The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content.
Mixture of Experts (MoE) are rising in popularity as a means to train extremely large-scale models, yet allowing for a reasonable computational cost at inference time.
no code implementations • 11 Apr 2023 • Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc-Huy Trinh, Danial Hasan, Xingwen Li, Taehyo Kim, Haochen Zhang, Theodore Wu, Kajanan Chinniah, Sina Maghsoudlou, Ryan Zhang, Stephen Yang, Jiadai Zhu, Lyndon Chan, Samir Khaki, Andrei Buin, Fatemeh Chaji, Ala Salehi, Alejandra Zambrano Luna, Bich Ngoc Nguyen, Dimitris Samaras, Konstantinos N. Plataniotis
Computational Pathology (CoPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images.
In this paper, we propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection that allows for heavy down-sampling of unimportant background regions while preserving the fine-grained details of a high-resolution image.
In this paper, we propose a conditional early exiting framework for efficient video recognition.
We reformulate standard convolution to be efficiently computed on residual frames: each layer is coupled with a binary gate deciding whether a residual is important to the model prediction,~\eg foreground regions, or it can be safely skipped, e. g. background regions.
When recognizing a long-range activity, exploring the entire video is exhaustive and computationally expensive, as it can span up to a few minutes.
Therefore, we additionally introduce a task classifier that predicts the task label of each example, to deal with settings in which a task oracle is not available.
To achieve this, we introduce a new residual block architecture that gates convolutional channels in a fine-grained manner.
no code implementations • 22 Jul 2018 • Mitko Veta, Yujing J. Heng, Nikolas Stathonikos, Babak Ehteshami Bejnordi, Francisco Beca, Thomas Wollmann, Karl Rohr, Manan A. Shah, Dayong Wang, Mikael Rousson, Martin Hedlund, David Tellez, Francesco Ciompi, Erwan Zerhouni, David Lanyi, Matheus Viana, Vassili Kovalev, Vitali Liauchuk, Hady Ahmady Phoulady, Talha Qaiser, Simon Graham, Nasir Rajpoot, Erik Sjöblom, Jesper Molin, Kyunghyun Paeng, Sangheum Hwang, Sunggyun Park, Zhipeng Jia, Eric I-Chao Chang, Yan Xu, Andrew H. Beck, Paul J. van Diest, Josien P. W. Pluim
The best performing automatic method for the first task achieved a quadratic-weighted Cohen's kappa score of $\kappa$ = 0. 567, 95% CI [0. 464, 0. 671] between the predicted scores and the ground truth.
no code implementations • 10 May 2017 • Babak Ehteshami Bejnordi, Guido Zuidhof, Maschenka Balkenhol, Meyke Hermsen, Peter Bult, Bram van Ginneken, Nico Karssemeijer, Geert Litjens, Jeroen van der Laak
Automated classification of histopathological whole-slide images (WSI) of breast tissue requires analysis at very high resolutions with a large contextual area.
1 code implementation • 20 Feb 2017 • Francesco Ciompi, Oscar Geessink, Babak Ehteshami Bejnordi, Gabriel Silva de Souza, Alexi Baidoshvili, Geert Litjens, Bram van Ginneken, Iris Nagtegaal, Jeroen van der Laak
The development of reliable imaging biomarkers for the analysis of colorectal cancer (CRC) in hematoxylin and eosin (H&E) stained histopathology images requires an accurate and reproducible classification of the main tissue components in the image.
no code implementations • 19 Feb 2017 • Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen A. W. M. van der Laak, Bram van Ginneken, Clara I. Sánchez
Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images.
Diagnosis of breast carcinomas has so far been limited to the morphological interpretation of epithelial cells and the assessment of epithelial tissue architecture.