Centroid Based Concept Learning for RGB-D Indoor Scene Classification

By Ali Ayub, Alan R. Wagner. 2019

32 citations recorded by the source corpus.

This paper contributes a novel cognitively-inspired method for RGB-D indoor scene classification. High intra-class variance and low inter-class variance make indoor scene classification an extremely challenging task. To cope with this problem, we propose a clustering approach inspired by the concept learning model of the hippocampus and the neocortex, to generate clusters and centroids for different scene categories. Test images depicting different scenes are classified by using their distance to the closest centroids (concepts). Modeling of RGB-D scenes as centroids not only leads to state-of-the-art classification performance on benchmark datasets (SUN RGB-D and NYU Depth V2), but also offers a method for inspecting and interpreting the space of centroids. Inspection of the centroids generated by our approach on RGB-D datasets leads us to propose a method for merging conceptually similar categories, resulting in improved accuracy for all approaches.

Citations in the corpus

• EEC: Learning to Encode and Regenerate Images for Continual Learning (2021, methodology): “To avoid storing old class images, some approaches store features from the last fully-connected layer of the neural networks (Xiang et al., 2019; Hayes & Kanan, 2020; Ayub & Wagner, 2020b;d).”
• Storing Encoded Episodes as Concepts for Continual Learning (2020, methodology): “…episodes Ny for a class y is calculated as (whole number): Ny(new) = Ny(1− Kr Kt−1 ) (4) To reduce the encoded episodes to Ny(new) for class y, inspired by the memory integration process, we use an incremental clustering process similar to Agg-Var clustering proposed in (Ayub & Wagner, 2019; 2020).”
• 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].”
• What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper (2020, background): “A more detailed description of CBCL-PR can be found in [4,2,3]”
• 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.”