Skip to Main content Skip to Navigation
New interface
Conference papers

Self-supervised continual learning for object recognition in image sequences

Ruiqi Dai 1 Mathieu Lefort 2 Frédéric Armetta 2 Mathieu Guillermin 3 Stefan Duffner 1 
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 SyCoSMA - Systèmes Cognitifs et Systèmes Multi-Agents
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : The autonomous learning of different objects in images, with a continual and unsupervised context, relies on detecting unknown objects and recognizing known ones based on the learned visual representation. Novelty detection is challenging because of the internal representation drifts of known objects not been seen for a long time. Most existing approaches either perform offline unsupervised learning on a large dataset, or continual supervised learning. Nevertheless, very few existing approaches propose unsupervised continual learning for object recognition. In this paper, we propose a new neural network-based approach for continually learning representations of objects from image sequences, that is able to autonomously detect novel objects and to recognize previously learned ones during training. It is based on a statistical test, performed on internal representations, adapted to counterbalance the concept drift, without storing any image. Experimental results show that our approach outperforms the state of the art on MNIST and Fashion-MNIST datasets. In particular, our approach avoids to over-segment the distribution of clusters, which artificially increases traditional indicators such as clustering accuracy.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03465149
Contributor : Stefan Duffner Connect in order to contact the contributor
Submitted on : Friday, December 3, 2021 - 4:43:04 PM
Last modification on : Friday, September 30, 2022 - 11:34:16 AM
Long-term archiving on: : Friday, March 4, 2022 - 7:27:47 PM

File

ICONIP_final_submission.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03465149, version 1

Citation

Ruiqi Dai, Mathieu Lefort, Frédéric Armetta, Mathieu Guillermin, Stefan Duffner. Self-supervised continual learning for object recognition in image sequences. International Conference on Neural Information Processing (ICONIP), Dec 2021, Bali, Indonesia. ⟨hal-03465149⟩

Share

Metrics

Record views

72

Files downloads

127