Abstract
In the last few years deep neural networks has significantly improved the state-of-the-art of robotic vision. However, they are mainly trained to recognize only the categories provided in the training set (closed world assumption), being ill equipped to operate in the real world, where new unknown objects may appear over time. In this work, we investigate the open world recognition (OWR) problem that presents two challenges: (i) learn new concepts over time (incremental learning) and (ii) discern between known and unknown categories (open set recognition). Current state-of-the-art OWR methods address incremental learning by employing a knowledge distillation loss. It forces the model to keep the same predictions across training steps, in order to maintain the acquired knowledge. This behaviour may induce the model in mimicking uncertain predictions, preventing it from reaching an optimal representation on the new classes. To overcome this limitation, we propose the Poly loss that penalizes less the changes in the predictions for uncertain samples, while forcing the same output on confident ones. Moreover, we introduce a forget constraint relaxation strategy that allows the model to obtain a better representation of new classes by randomly zeroing the contribution of some old classes from the distillation loss. Finally, while current methods rely on metric learning to detect unknown samples, we propose a new rejection strategy that sidesteps it and directly uses the model classifier to estimate if a sample is known or not. Experiments on three datasets demonstrate that our method outperforms the state of the art.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Belouadah, E., Popescu, A.: Il2m: class incremental learning with dual memory. In: ICCV-19
Bendale, A., Boult, T.: Towards open world recognition. In: CVPR-15
Camoriano, R., Pasquale, G., Ciliberto, C., Natale, L., Rosasco, L., Metta, G.: Incremental robot learning of new objects with fixed update time. In: ICRA-17
Camoriano, R., Traversaro, S., Rosasco, L., Metta, G., Nori, F.: Incremental semiparametric inverse dynamics learning. In: ICRA-16
Castro, F.M., Marín-Jiménez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 241–257. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_15
Cermelli, F., Mancini, M., Bulò, S.R., Ricci, E., Caputo, B.: Modeling the background for incremental learning in semantic segmentation. In: CVPR-20
De Lange, M., et al.: Continual learning: A comparative study on how to defy forgetting in classification tasks. 2(6) (2019). arXiv preprint arXiv:1909.08383
De Rosa, R., Mensink, T., Caputo, B.: Online open world recognition. arXiv:1604.02275 (2016)
Della Santina, C., et al.: Learning from humans how to grasp: a data-driven architecture for autonomous grasping with anthropomorphic soft hands. RA-L-19
Douillard, A., Chen, Y., Dapogny, A., Cord, M.: Plop: learning without forgetting for continual semantic segmentation. In: CVPR-21
Douillard, A., Cord, M., Ollion, C., Robert, T., Valle, E.: PODNet: pooled outputs distillation for small-tasks incremental learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 86–102. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_6
Fontanel, D., Cermelli, F., Mancini, M., Caputo, B.: On the challenges of open world recognition under shifting visual domains. RA-L-20 6(2)
Fontanel, D., Cermelli, F., Mancini, M., Rota Buló, S., Ricci, E., Caputo, B.: Boosting deep open world recognition by clustering. RA-L 5(4), 5985–5992 (2020)
Fragoso, V., Sen, P., Rodriguez, S., Turk, M.: EVSAC: accelerating hypotheses generation by modeling matching scores with extreme value theory. In: ICCV-13
French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cognit. Sci. 3(4) (1999)
Guerriero, S., Caputo, B., Mensink, T.: Deep nearest class mean classifiers. In: ICLR-WS-18
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR-16
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv 1503.02531 (2015)
Hu, X., Tang, K., Miao, C., Hua, X.S., Zhang, H.: Distilling causal effect of data in class-incremental learning. In: CVPR-21
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)
Kumar, V.R., et al.: Omnidet: surround view cameras based multi-task visual perception network for autonomous driving. RA-L-21 6(2)
Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view RGB-d object dataset. In: ICRA-11
Lesort, T., Lomonaco, V., Stoian, A., Maltoni, D., Filliat, D., Díaz-Rodríguez, N.: Continual learning for robotics: definition, framework, learning strategies, opportunities and challenges. Inf. Fusion 58, 52–68 (2020)
Li, Z., Hoiem, D.: Learning without forgetting. T-PAMI-17
Liu, X., et al.: Generative feature replay for class-incremental learning. In: CVPR-20
Liu, Y., Su, Y., Liu, A.A., Schiele, B., Sun, Q.: Mnemonics training: multi-class incremental learning without forgetting. In: CVPR-20
Lomonaco, V., Maltoni, D.: Core50: a new dataset and benchmark for continuous object recognition. In: CoRL-17
Mancini, M., Karaoguz, H., Ricci, E., Jensfelt, P., Caputo, B.: Knowledge is never enough: towards web aided deep open world recognition. In: ICRA-19
Mancini, M., Costante, G., Valigi, P., Ciarfuglia, T.A., Delmerico, J., Scaramuzza, D.: Toward domain independence for learning-based monocular depth estimation. RA-L-17 2(3)
McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol. 24, pp. 109–165. Elsevier (1989)
Mensink, T., Verbeek, J., Perronnin, F., Csurka, G.: Metric learning for large scale image classification: generalizing to new classes at near-zero cost. In: ECCV-12
Michieli, U., Zanuttigh, P.: Continual semantic segmentation via repulsion-attraction of sparse and disentangled latent representations. In: CVPR-21
Michieli, U., Zanuttigh, P.: Knowledge distillation for incremental learning in semantic segmentation. CVIU-21 205
Peng, C., Zhao, K., Lovell, B.C.: Faster ilod: incremental learning for object detectors based on faster RCNN. Pattern Recognit. Lett. 140 (2020)
Perez-Rua, J.M., Zhu, X., Hospedales, T.M., Xiang, T.: Incremental few-shot object detection. In: CVPR-20
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: CVPR-17
Saito, N., Ogata, T., Funabashi, S., Mori, H., Sugano, S.: How to select and use tools? Active perception of target objects using multimodal deep learning. RA-L-21 6(2)
Scheirer, W.J., De Rezende Rocha, A., Sapkota, A., Boult, T.E.: Toward open set recognition. T-PAMI-12 35(7)
Schwarz, M., Milan, A., Periyasamy, A.S., Behnke, S.: RGB-D object detection and semantic segmentation for autonomous manipulation in clutter. IJRR-18 37(4–5)
Shmelkov, K., Schmid, C., Alahari, K.: Incremental learning of object detectors without catastrophic forgetting. In: ICCV-17
Sünderhauf, N., et al.: The limits and potentials of deep learning for robotics. IJRR-18 37(4–5)
Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., Gong, Y.: Few-shot class-incremental learning. In: CVPR-20
Valipour, S., Perez, C., Jagersand, M.: Incremental learning for robot perception through HRI. In: IROS-17
Wu, Y., et al.: Large scale incremental learning. In: CVPR-19
Zhao, B., Xiao, X., Gan, G., Zhang, B., Xia, S.T.: Maintaining discrimination and fairness in class incremental learning. In: CVPR-20
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fontanel, D., Cermelli, F., Geraci, A., Musarra, M., Tarantino, M., Caputo, B. (2022). Relaxing the Forget Constraints in Open World Recognition. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds) Image Analysis and Processing – ICIAP 2022. ICIAP 2022. Lecture Notes in Computer Science, vol 13231. Springer, Cham. https://doi.org/10.1007/978-3-031-06427-2_62
Download citation
DOI: https://doi.org/10.1007/978-3-031-06427-2_62
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06426-5
Online ISBN: 978-3-031-06427-2
eBook Packages: Computer ScienceComputer Science (R0)