩这些特征,我们引入了一个可解释的注意力模块,其核心是局部最大值聚合而不是全自动学习,其机制是完全可以理解的,其响应图是物理上合理的。据我们所知,我们是第一个执行自监督学习来发现几何特征的人。我们对三个最流行的车辆ReID数据集进行了全面的实验,即,VeRi-776、CityFlow-ReID和VehicleID。我们报告我们的国家的最先进的(SOTA)的性能和有前途的可视化结果。我们还展示了我们的方法在其他ReID相关任务上的出色可扩展性,即,个人ReID和多目标多摄像头(MTMC)车辆跟踪。该代码可在https://github.com/ ming 1993 li/Self-supervised-Geometric上获得。
ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency
Sun Yat-sen University(中山大学);University of Technology Sydney(悉尼科技大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);University of Oxford(牛津大学);MBZUAI(穆罕默德·本·扎耶德人工智能大学)
IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);The Chinese University of Hong Kong(香港中文大学)
Uncertainty-Supervised Interpretable and Robust Evidential Segmentation
School of Data Science, Fudan University, Shanghai, China(复旦大学数据科学学院);Institute of Science and Technology for Brain-inspired intelligence, Fudan University, Shanghai, China(复旦大学脑启发式智能技术研究所);Nuffield Department of Population Health, University of Oxford, Oxford, UK(牛津大学人口健康牛津部门)
Semi-Supervised Multi-Task Learning for Interpretable Quality As- sessment of Fundus Images
UNCPBA, CONICET, Yatiris Group, Pladema Institute(UNCPBA、CONICET、Yatiris集团、Pladema研究所);Servicio de Oftalmología, Hospital de Alta Complejidad en Red ``El Cruce'' Dr. Néstor Carlos Kirchner(眼科服务,高级复杂性网络‘El Cruce’医院Dr. Néstor Carlos Kirchner)