Becoming the expert - interactive multi-class machine teaching
By Edward Johns, Oisin Mac Aodha, Gabriel J. Brostow. 2015
76 citations recorded by the source corpus.
Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching images is required. To learn categories more quickly, people should see important and representative images first, followed by less important images later - or not at all. However, image-importance is individual-specific, i.e. a teaching image is important to a student if it changes their overall ability to discriminate between classes. Further, students keep learning, so while image-importance depends on their current knowledge, it also varies with time. In this work we propose an Interactive Machine Teaching algorithm that enables a computer to teach challenging visual concepts to a human. Our adaptive algorithm chooses, online, which labeled images from a teaching set should be shown to the student as they learn. We show that a teaching strategy that probabilistically models the student's ability and progress, based on their correct and incorrect answers, produces better `experts'. We present results using real human participants across several varied and challenging real-world datasets.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Stacking with Auxiliary Features for Visual Question Answering (2018, background): “There are several advantages of having AI systems that can generate explanations that support their predictions (Johns et al., 2015; Agrawal et al., 2016).”
- The iNaturalist Challenge 2017 Dataset (2017, background): “Finally, we intend to explore the application of iNat2017 to low-shot learning [9], generative models [7, 29], and the teaching of fine-grained visual categories to humans [33, 12].”
- Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning (2018, background): “A successful FGVC model should be able to discriminate categories with subtle differences, which presents formidable challenges for the model design yet also provides insights to a wide range of applications such as rich image captioning [3], image generation [5], and machine teaching [27, 37].”
- The iNaturalist Species Classification and Detection Dataset (2017, background): “Finally, we expect this dataset to be useful in studying how to teach fine-grained visual categories to humans [34, 15], and plan to experiment with models of human learning.”
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization (2016, background): “chess or Go [39]), the goal of explanations is in machine teaching [20] – i.”
- Pairwise Decomposition of Image Sequences for Active Multi-view Recognition (2016, background): “Recently, the introduction of the ModelNet dataset of 3D CAD meshes [39] provided data of sufficient magnitude for training deep networks with images covering the full sphere of viewpoints over an object, enabling view synthesis without the need for laborious manual labelling of each image [16].”
- Crowdsourcing in Computer Vision (2016, unknown): “Johns et al. [2015] flip this framework around, by employing active learning to enable the system to teach a human user about difficult visual concepts. Their system selects which image examples to show to the human student, and monitors the student’s learning progress and ability, much like an acti”
- Human-in-the-loop machine learning: a state of the art (2022, background): “In fact, since the term “Machine Teaching” is such an ordinary combination of words, some of the early uses of the term that can be found refer precisely to machines teaching humans [e.g., Weimer (2010) or Johns et al. (2015)].”