Incremental Object Learning From Contiguous Views

By Stefan Stojanov, Samarth Mishra, Ngoc Anh Thai, N. Dhanda, Ahmad Humayun, Chen Yu, Linda B. Smith, James M. Rehg. 2019

44 citations recorded by the source corpus.

In this work, we present CRIB (Continual Recognition Inspired by Babies), a synthetic incremental object learning environment that can produce data that models visual imagery produced by object exploration in early infancy. CRIB is coupled with a new 3D object dataset, Toys-200, that contains 200 unique toy-like object instances, and is also compatible with existing 3D datasets. Through extensive empirical evaluation of state-of-the-art incremental learning algorithms, we find the novel empirical result that repetition can significantly ameliorate the effects of catastrophic forgetting. Furthermore, we find that in certain cases repetition allows for performance approaching that of batch learning algorithms. Finally, we propose an unsupervised incremental learning task with intriguing baseline results.

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Recent Advances of Continual Learning in Computer Vision: An Overview (2021, positive): “They proposed a bottom-up pruning method to build a sparse subnetwork for each task, which is lightweight but can still achieve comparable or even better performance than the original dense model.”
Continuous Coordination As a Realistic Scenario for Lifelong Learning (2021, neutral): “There have been efforts to address this by proposing more challenging benchmarks like CORe50 (Lomonaco & Mal-toni, 2017), CRIB (Stojanov et al., 2019), OpenLoris (Shi et al., 2020), Stream51 (Roady et al., 2020), and IIRC (Ab-delsalam et al., 2020).”
Unsupervised Class-Incremental Learning Through Confusion (2021, methodology): “Recently, Stojanov et al. (2019) introduced a novel unsupervised class-incremental learning problem motivated by the desire to simulate how children’s play behaviors support their ability to learn object models (IOLfCV).”
Sequential Mastery of Multiple Visual Tasks: Networks Naturally Learn to Learn and Forget to Forget (2019, background): “Stojanov et al. [26] oﬀer an incremental learning environment inspired by development, allowing for repeated encounters with the same objects from diﬀerent perspectives.”
Unsupervised Continual Learning Via Pseudo Labels (2021, background): “[46] proposed an unsupervised object learning environment to learn a sequence of single-class exposures containing sets of frames with contiguous viewpoints.”
Continual Learning in Linear Classification on Separable Data (2023, background): “Several recent papers have observed empirically that task repetitions mitigate catastrophic forgetting in continual learning (Stojanov et al., 2019; Cossu et al., 2022), even when training is performed with vanilla SGD, without any forgetting-preventing method (Lesort et al.”