2 citations · 6 across the 10 of their papers we have counts for
13 papers
Towards Data-Efficient Medical Imaging: A Generative and Semi-Supervised Framework
Mosong Ma, Tania Stathaki, Michalis Lazarou
Deep learning in medical imaging is often limited by scarce and imbalanced annotated data. We present SSGNet, a unified framework that combines class specific generative modeling w…
Enhanced Detection of Tiny Objects in Aerial Images
Kihyun Kim, Michalis Lazarou, Tania Stathaki
While one-stage detectors like YOLOv8 offer fast training speed, they often under-perform on detecting small objects as a trade-off. This becomes even more critical when detecting…
No Masks Needed: Explainable AI for Deriving Segmentation from Classification
Mosong Ma, Tania Stathaki, Michalis Lazarou
Medical image segmentation is vital for modern healthcare and is a key element of computer-aided diagnosis. While recent advancements in computer vision have explored unsupervised…
Image compositing is all you need for data augmentation
Ang Jia Ning Shermaine, Michalis Lazarou, Tania Stathaki
This paper investigates the impact of various data augmentation techniques on the performance of object detection models. Specifically, we explore classical augmentation methods, i…
Image edge enhancement for effective image classification
Tianhao Bu, Michalis Lazarou, Tania Stathaki
Image classification has been a popular task due to its feasibility in real-world applications. Training neural networks by feeding them RGB images has demonstrated success over it…
Adaptive Anchor Label Propagation for Transductive Few-Shot Learning
Michalis Lazarou, Yannis Avrithis, Guangyu Ren +1
Few-shot learning addresses the issue of classifying images using limited labeled data. Exploiting unlabeled data through the use of transductive inference methods such as label pr…
Adaptive manifold for imbalanced transductive few-shot learning
Michalis Lazarou, Yannis Avrithis, Tania Stathaki
Transductive few-shot learning algorithms have showed substantially superior performance over their inductive counterparts by leveraging the unlabeled queries. However, the vast ma…
Towards Automated Polyp Segmentation Using Weakly- and Semi-Supervised Learning and Deformable Transformers
Guangyu Ren, Michalis Lazarou, Jing Yuan +1
Polyp segmentation is a crucial step towards computer-aided diagnosis of colorectal cancer. However, most of the polyp segmentation methods require pixel-wise annotated datasets. A…
Tensor feature hallucination for few-shot learning
Michalis Lazarou, Tania Stathaki, Yannis Avrithis
Few-shot learning addresses the challenge of learning how to address novel tasks given not just limited supervision but limited data as well. An attractive solution is synthetic da…
Few-shot learning via tensor hallucination
Michalis Lazarou, Yannis Avrithis, Tania Stathaki
Few-shot classification addresses the challenge of classifying examples given only limited labeled data. A powerful approach is to go beyond data augmentation, towards data synthes…
A novel shape matching descriptor for real-time hand gesture recognition
Michalis Lazarou, Bo Li, Tania Stathaki
The current state-of-the-art hand gesture recognition methodologies heavily rely in the use of machine learning. However there are scenarios that machine learning cannot be applied…
Iterative label cleaning for transductive and semi-supervised few-shot learning
Michalis Lazarou, Tania Stathaki, Yannis Avrithis
Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance…
GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
Daniel Lengyel, Janith Petangoda, Isak Falk +5
We propose an efficient algorithm to visualise symmetries in neural networks. Typically, models are defined with respect to a parameter space, where non-equal parameters can produc…