Baptiste Wagner
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Baptiste Wagner has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Denis Pellerin
CNRS, Grenoble INP, GIPSA-Laboratory, Universit Grenoble Alpes, Grenoble, France
1 shared publication - Sylvain Huet
Grenoble INP, GIPSA-Lab, Univ. Grenoble Alpes, Grenoble, France
1 shared publication
Latest Publications
- Open Access
- 27 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 6067-6079
Studying Forgetting in Faster R-CNN for Online Object Detection: Analysis Scenarios, Localization in the Architecture, and Mitigation
Online Object Detection (OOD) requires learning new object categories from a stream of images, similar to an agent exploring new environments. In this context, the widely used Faster R-CNN (Region Convolutional Neural Network) architecture faces catastrophic forgetting: the acquisition of new knowledge leads to the loss of previously learned information. In this paper, we investigate the learning and forgetting mechanisms of the Faster R-CNN in OOD through three main contributions. First, we observe that the forgetting curves of the Faster R-CNN exhibit patterns similar to those described in human memory studies by Hermann Ebbinghaus: knowledge is lost exponentially over time and recall improves knowledge retention. Second, we present a new methodology for analysing the Faster R-CNN architecture and quantifying forgetting across the Faster R-CNN components. We show that forgetting is mainly localised in the Softmax classification layer. Finally, we propose a new training strategy for OOD called Configurable Recall (CR). CR performs recalls on old data using images stored in a memory buffer with variable frequency and recall length to ensure efficient learning. CR also masks the logits of old objects in the softmax classification layer to mitigate forgetting. We evaluate our strategy against state-of-the-art methods on three OOD benchmarks. We analyse the effectiveness of different recall types in mitigating forgetting and show that CR outperforms existing methods.
- 27 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 6067-6079
Open AccessStudying Forgetting in Faster R-CNN for Online Object Detection: Analysis Scenarios, Localization in the Architecture, and Mitigation
Online Object Detection (OOD) requires learning new object categories from a stream of images, similar to an agent exploring new environments. In this context, the widely used Faster R-CNN (Region Convolutional Neural Network) architecture faces catastrophic forgetting: the acquisition of new knowledge leads to the loss of previously learned information. In this paper, we investigate the learning and forgetting mechanisms of the Faster R-CNN in OOD through three main contributions. First, we observe that the forgetting curves of the Faster R-CNN exhibit patterns similar to those described in human memory studies by Hermann Ebbinghaus: knowledge is lost exponentially over time and recall improves knowledge retention. Second, we present a new methodology for analysing the Faster R-CNN architecture and quantifying forgetting across the Faster R-CNN components. We show that forgetting is mainly localised in the Softmax classification layer. Finally, we propose a new training strategy for OOD called Configurable Recall (CR). CR performs recalls on old data using images stored in a memory buffer with variable frequency and recall length to ensure efficient learning. CR also masks the logits of old objects in the softmax classification layer to mitigate forgetting. We evaluate our strategy against state-of-the-art methods on three OOD benchmarks. We analyse the effectiveness of different recall types in mitigating forgetting and show that CR outperforms existing methods.