LAMP

Category: Publications

  • Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning

    Grzegorz Rypeść, Sebastian Cygert, Tomasz Trzciński, Bartłomiej Twardowski Read Full Paper → Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data. Existing state-of-the-art methods represent classes as Gaussian distributions in the feature extractor’s latent space, enabling Bayes classification or training the classifier by replaying pseudo […]

  • Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis

    Taihang Hu, Linxuan Li, Joost van de Weijer, Hongcheng Gao, Fahad Shahbaz Khan, Jian Yang, Ming-Ming Cheng, Kai Wang, Yaxing Wang Read Full Paper → Although text-to-image (T2I) models exhibit remarkable generation capabilities, they frequently fail to accurately bind semantically related objects or attributes in the input prompts; a challenge termed semantic binding. Previous approaches either involve intensive fine-tuning of the entire T2I […]

  • Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference

    Senmao Li, Taihang Hu, Joost van de Weijer, Fahad Shahbaz Khan, Tao Liu, Linxuan Li, Shiqi Yang, Yaxing Wang, Ming-Ming Cheng, Jian Yang Read Full Paper → One of the main drawback of diffusion models is the slow inference time for image generation. Among the most successful approaches to addressing this problem are distillation methods. However, these methods require considerable computational resources. In this […]

  • Exemplar-free Continual Representation Learning via Learnable Drift Compensation

    Alex Gomez-Villa, Dipam Goswami, Kai Wang, Andrew D. Bagdanov, Bartlomiej Twardowski, Joost van de Weijer Read Full Paper → Exemplar-free class-incremental learning using a backbone trained from scratch and starting from a small first task presents a significant challenge for continual representation learning. Prototype-based approaches, when continually updated, face the critical issue of semantic drift due to which the old […]

  • ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement

    Muhammad Atif Butt, Kai Wang, Javier Vazquez-Corral, Joost van de Weijer Read Full Paper → Text-to-Image (T2I) generation has made significant advancements with the advent of diffusion models. These models exhibit remarkable abilities to produce images based on textual prompts. Current T2I models allow users to specify object colors using linguistic color names. However, these labels encompass broad […]

  • Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models

    Claudio Rota, Marco Buzzelli, Joost van de Weijer Read Full Paper → In this paper, we address the problem of enhancing perceptual quality in video super-resolution (VSR) using Diffusion Models (DMs) while ensuring temporal consistency among frames. We present StableVSR, a VSR method based on DMs that can significantly enhance the perceptual quality of upscaled videos by […]

  • MagMax: Leveraging Model Merging for Seamless Continual Learning

    Daniel Marczak, Bartłomiej Twardowski, Tomasz Trzciński, Sebastian Cygert Read Full Paper → This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge. Distinct from traditional continual learning methods that aim to reduce forgetting during task training, MagMax combines sequential […]

  • Revisiting Supervision for Continual Representation Learning

    Daniel Marczak, Sebastian Cygert, Tomasz Trzciński, Bartłomiej Twardowski Read Full Paper → In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use of the vast amounts of unlabeled data. Recent studies […]

  • Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery

    Grzegorz Rypeść, Daniel Marczak, Sebastian Cygert, Tomasz Trzciński, Bartłomiej Twardowski Read Full Paper → Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to prevent forgetting the old knowledge. However, this strategy restricts the model’s ability to adapt and effectively distinguish new categories. To address […]

  • Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

    Dipam Goswami, Albin Soutif-Cormerais, Yuyang Liu, Sandesh Kamath, Bartlomiej Twardowski, Joost van de Weijer Read Full Paper → Continual learning methods are known to suffer from catastrophic forgetting a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore to reduce potential drift in the feature extractor […]