arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.05660cs.CVcs.AIcs.HC
收藏

用于深度学习解释的交互式分类

Interactive Classification for Deep Learning Interpretation

Georgia Institute of Technology(佐治亚理工学院)

Ángel Alexander Cabrera, Fred Hohman, Jason Lin, Duen Horng Chau

摘要:

我们提出了一个交互式系统,使用户能够操纵图像,以探索深度学习图像分类器的鲁棒性和灵敏度。使用现代网络技术运行浏览器内推理,用户可以使用修复算法删除图像特征,并实时的获得新的分类,这使他们能够通过实验性地修改图像并观察模型的反应来提出各种“如果”的问题。我们的系统允许用户比较和对比人类和机器学习模型用于分类的图像区域,揭示了广泛的令人惊讶的结果,从壮观的失败(例如,“水瓶”图像在移除人时变成“音乐会”)到令人印象深刻的弹性(例如,即使没有手套或底座,“棒球运动员”图像也保持正确分类)。我们在2018年计算机视觉和模式识别(CVPR)会议上展示了我们的系统,供观众现场试用。我们的系统在https://github.com/poloclub/interactive-classification上开源。视频演示可在https://youtu.be/llub5GcOF6w上获得。

英文摘要:

We present an interactive system enabling users to manipulate images to explore the robustness and sensitivity of deep learning image classifiers. Using modern web technologies to run in-browser inference, users can remove image features using inpainting algorithms and obtain new classifications in real time, which allows them to ask a variety of "what if" questions by experimentally modifying images and seeing how the model reacts. Our system allows users to compare and contrast what image regions humans and machine learning models use for classification, revealing a wide range of surprising results ranging from spectacular failures (e.g., a "water bottle" image becomes a "concert" when removing a person) to impressive resilience (e.g., a "baseball player" image remains correctly classified even without a glove or base). We demonstrate our system at The 2018 Conference on Computer Vision and Pattern Recognition (CVPR) for the audience to try it live. Our system is open-sourced at https://github.com/poloclub/interactive-classification. A video demo is available at https://youtu.be/llub5GcOF6w.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑