Incremental Learning for Scene Analysis H/F à

Capijobnew
139848 Annonce(s)

Capijobnew

Incremental Learning for Scene Analysis H/F

Dpt / Région : Provence Alpes Côte d'Azur, 05, 06, 13, 83, 84, 04

Contrat :

Expérience : NC

Niveau d´étude : NC

Salaire : NC

Permis demandé : Permis NC

Niveau de qualification : NC

Position descriptionCategoryMathematics, information, scientific, software ContractInternship Job titleIncremental Learning for Scene Analysis H/F SubjectObjectives of the internship:- Analyze existing incremental learning for object detection and semantic segmentation methods and point their limitations.- Propose and develop an incremental learning method with severe memory and computational constraints.- Evaluate the developed method on public datasets (e.g. PASCAL VOC, MsCOCO).- Publication of results will be encouraged.Keywords: Object detection, semantic segmentation, deep learning, incremental learning, knowledge distillation. Contract duration (months)6 Job description ContextIncrementally adapting an existing object detection model to detect new unseen classes with severe memory and computational constraints is a critical capacity in real-word applications such as robotics, self-driving vehicles or video surveillance. However, while human beings can easily recognize new objects continuously without forgetting the old knowledge, deep learning models can suffer from ?catastrophic forgetting?. In fact, adding new classes without using the old training dataset can cause a big degradation of performance on the original set of classes.To overcome this issue, several methods use a memory buffer to save a set of the old dataset and re-use it to retrain the model with the new classes [1] or extend the model architecture by adding other detection heads. Others focus essentially on regularizing the training to minimize the discrepancy between responses for the old and the updated model [2]. The results of these methods are still limited compared to the models trained jointly with all the dataset. Recent methods identify instances of unknown objects as unknown and subsequently learn to recognize them when training data progressively arrive without retraining from scratch [3].While various studies are conducted on image classification and object detection, only few methods [4,5] focus on incremental learning for other scene analysis tasks like semantic segmentation. However, semantic segmentation is a key task that computer vision systems must face frequently in various applications. References[1] Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari (2017) Incremental Learning of Object Detectors without Catastrophic Forgetting, 2017 IEEE International Conference on Computer Vision (ICCV).[2] Shieh, J.-L.; Haq, Q.M.u.; Haq, M.A.; Karam, S.; Chondro, P.; Gao, D.-Q.; Ruan, S.-J (2020) Continual Learning Strategy in One-Stage Object Detection Framework Based on Experience Replay for Autonomous Driving Vehicle, Sensors 20, no. 23: 6777.[3] K. J. Joseph, Salman H. Khan, Fahad Shahbaz Khan, Vineeth N. Balasubramanian (2021) Towards Open World Object Detection, CVPR.[4] Umberto Michieli and Pietro Zanuttigh (2019) Incremental Learning Techniques for Semantic Segmentation, ICCV.[5] Umberto Michieli, Pietro Zanuttigh (2021) Knowledge Distillation for Incremental Learning in Semantic Segmentation, Computer Vision and Image Understanding (CVIU), Vol. 205. Applicant Profile Engineer, Master 2Required Skills:- Computer vision- Machine learning (deep learning)- Shape recognition- Python, C / C ++- Mastery of a deep learning framework (in particular Tensorflow or PyTorch)This internship opens the possibility of pursuing a thesis and R&D engineer in our laboratory.Position location SiteSaclay Job locationFrance, Ile-de-France, Essonne (91) Location PalaiseauCandidate criteria Prepared diploma Bac+5 - Master 2 Recommended trainingEngineer / Master 2 PhD opportunityOuiRequester Position start date01/03/2022

Crée en 1978 par Jean AYMAR

Présent en 8 pays

+ 10 0000 Colaborateurs

20 M de CA

Le Lorem Ipsum est simplement du faux texte employé dans la composition et la mise en page avant impression. Le Lorem Ipsum est le faux texte standard de l'imprimerie depuis les années 1500, quand un imprimeur anonyme assembla ensemble des morceaux de texte pour réaliser un livre spécimen de polices de texte. Il n'a pas fait que survivre cinq siècles, mais s'est aussi adapté à la bureautique informatique, sans que son contenu n'en soit modifié. Il a été popularisé dans les années 1960 grâce à la vente de feuilles Letraset contenant des passages du Lorem Ipsum, et, plus récemment, par son inclusion dans des applications de mise en page de texte, comme Aldus PageMaker.fsf