Dimitris Samaras

Dimitris Samaras

Auto-generated profile, based on publicly available information

Dimitris Samaras

Stony Brook University

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2016
Verified
Conference Paper
Closed access
LHLe Hou
Le Hou
DSDimitris Samaras
Dimitris Samaras
TKTahsin M. Kurc
Tahsin M. Kurc
YGYi Gao
Yi Gao
JDJames E. Davis
James E. Davis
JSJoel H. Saltz
Joel H. Saltz
Convolutional Neural Networks (CNN) are state-of-theart models for many image classification tasks. However, to recognize cancer subtypes automatically, training a CNN on gigapixel resolution Whole Slide Tissue Images (WSI) is currently computationally impossible. The differentiation of cancer subtypes is based on cellular-level visual features observed on image patch scale. Therefore, we argue that in this situation, training a patch-level classifier on image patches will perform better than or similar to an image-level classifier. The challenge becomes how to intelligently combine patch-level classification results and model the fact that not all patches will be discriminative. We propose to train a decision fusion model to aggregate patch-level predictions given by patch-level CNNs, which to the best of our knowledge has not been shown before. Furthermore, we formulate a novel Expectation-Maximization (EM) based method that automatically locates discriminative patches robustly by utilizing the spatial relationships of patches. We apply our method to the classification of glioma and non-small-cell lung carcinoma cases into subtypes. The classification accuracy of our method is similar to the inter-observer agreement between pathologists. Although it is impossible to train CNNs on WSIs, we experimentally demonstrate using a comparable non-cancer dataset of smaller images that a patch-based CNN can outperform an image-based CNN.

13 October 2023 in Nature Communications
Verified
Journal Article
Open access
PDF file
JDJianyuan Deng
Jianyuan Deng
ZYZhibo Yang
Zhibo Yang
HWHehe Wang
Hehe Wang
IOIwao Ojima
Iwao Ojima
DSDimitris Samaras
Dimitris Samaras
FWFusheng Wang
Fusheng Wang
Artificial intelligence (AI) has been widely applied in drug discovery with a major task as molecular property prediction. Despite booming techniques in molecular representation learning, key elements underlying molecular property prediction remain largely unexplored, which impedes further advancements in this field. Herein, we conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets, a suite of opioids-related datasets and two additional activity datasets from the literature. To investigate the predictive power in low-data and high-data space, a series of descriptors datasets of varying sizes are also assembled to evaluate the models. In total, we have trained 62,820 models, including 50,220 models on fixed representations, 4200 models on SMILES sequences and 8400 models on molecular graphs. Based on extensive experimentation and rigorous comparison, we show that representation learning models exhibit limited performance in molecular property prediction in most datasets. Besides, multiple key elements underlying molecular property prediction can affect the evaluation results. Furthermore, we show that activity cliffs can significantly impact model prediction. Finally, we explore into potential causes why representation learning models can fail and show that dataset size is essential for representation learning models to excel.

4 November 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HLHieu Le
Hieu Le
DSDimitris Samaras
Dimitris Samaras
We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks, namely SP-Net and M-Net, to predict the shadow parameters and the shadow matte respectively. This system allows us to remove the shadow effects from images. We then employ an inpainting network, I-Net, to further refine the results. We train and test our framework on the most challenging shadow removal dataset (ISTD). Our method improves the state-of-the-art in terms of mean absolute error (MAE) for the shadow area by 20%. Furthermore, this decomposition allows us to formulate a patch-based weakly-supervised shadow removal method. This model can be trained without any shadow- free images (that are cumbersome to acquire) and achieves competitive shadow removal results compared to state-of-the-art methods that are trained with fully paired shadow and shadow-free images. Last, we introduce SBU-Timelapse, a video shadow removal dataset for evaluating shadow removal methods.

1 January 2007
Verified
Conference Paper
Closed access
WZWei Zhang
Wei Zhang
GZGregory Zelinsky
Gregory Zelinsky
DSDimitris Samaras
Dimitris Samaras
We propose a multi-resolution framework inspired by human visual search for general object detection. Different resolutions are represented using a coarse-to-fine feature hierarchy. During detection, the lower resolution features are initially used to reject the majority of negative windows at relatively low cost, leaving a relatively small number of windows to be processed in higher resolutions. This enables the use of computationally more expensive higher resolution features to achieve high detection accuracy. We applied this framework on Histograms of Oriented Gradient (HOG) features for object detection. Our multi-resolution detector produced better performance for pedestrian detection than state-of-the-art methods (Dalal and Triggs, 2005), and was faster during both training and testing. Testing our method on motorbikes and cars from the VOC database revealed similar improvements in both speed and accuracy, suggesting that our approach is suitable for realtime general object detection applications.

14 July 2007 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YWYang Wang
Yang Wang
MGMohit Gupta
Mohit Gupta
SZSong Zhang
Song Zhang
SWSen Wang
Sen Wang
DGDavid Gu
David Gu
PHPeisen Huang
Peisen Huang

1 December 2023
Verified
Book Chapter
Closed access
PDF file
JZJingwei Zhang
Jingwei Zhang
KMKe Ma
Ke Ma
Saarthak KapseSaarthak Kapse
Saarthak Kapse
JSJoel Saltz
Joel Saltz
MVMaria Vakalopoulou
Maria Vakalopoulou
DSDimitris Samaras
Dimitris Samaras