Martine Hjelkrem-Tan — accepted AI-conference papers

2026

Suppressing Non-Semantic Noise in Masked Image Modeling Representations

Martine Hjelkrem-Tan, Marius Aasan, Rwiddhi Chakraborty, Gabriel Y. Arteaga, Changkyu Choi, Adín Ramírez Rivera

CVPR 2026

Masked Image Modeling (MIM) has become a ubiquitous self-supervised vision paradigm. In this work, we show that MIM objectives cause the learned representations to retain non-semantic information, which ultimately hurts performance during inference. We introduce a model-agnostic score for semantic i

Cited by 0 Source ↗code ↗Scholar ↗

2026

Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning

Gabriel Y. Arteaga, Marius Aasan, Rwiddhi Chakraborty, Martine Hjelkrem-Tan, Thalles Silva, Michael Kampffmeyer +1

ICLR 2026poster

Prototypical self-supervised learning methods consistently suffer from partial prototype collapse, where multiple prototypes converge to nearly identical representations. This undermines their central purpose—providing diverse and informative targets to guide encoders toward rich representations—and…

Cited by 0 Source ↗Scholar ↗

2025

Differentiable Hierarchical Visual Tokenization

Marius Aasan, Martine Hjelkrem-Tan, Nico Catalano, Changkyu Choi, Adín Ramírez Rivera

NeurIPS 2025spotlight

Vision Transformers rely on fixed patch tokens that ignore the spatial and semantic structure of images. In this work, we introduce an end-to-end differentiable tokenizer that adapts to image content with pixel-level granularity while remaining backward-compatible with existing architectures for ret…

Cited by 0 Source ↗Scholar ↗