July 13, 2021

Marjan Firouznia, Amirkabir University

Develop New Deep Learning/Machine Learning Models for Medical Image Analysis

Biomedical image segmentation is an important tool for current clinical applications and basic research. The manual segmentation of medical images is a time-consuming, labor-intensive, and error-prone process. In Artificial Intelligence (AI), approaches inspired by mathematical models such as probability distribution mixture models and optimization theory have been employed to handle some main challenges in these areas. In this project we will propose new image segmentation methods for biomedical image analysis using deep learning models and fractal maps from CT scans. We will improve traditional image segmentation in 3D and deep learning models for CT/MRI scans. Also, we will apply the fractal features and Poincare maps to propose a new deep learning model for 3D segmentation using rich information of regions and voxels. The fractal analysis is used to represent shape and texture-based features to separate region interest from it surrounding. Then, we will apply Poincare maps to model the changes of boundaries to achieve a robust segmentation with high anatomical variations. Also, a novel machine learning (ML) method using a deep learning approach will be introduced for semantic segmentation of vessels, nodules, and myocardial walls using fractal maps. Multi-task fully convolutional networks (FCNs) will be constructed to improve the accuracy of semantic segmentation. These FCNs will learn the main task of semantic segmentation together with the auxiliary tasks of estimating the fractal maps.

July 6, 2021

Mustafa Akın Yılmaz, Koç University

End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression

Conventional video compression methods employ a linear transform and block motion model, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to the combinatorial nature of the end-to-end optimization problem. Learned video compression allows end-to-end rate-distortion optimized training of all nonlinear modules, quantization parameter and entropy model simultaneously. Most of the works on learned video compression considered training a sequential video codec based on end-to-end optimization of cost averaged over pairs of successive frames. It is well-known in conventional video compression that hierarchical, bi-directional coding outperforms sequential compression because of its ability to selectively use reference frames from both future and past. To this effect, a hierarchical bi-directional learned lossy video compression system is presented in this thesis. Experimental results show that the rate-distortion performance of the proposed framework outperforms both traditional and other learned codecs in the literature yielding state-of-the art results.

Jun 29, 2021

Barbara Plank, IT University of Copenhagen

Learning with Scarce and Biased Data in Natural Language Processing

Transferring knowledge to solve a related problem and learning from scarce labeled data and unreliable biased inputs are examples of extraordinary human ability. State-of-the-art NLP models often fail under such conditions. In this talk, I will present some recent work to addresses these ubiquitous challenges. This includes work on cross-lingual learning for NLP, multi-task learning and learning from unreliable data.

Jun 22, 2021

 Atil Iscen, Google Brain Robotics

Learning Legged Locomotion

Designing agile locomotion controllers for quadruped robots often requires extensive expertise and tedious manual tuning. Reinforcement Learning has shown success in solving many difficult control problems, and has potential to help with learning locomotion for physical robots. In this talk, I’ll present different methods we developed to tackle the locomotion problem using learning: Embedding prior knowledge, sim-to-real transfer, model-based reinforcement learning, hierarchical reinforcement learning, multi-task learning and using a mentor for harder tasks.

 

 

 

Jun 15, 2021

Jure Žbontar, Facebook AI Research

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn representations which are invariant to distortions of the input sample. However, a recurring issue with this approach is the existence of trivial constant representations. Most current methods avoid such collapsed solutions by careful implementation details. We propose an objective function that naturally avoids such collapse by measuring the cross-correlation matrix between the outputs of two identical networks fed with distorted versions of a sample, and making it as close to the identity matrix as possible. This causes the representation vectors of distorted versions of a sample to be similar, while minimizing the redundancy between the components of these vectors. The method is called Barlow Twins, owing to neuroscientist H. Barlow’s redundancy-reduction principle applied to a pair of identical networks. Barlow Twins does not require large batches nor asymmetry between the network twins such as a predictor network, gradient stopping, or a moving average on the weight updates. It allows the use of very high-dimensional output vectors. Barlow Twins outperforms previous methods on ImageNet for semi-supervised classification in the low-data regime, and is on par with current state of the art for ImageNet classification with a linear classifier head, and for transfer tasks of classification and object detection.

Jun 8, 2021

Fatma Güney, KUIS AI, Koç University

Structure, Motion, and Future Prediction in Dynamic Scenes

In this talk, I’ll talk about what we’ve been working on with Sadra and Kaan* in the last one and a half years in my group**. I’ll start by introducing the view synthesis approach to unsupervised monocular depth and ego-motion estimation by Zhou et al. [1]. I’ll point to its limitation with dynamic objects due to static background assumption and mention a few related works addressing it by conditioning on a given segmentation map. Then, I’ll introduce our approach to jointly reason about segmentation and depth without any conditioning. In the second part, I’ll introduce the stochastic video prediction framework proposed by Denton et al. [2] and show how we extend it to motion space with “SLAMP: Stochastic Latent Appearance and Motion Prediction”. Finally, I’ll talk about how structure and motion from the first part can help stochastic video prediction from the second part in real-world driving scenarios. [1] T. Zhou, M. Brown, N. Snavely, and D. G. Lowe. Unsupervised learning of depth and ego-motion from video. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017. [2] E. Denton and R. Fergus. Stochastic video generation with a learned prior. In Proc. of the International Conf. on Machine learning (ICML), 2018. *Also in collaboration with Aykut Erdem and Erkut Erdem. **Work under submission, please do not share.

Jun 1, 2021

Ömer Güneş, University of Oxford

Character Identification from Narrative Text

Having more than ten kinds of style; e.g. autobiography, fable, historical fiction, novel; narrative text constitutes an important part of written text. Despite the abundance of long-form textual data, it is not straightforward to develop robust natural language processing (NLP) models to understand narrative text automatically. Even for domain experts, analyzing and interpreting potentially long and complicated narrative (literary) texts to extract legible and concise information is a difficult process. Characters are among the most important aspects of a story. It is crucial to identify the characters of a narrative to understand that narrative deeply. Therefore, automatic character identification is a critical task in narrative natural language understanding. In this talk, we will provide a comprehensive overview of this new and exciting paradigm of character identification in the context of NLP and deep learning, and then we outline the major research challenges. We will also present our recent approach to automatically identifying characters from unannotated stories in natural language text, segmentation of conversations and attribution of utterances to characters for generating longform multi-voice audiobooks at scale.