Mert Bülent Sarıyıldız — accepted AI-conference papers

2025

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers

Mert Bülent Sarıyıldız, Philippe Weinzaepfel, Thomas Lucas, Pau de Jorge, Diane Larlus, Yannis Kalantidis

CVPR 2025poster

Recent multi-teacher distillation methods have unified the encoders of multiple foundation models into a single encoder, achieving competitive performance on core vision tasks like classification, segmentation, and depth estimation. This led us to ask: Could similar success be achieved when the pool…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Kinaema: a recurrent sequence model for memory and pose in motion

Mert Bülent Sarıyıldız, Philippe Weinzaepfel, Guillaume Bono, Gianluca Monaci, Christian Wolf

NeurIPS 2025poster

One key aspect of spatially aware robots is the ability to "find their bearings", ie. to correctly situate themselves or previously seen spaces. In this work, we focus on this particular scenario of continuous robotics operations, where information observed before an actual episode start is exploite…

Cited by 0 Source ↗Scholar ↗

2024

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

Yannis Kalantidis, Mert Bülent Sarıyıldız, Rafael S. Rezende, Philippe Weinzaepfel, Diane Larlus, Gabriela Csurka

ICLR 2024poster

State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions, due to e.g. weather or time of day, with dramatic consequences on the visual localization accuracy. In this paper, we i…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones

Mert Bülent Sarıyıldız, Karteek Alahari, Diane Larlus, Yannis Kalantidis

CVPR 2023poster

Recent image generation models such as Stable Diffusion have exhibited an impressive ability to generate fairly realistic images starting from a simple text prompt. Could such models render real images obsolete for training image prediction models? In this paper, we answer part of this provocative q…

Cited by 179 Source ↗PDF ↗Scholar ↗

2023

No Reason for No Supervision: Improved Generalization in Supervised Models

Mert Bülent Sarıyıldız, Yannis Kalantidis, Karteek Alahari, Diane Larlus

ICLR 2023top-25%

We consider the problem of training a deep neural network on a given classification task, e.g., ImageNet-1K (IN1K), so that it excels at both the training task as well as at other (future) transfer tasks. These two seemingly contradictory properties impose a trade-off between improving the model’s g…

Cited by 35 Source ↗PDF ↗Scholar ↗