Contrastive Neural Processes for Self-Supervised Learning

1 code implementation • 24 Oct 2021 • Konstantinos Kallidromitis, Denis Gudovskiy, Kazuki Kozuka, Iku Ohama, Luca Rigazio

In this paper, we propose a novel self-supervised learning framework that combines contrastive learning with neural processes.

Contrastive Learning Data Augmentation +3

Refine and Represent: Region-to-Object Representation Learning

1 code implementation • 25 Aug 2022 • Akash Gokul, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Kazuki Kozuka, Trevor Darrell, Colorado J Reed

Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondence objectives.

Object Representation Learning +4

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

no code implementations • 19 Jun 2023 • Luca Franco, Paolo Mandica, Konstantinos Kallidromitis, Devin Guillory, Yu-Teng Li, Trevor Darrell, Fabio Galasso

In HALO (Hyperbolic Active Learning Optimization), for the first time, we propose the use of epistemic uncertainty as a data acquisition strategy, following the intuition of selecting data points that are the least known.

Active Learning Domain Adaptation +2

Hierarchical Open-vocabulary Universal Image Segmentation

1 code implementation • NeurIPS 2023 • Xudong Wang, Shufan Li, Konstantinos Kallidromitis, Yusuke Kato, Kazuki Kozuka, Trevor Darrell

Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions.

Image Comprehension Image Segmentation +8

Aligning Diffusion Models by Optimizing Human Utility

no code implementations • 6 Apr 2024 • Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka

We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility.