58 citations · 163 across the 41 of their papers we have counts for
21 papers · 1 filter
Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion Models
Jonas Kneifl, Jakub Skalski, Bartłomiej Twardowski +1
Video generation models produce strikingly realistic sequences and are increasingly proposed as world models, yet recent benchmarks reveal pronounced deficits in their physical rea…
Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models
Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen +4
Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unl…
Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval
Alicja Dobrzeniecka, Filip Szatkowski, Sebastian Cygert +2
While retrieval is a core function of vision-language models, continually updating these models for retrieval tasks remains critically underexplored. Existing work often approaches…
Project and Mix: Task-Semantic Prototypes for Few-Shot Image Classification
Dipam Goswami, Simone Magistri, Gido M. van de Ven +4
Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that exploiting few-shot image embedd…
IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
Simone Magistri, Dipam Goswami, Marco Mistretta +3
Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individual modality encoders are applie…
Accurate and Efficient Low-Rank Model Merging in Core Space
Aniello Panariello, Daniel Marczak, Simone Magistri +5
In this paper, we address the challenges associated with merging low-rank adaptations of large neural networks. With the rise of parameter-efficient adaptation techniques, such as…
The Art of Deception: Color Visual Illusions and Diffusion Models
Alex Gomez-Villa, Kai Wang, Alejandro C. Parraga +4
Visual illusions in humans arise when interpreting out-of-distribution stimuli: if the observer is adapted to certain statistics, perception of outliers deviates from reality. Rece…
Exemplar-free Continual Representation Learning via Learnable Drift Compensation
Alex Gomez-Villa, Dipam Goswami, Kai Wang +3
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 le…
Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
Dipam Goswami, Albin Soutif--Cormerais, Yuyang Liu +3
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 t…
Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
Dipam Goswami, Bartłomiej Twardowski, Joost van de Weijer
Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from very few data (5 samples) without forgetting the previously learned classes. Recent works in…
Technical Report for ICCV 2023 Visual Continual Learning Challenge: Continuous Test-time Adaptation for Semantic Segmentation
Damian Sójka, Yuyang Liu, Dipam Goswami +3
The goal of the challenge is to develop a test-time adaptation (TTA) method, which could adapt the model to gradually changing domains in video sequences for semantic segmentation…
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
Dipam Goswami, Yuyang Liu, Bartłomiej Twardowski +1
Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting.…
AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation
Damian Sójka, Sebastian Cygert, Bartłomiej Twardowski +1
Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods ar…
Augmentation-aware Self-supervised Learning with Conditioned Projector
Marcin Przewięźlikowski, Mateusz Pyla, Bartosz Zieliński +3
Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and M…
Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training
Simone Zini, Alex Gomez-Villa, Marco Buzzelli +3
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 ar…
Continually Learning Self-Supervised Representations with Projected Functional Regularization
Alex Gomez-Villa, Bartlomiej Twardowski, Lu Yu +2
Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches. However, these methods are unable t…
Reducing Label Effort: Self-Supervised meets Active Learning
Javad Zolfaghari Bengar, Joost van de Weijer, Bartlomiej Twardowski +1
Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to redu…
On Class Orderings for Incremental Learning
Marc Masana, Bartłomiej Twardowski, Joost van de Weijer
The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incre…
RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
Riccardo Del Chiaro, Bartłomiej Twardowski, Andrew D. Bagdanov +1
Research on continual learning has led to a variety of approaches to mitigating catastrophic forgetting in feed-forward classification networks. Until now surprisingly little atten…
Semantic Drift Compensation for Class-Incremental Learning
Lu Yu, Bartłomiej Twardowski, Xialei Liu +5
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a tim…
Orderless Recurrent Models for Multi-label Classification
Vacit Oguz Yazici, Abel Gonzalez-Garcia, Arnau Ramisa +2
Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered f…