no code implementations • 7 Jan 2024 • Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Michael Felsberg
Kernel methods are employed to simplify computations by approximating softmax but often lead to performance drops compared to softmax attention.
no code implementations • 11 Oct 2023 • Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Xuelong Li, Yue Lu
The challenge of image generation has been effectively modeled as a problem of structure priors or transformation.
no code implementations • 24 Jul 2023 • Pourya Shamsolmoali, Masoumeh Zareapoor
This paper focuses on an accurate and fast interpolation approach for image transformation employed in the design of CNN architectures.
1 code implementation • 30 Apr 2023 • Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger
Given the recent advances with image-generating algorithms, deep image completion methods have made significant progress.
1 code implementation • 3 Apr 2023 • Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, DaCheng Tao, Xuelong Li
This weak projection, however, can be addressed by a Riemannian metric, and we show that geodesics computation and accurate interpolations between data samples on the Riemannian manifold can substantially improve the performance of deep generative models.
no code implementations • 1 Sep 2022 • Pourya Shamsolmoali, Masoumeh Zareapoor, Swagatam Das, Eric Granger, Salvador Garcia
Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relations using a two-step process involving part-whole transformation and hierarchical component routing.
no code implementations • 20 May 2022 • Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Huiyu Zhou
Skin lesion detection in dermoscopic images is essential in the accurate and early diagnosis of skin cancer by a computerized apparatus.
no code implementations • 12 May 2022 • Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Jocelyn Chanussot, Jie Yang
In IPSSD, single-shot detector is adopted combined with an image pyramid network to extract semantically strong features for generating candidate regions.
no code implementations • 9 Feb 2022 • Lu Wang, Jie Yang, Masoumeh Zareapoor, ZhongLong Zheng
Cross-modal hashing still has some challenges needed to address: (1) most existing CMH methods take graphs as input to model data distribution.
no code implementations • 18 Aug 2021 • Pourya Shamsolmoali, Jocelyn Chanussot, Masoumeh Zareapoor, Huiyu Zhou, Jie Yang
Second, most of the standard methods used hand-crafted features, and do not work well on the detection of objects parts of which are missing.
no code implementations • 2 Jun 2021 • Pourya Shamsolmoali, Masoumeh Zareapoor, Jocelyn Chanussot, Huiyu Zhou, Jie Yang
The proposed model adopts single-shot detector in parallel with a lightweight image pyramid module to extract representative features and generate regions of interest in an optimization approach.
1 code implementation • 26 Dec 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Huiyu Zhou, Ruili Wang, M. Emre Celebi, Jie Yang
However, there is a lack of comprehensive review in this field, especially lack of a collection of GANs loss-variant, evaluation metrics, remedies for diverse image generation, and stable training.
1 code implementation • 10 Aug 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Ruili Wang, Jie Yang
We also propose a feature pyramid network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales objects.
no code implementations • 7 Aug 2020 • Masoumeh Zareapoor, Pourya Shamsolmoali, Jie Yang
In particular, we restore the balance in the imbalanced dataset by generating faulty samples from the proposed mixture of data distribution.
no code implementations • 5 Apr 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Linlin Shen, Abdul Hamid Sadka, Jie Yang
It improves learning from imbalanced data by incorporating the majority distribution structure in the generation of new minority samples.
1 code implementation • 18 Mar 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Jie Yang
The proposed adversarial residual multi-instance neural network that is based on pooling has been validated on two datasets for the human pose estimation task and successfully outperforms the other state-of-arts models.
no code implementations • 17 Mar 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Ruili Wang, Huiyu Zhou, Jie Yang
This paper presents a novel deep neural network structure for pixel-wise sea-land segmentation, a Residual Dense U-Net (RDU-Net), in complex and high-density remote sensing images.
no code implementations • 5 Mar 2019 • Hafiz Tayyab Mustafa, Jie Yang, Masoumeh Zareapoor
To address the above issues, we proposed a new MFIF method, which aims to learn feature extraction, fusion and reconstruction components together to produce a complete unsupervised end-to-end trainable deep CNN.