584 citations · 2.3k across the 78 of their papers we have counts for
78 papers · 1 filter
DiDE:Direct Injection with Color-Texture DEcoupling for 3D Stylization
Tao Wu, Alexandra Gomez-Villa, Senmao Li +3
Recent advances in rectified flow-based image-to-3D generative models have enabled high-fidelity 3D asset generation. Building on this, a growing line of work has exploited these s…
BTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D Generation
Junyu Li, Qiuyu Chen, Pengcheng Wang +5
Recent diffusion-based pipelines have achieved promising progress in image-to-3D synthesis. However, generating high-fidelity details remains challenging, especially when the input…
Rethinking Expert Training for Model Merging with Prompt Learning
Christos Georgakilas, Aniello Panariello, Samir El Karrat Moreno +3
Model merging aims to combine multiple domain-specialized experts trained from a shared foundation model into a single multi-task model. Existing approaches largely focus on improv…
Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing
Kai Wang, Fei Yang, Shiqi Yang +2
Large-scale text-to-image generative models have been a ground-breaking development in generative AI, with diffusion models showing their astounding ability to synthesize convincin…
Continual Evidential Deep Learning for Out-of-Distribution Detection
Eduardo Aguilar, Bogdan Raducanu, Petia Radeva +1
Uncertainty-based deep learning models have attracted a great deal of interest for their ability to provide accurate and reliable predictions. Evidential deep learning stands out a…
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.…
ScrollNet: Dynamic Weight Importance for Continual Learning
Fei Yang, Kai Wang, Joost van de Weijer
The principle underlying most existing continual learning (CL) methods is to prioritize stability by penalizing changes in parameters crucial to old tasks, while allowing for plast…
Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection
Liu Yuyang, Cong Yang, Goswami Dipam +2
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.…
Density Map Distillation for Incremental Object Counting
Chenshen Wu, Joost van de Weijer
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…
3D-Aware Multi-Class Image-to-Image Translation with NeRFs
Senmao Li, Joost van de Weijer, Yaxing Wang +3
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-aw…
StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
Senmao Li, Joost van de Weijer, Taihang Hu +5
A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the…
Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation
Marco Cotogni, Fei Yang, Claudio Cusano +2
We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner withou…
Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
Dipam Goswami, René Schuster, Joost van de Weijer +1
In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift. Although…
Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
Kai Wang, Chenshen Wu, Andy Bagdanov +4
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 tha…
Attention Distillation: self-supervised vision transformer students need more guidance
Kai Wang, Fei Yang, Joost van de Weijer
Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is there…
OneRing: A Simple Method for Source-free Open-partial Domain Adaptation
Shiqi Yang, Yaxing Wang, Kai Wang +2
In this paper, we investigate Source-free Open-partial Domain Adaptation (SF-OPDA), which addresses the situation where there exist both domain and category shifts between source a…
MVMO: A Multi-Object Dataset for Wide Baseline Multi-View Semantic Segmentation
Aitor Alvarez-Gila, Joost van de Weijer, Yaxing Wang +1
We present MVMO (Multi-View, Multi-Object dataset): a synthetic dataset of 116,000 scenes containing randomly placed objects of 10 distinct classes and captured from 25 camera loca…
Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
Shiqi Yang, Yaxing Wang, Kai Wang +2
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…
Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization
Francesco Pelosin, Saurav Jha, Andrea Torsello +2
In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the k…
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…
Main Product Detection with Graph Networks for Fashion
Vacit Oguz Yazici, Longlong Yu, Arnau Ramisa +2
Computer vision has established a foothold in the online fashion retail industry. Main product detection is a crucial step of vision-based fashion product feed parsing pipelines, f…
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…
Visual Transformers with Primal Object Queries for Multi-Label Image Classification
Vacit Oguz Yazici, Joost van de Weijer, Longlong Yu
Multi-label image classification is about predicting a set of class labels that can be considered as orderless sequential data. Transformers process the sequential data as a whole,…
Transferring Unconditional to Conditional GANs with Hyper-Modulation
Héctor Laria, Yaxing Wang, Joost van de Weijer +1
GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-qu…