31 citations · 123 across the 64 of their papers we have counts for
14 papers · 1 filter
Head Pursuit: Probing Attention Specialization in Multimodal Transformers
Lorenzo Basile, Valentino Maiorca, Diego Doimo +2
Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we st…
How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations
Siddhartha Gairola, Moritz Böhle, Francesco Locatello +1
Post-hoc importance attribution methods are a popular tool for "explaining" Deep Neural Networks (DNNs) and are inherently based on the assumption that the explanations can be appl…
ResiDual Transformer Alignment with Spectral Decomposition
Lorenzo Basile, Valentino Maiorca, Luca Bortolussi +2
When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions (e.g., attention heads) sometimes specialize i…
Near, far: Patch-ordering enhances vision foundation models' scene understanding
Valentinos Pariza, Mohammadreza Salehi, Gertjan Burghouts +2
We introduce NeCo: Patch Neighbor Consistency, a novel self-supervised training loss that enforces patch-level nearest neighbor consistency across a student and teacher model. Comp…
Adaptive Slot Attention: Object Discovery with Dynamic Slot Number
Ke Fan, Zechen Bai, Tianjun Xiao +5
Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level percept…
Boosting Unsupervised Segmentation Learning
Alp Eren Sari, Francesco Locatello, Paolo Favaro
We present two practical improvement techniques for unsupervised segmentation learning. These techniques address limitations in the resolution and accuracy of predicted segmentatio…
Object-Centric Multiple Object Tracking
Zixu Zhao, Jiaze Wang, Max Horn +13
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing th…
Unsupervised Open-Vocabulary Object Localization in Videos
Ke Fan, Zechen Bai, Tianjun Xiao +11
In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video obje…
Image retrieval outperforms diffusion models on data augmentation
Max F. Burg, Florian Wenzel, Dominik Zietlow +4
Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves train…
Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots
Dong Lao, Zhengyang Hu, Francesco Locatello +2
We investigate the emergence of objects in visual perception in the absence of any semantic annotation. The resulting model has received no supervision, does not use any pre-traine…
Self-supervised Amodal Video Object Segmentation
Jian Yao, Yuxin Hong, Chiyu Wang +6
Amodal perception requires inferring the full shape of an object that is partially occluded. This task is particularly challenging on two levels: (1) it requires more information t…
TeST: Test-time Self-Training under Distribution Shift
Samarth Sinha, Peter Gehler, Francesco Locatello +1
Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter…
Bridging the Gap to Real-World Object-Centric Learning
Maximilian Seitzer, Max Horn, Andrii Zadaianchuk +8
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decompos…
Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations
Andrii Zadaianchuk, Matthaeus Kleindessner, Yi Zhu +2
In this paper, we show that recent advances in self-supervised feature learning enable unsupervised object discovery and semantic segmentation with a performance that matches the s…