11 papers · 1 filter
Balancing Representations by Identifying and Generating Under-represented Data
Filipe Laitenberger, Hirokatsu Kataoka, Yuki Asano +2
Self-supervised learning inherits the coverage of its source data. When an unlabeled corpus is long-tailed, the representation becomes dense around frequent modes and thin where co…
RFDM: Residual Flow Diffusion Model for Efficient Causal Video Editing
Mohammadreza Salehi, Mehdi Noroozi, Luca Morreale +4
Instructional video editing applies edits to an input video using only text prompts, enabling intuitive natural-language control. Despite rapid progress, most methods still require…
Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis
Valentina Lilova, Toyesh Chakravorty, Julian I. Bibo +5
Benchmarking 3D spatial understanding of foundation models is essential for real-world applications such as robotics and autonomous driving. Existing evaluations often rely on down…
MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning
Mohammadreza Salehi, Shashanka Venkataramanan, Ioana Simion +3
Dense self-supervised learning has shown great promise for learning pixel- and patch-level representations, but extending it to videos remains challenging due to the complexity of…
Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
Shashanka Venkataramanan, Valentinos Pariza, Mohammadreza Salehi +5
We present Franca (pronounced Fran-ka): free one; the first fully open-source (data, code, weights) vision foundation model that matches and in many cases surpasses the performance…
Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
Divyanshu Mishra, Mohammadreza Salehi, Pramit Saha +4
Self-supervised learning (SSL) has achieved major advances in natural images and video understanding, but challenges remain in domains like echocardiography (heart ultrasound) due…
Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection
Mohammadreza Salehi, Nikolaos Apostolikas, Efstratios Gavves +2
In the realm of novelty detection, accurately identifying outliers in data without specific class information poses a significant challenge. While current methods excel in single-o…
SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery
Sarah Rastegar, Mohammadreza Salehi, Yuki M. Asano +2
In this paper, we address Generalized Category Discovery, aiming to simultaneously uncover novel categories and accurately classify known ones. Traditional methods, which lean heav…
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…
SIGMA: Sinkhorn-Guided Masked Video Modeling
Mohammadreza Salehi, Michael Dorkenwald, Fida Mohammad Thoker +3
Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising…
GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features
Luc P. J. Sträter, Mohammadreza Salehi, Efstratios Gavves +2
In the domain of anomaly detection, methods often excel in either high-level semantic or low-level industrial benchmarks, rarely achieving cross-domain proficiency. Semantic anomal…