9 citations · 19 across the 19 of their papers we have counts for
19 papers
Adapt & Align: Continual Learning with Generative Models Latent Space Alignment
Kamil Deja, Bartosz Cywiński, Jan Rybarczyk +1
In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from ab…
CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation
Monika Wysoczańska, Oriane Siméoni, Michaël Ramamonjisoa +3
The popular CLIP model displays impressive zero-shot capabilities thanks to its seamless interaction with arbitrary text prompts. However, its lack of spatial awareness makes it un…
On consequences of finetuning on data with highly discriminative features
Wojciech Masarczyk, Tomasz Trzciński, Mateusz Ostaszewski
In the era of transfer learning, training neural networks from scratch is becoming obsolete. Transfer learning leverages prior knowledge for new tasks, conserving computational res…
Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
Jan Dubiński, Stanisław Pawlak, Franziska Boenisch +2
Machine Learning as a Service (MLaaS) APIs provide ready-to-use and high-utility encoders that generate vector representations for given inputs. Since these encoders are very costl…
Revisiting Supervision for Continual Representation Learning
Daniel Marczak, Sebastian Cygert, Tomasz Trzciński +1
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 in…
Bayesian Flow Networks in Continual Learning
Mateusz Pyla, Kamil Deja, Bartłomiej Twardowski +1
Bayesian Flow Networks (BFNs) has been recently proposed as one of the most promising direction to universal generative modelling, having ability to learn any of the data type. The…
Looking through the past: better knowledge retention for generative replay in continual learning
Valeriya Khan, Sebastian Cygert, Kamil Deja +2
In this work, we improve the generative replay in a continual learning setting to perform well on challenging scenarios. Current generative rehearsal methods are usually benchmarke…
CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free
Monika Wysoczańska, Michaël Ramamonjisoa, Tomasz Trzciński +1
The emergence of CLIP has opened the way for open-world image perception. The zero-shot classification capabilities of the model are impressive but are harder to use for dense task…
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…
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
Grzegorz Rypeść, Daniel Marczak, Sebastian Cygert +2
Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend…
Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN
Jan Dubiński, Kamil Deja, Sandro Wenzel +2
Currently, over half of the computing power at CERN GRID is used to run High Energy Physics simulations. The recent updates at the Large Hadron Collider (LHC) create the need for d…
Towards More Realistic Membership Inference Attacks on Large Diffusion Models
Jan Dubiński, Antoni Kowalczuk, Stanisław Pawlak +3
Generative diffusion models, including Stable Diffusion and Midjourney, can generate visually appealing, diverse, and high-resolution images for various applications. These models…
The Tunnel Effect: Building Data Representations in Deep Neural Networks
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani +3
Deep neural networks are widely known for their remarkable effectiveness across various tasks, with the consensus that deeper networks implicitly learn more complex data representa…
Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?
Monika Wysoczańska, Tom Monnier, Tomasz Trzciński +1
Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work ai…
Emergency action termination for immediate reaction in hierarchical reinforcement learning
Michał Bortkiewicz, Jakub Łyskawa, Paweł Wawrzyński +3
Hierarchical decomposition of control is unavoidable in large dynamical systems. In reinforcement learning (RL), it is usually solved with subgoals defined at higher policy levels…
Progressive Latent Replay for efficient Generative Rehearsal
Stanisław Pawlak, Filip Szatkowski, Michał Bortkiewicz +2
We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network. While replay strategies mitigate the effects of catastrop…
Selectively increasing the diversity of GAN-generated samples
Jan Dubiński, Kamil Deja, Sandro Wenzel +2
Generative Adversarial Networks (GANs) are powerful models able to synthesize data samples closely resembling the distribution of real data, yet the diversity of those generated sa…
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
Kamil Deja, Anna Kuzina, Tomasz Trzciński +1
Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art performance in generative modeling. Their main strength comes from their unique setup in which a model (the ba…
On robustness of generative representations against catastrophic forgetting
Wojciech Masarczyk, Kamil Deja, Tomasz Trzciński
Catastrophic forgetting of previously learned knowledge while learning new tasks is a widely observed limitation of contemporary neural networks. Although many continual learning m…