1 code implementation • 10 May 2024 • Junfeng Cheng, Tania Stathaki
In our framework, we design a gradient-field-based selection graph neural network (GNN) to learn the gradients of a log conditional probability density in terms of part selection, where the condition is the given mixed part set.
no code implementations • 8 May 2024 • Nikolaos Giakoumoglou, Tania Stathaki
In the field of computer vision, self-supervised learning has emerged as a method to extract robust features from unlabeled data, where models derive labels autonomously from the data itself, without the need for manual annotation.
no code implementations • 22 Mar 2024 • Lucas Iijima, Tania Stathaki
With the latest AI technology, millions of high quality images are being generated by the public, which are constantly motivating the research community to push the limits of generative models to create more complex and realistic images.
no code implementations • 20 Mar 2024 • Kaushalya Kularatnam, Tania Stathaki
As algorithmic trading and electronic markets continue to transform the landscape of financial markets, detecting and deterring rogue agents to maintain a fair and efficient marketplace is crucial.
no code implementations • 13 Jan 2024 • Tianhao Bu, Michalis Lazarou, Tania Stathaki
A widely popular embraced method to improve the classification performance of neural networks is to incorporate data augmentations during the training process.
1 code implementation • 30 Oct 2023 • Michalis Lazarou, Yannis Avrithis, Guangyu Ren, Tania Stathaki
Our novel algorithm, Adaptive Anchor Label Propagation}, outperforms the standard label propagation algorithm by as much as 7% and 2% in the 1-shot and 5-shot settings respectively.
no code implementations • 27 Apr 2023 • Michalis Lazarou, Yannis Avrithis, Tania Stathaki
Our method exploits the underlying manifold of the labeled support examples and unlabeled queries by using manifold similarity to predict the class probability distribution per query.
no code implementations • 21 Nov 2022 • Guangyu Ren, Michalis Lazarou, Jing Yuan, Tania Stathaki
Also, our framework can be utilized to fine-tune models trained on natural image segmentation datasets drastically improving their performance for polyp segmentation and impressively demonstrating superior performance to fully supervised fine-tuning.
no code implementations • 17 Jun 2021 • Guangyu Ren, Yinxiao Yu, Hengyan Liu, Tania Stathaki
RGB-D salient object detection (SOD) demonstrates its superiority on detecting in complex environments due to the additional depth information introduced in the data.
1 code implementation • 9 Jun 2021 • Michalis Lazarou, Tania Stathaki, Yannis Avrithis
We follow a different approach and investigate how a simple and straightforward synthetic data generation method can be used effectively.
no code implementations • 7 Jun 2021 • Guangyu Ren, Yanchu Xie, Tianhong Dai, Tania Stathaki
We further introduce a mask-guided refinement module(MGRM) to complement the high-level semantic features and reduce the irrelevant features from multi-scale fusion, leading to an overall refinement of detection.
1 code implementation • 19 Apr 2021 • Michalis Lazarou, Yannis Avrithis, Tania Stathaki
Few-shot classification addresses the challenge of classifying examples given only limited labeled data.
no code implementations • 11 Jan 2021 • Michalis Lazarou, Bo Li, Tania Stathaki
In this work we present a novel shape matching methodology for real-time hand gesture recognition.
1 code implementation • ICCV 2021 • 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.
no code implementations • 30 Apr 2020 • Guangyu Ren, Tianhong Dai, Panagiotis Barmpoutis, Tania Stathaki
Salient object detection has achieved great improvement by using the Fully Convolution Network (FCN).
no code implementations • 18 Dec 2019 • Tianrui Liu, Wenhan Luo, Lin Ma, Jun-Jie Huang, Tania Stathaki, Tianhong Dai
Ablation studies have validated the effectiveness of both the proposed gated multi-layer feature extraction sub-network and the deformable occlusion handling sub-network.
no code implementations • 25 Oct 2019 • Tianrui Liu, Jun-Jie Huang, Tianhong Dai, Guangyu Ren, Tania Stathaki
In this paper, we propose a gated multi-layer convolutional feature extraction method which can adaptively generate discriminative features for candidate pedestrian regions.
no code implementations • 7 Aug 2018 • Tianrui Liu, Mohamed Elmikaty, Tania Stathaki
Convolutional neural networks (CNN) have enabled significant improvements in pedestrian detection owing to the strong representation ability of the CNN features.