LAMP

Category: Publications

  • Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

    Liu Yuyang, Cong Yang, Goswami Dipam, Liu Xialei, Joost van de Weijer Read Full Paper → In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this […]

  • Density Map Distillation for Incremental Object Counting

    Chenshen Wu, Joost van de Weijer Read Full Paper → We investigate the problem of incremental learning for object counting, where a method must learn to count a variety of object classes from a sequence of datasets. A naïve approach to incremental object counting would suffer from catastrophic forgetting, where it would suffer from a dramatic […]

  • Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training

    Simone Zini, Alex Gomez-Villa, Marco Buzzelli, Bartłomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer Read Full Paper → Several recent works on self-supervised learning are trained by mapping different augmentations of the same image to the same feature representation. The data augmentations used are of crucial importance to the quality of learned feature representations. In this paper, we analyze […]

  • 3D-aware multi-class image-to-image translation with NeRFs

    Senmao Li, Joost van de Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang Read Full Paper → Recent advances in 3D-aware generative models (3D-aware GANs) combined with Neural Radiance Fields (NeRF) have achieved impressive results. However no prior works investigate 3D-aware GANs for 3D consistent multi-class image-to-image (3D-aware I2I) translation. Naively using 2D-I2I translation methods suffers from unrealistic […]

  • Endpoints Weight Fusion for Class Incremental Semantic Segmentation

    Jia-Wen Xiao, Chang-Bin Zhang, Jiekang Feng, Xialei Liu, Joost van de Weijer, Ming-Ming Cheng Read Full Paper → Class incremental semantic segmentation (CISS) focuses on alleviating catastrophic forgetting to improve discrimination. Previous work mainly exploit regularization (e.g., knowledge distillation) to maintain previous knowledge in the current model. However, distillation alone often yields limited gain to […]

  • MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains

    Yaxing Wang, Abel Gonzalez-Garcia, Chenshen Wu, Luis Herranz, Fahad Shahbaz Khan, Shangling Jui, Joost van de Weijer Read Full Paper → GANs largely increases the potential impact of generative models. Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple […]

  • Generative Multi-Label Zero-Shot Learning

    Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Joost van de Weijer Read Full Paper → Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention […]

  • Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation

    Shiqi Yang, Yaxing Wang, Kai Wang, Shangling Jui, Joost van de Weijer Read Full Paper → We propose a simple but effective source-free domain adaptation (SFDA) method. Treating SFDA as an unsupervised clustering problem and following the intuition that local neighbors in feature space should have more similar predictions than other features, we propose to optimize an objective of […]

  • Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation

    Dipam Goswami, René Schuster, Joost van de Weijer, Didier Stricker Read Full Paper → In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift. Although recent works focused on these issues, existing classifier initialization methods do not address the background shift problem and assign the same initialization weights […]

  • Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification

    Kai Wang, Chenshen Wu, Andy Bagdanov, Xialei Liu, Shiqi Yang, Shangling Jui, Joost van de Weijer Read Full Paper → Lifelong object re-identification incrementally learns from a stream of re-identification tasks. The objective is to learn a representation that can be applied to all tasks and that generalizes to previously unseen re-identification tasks. The main challenge is that at inference time […]