Tell me what this is: Few-Shot Incremental Object Learning by a Robot

By Ali Ayub, Alan R. Wagner. 2020

34 citations recorded by the source corpus.

For many applications, robots will need to be incrementally trained to recognize the specific objects needed for an application. This paper presents a practical system for incrementally training a robot to recognize different object categories using only a small set of visual examples provided by a human. The paper uses a recently developed state-of-the-art method for few-shot incremental learning of objects. After learning the object classes incrementally, the robot performs a table cleaning task organizing objects into categories specified by the human. We also demonstrate the system’s ability to learn arrangements of objects and predict missing or incorrectly placed objects. Experimental evaluations demonstrate that our approach achieves nearly the same performance as a system trained with all examples at one time (batch training), which constitutes a theoretical upper bound.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

1. Ali Ayub
2. C. Fendley
3. Alan R. Wagner
4. Xin Ning
5. Weijun Li
6. Prayag Tiwari
7. Hang Ran
8. Lusi Li

In Computer Vision and Pattern Recognition

1. Ali Ayub
2. Alan R. Wagner
3. C. Fendley
4. Xin Ning
5. Weijun Li
6. Prayag Tiwari
7. Hang Ran
8. Lusi Li

Citations in the corpus

• Few-Shot Continual Active Learning by a Robot (2022, background): “In contrast, robots operating in real-world environments mostly have to learn from supervision provided by their users [11, 5, 12].”
• Online Learning of Objects through Curiosity-Driven Active Learning (2021, methodology): “We use our recently proposed state-of-the-art approach to continual learning termed Centroid-Based Concept Learning (CBCL) [15], [19], [20] which has been further extended to use Pseudorehearsal (CBCL-PR) [21].”
• A Survey on Few-Shot Class-Incremental Learning (2023, background): “Previous studies have explored the use of a small set of visual examples to incrementally train robots and enhance their recognition capabilities (Ayub and Wagner, 2020b).”
• What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper (2020, unknown): “CBCL-PR [3] is a revised version of CBCL [4] which is a recently developed state-of-the-art method for incremental learning [4,7] and RGB-D indoor scene classification [2].”
• F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning (2021, background): “To the best of our knowledge, CBCL [10], [21], [22], [23] is currently the only approach that tackles the FSIL problem.”
• Centroid Based Concept Learning for RGB-D Indoor Scene Classification (2019, background): “Furthermore, it can applied to other classification tasks, such as incremental learning of objects from object-centric RGB images [2, 3, 4].”