Fatih Porikli's guest appearances

Fatih Porikli

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

OwlTail

Today we kick off our coverage of the 2023 CVPR conference joined by Fatih Porikli, a Senior Director of Technology at Qualcomm. In our conversation with Fatih, we covered quite a bit of ground, touching on a total of 12 papers/demos, focusing on topics like data augmentation and optimized architectures for computer vision. We explore advances in optical flow estimation networks, cross-model, and stage knowledge distillation for efficient 3D object detection, and zero-shot learning via language models for fine-grained labeling. We also discuss generative AI advancements and computer vision optimization for running large models on edge devices. Finally, we discuss objective functions, architecture design choices for neural networks, and efficiency and accuracy improvements in AI models via the techniques introduced in the papers.

Today we kick off our coverage of the 2023 CVPR conference joined by Fatih Porikli, a Senior Director of Technology at Qualcomm. In our conversation with Fatih, we covered quite a bit of ground, touching on a total of 12 papers/demos, focusing on topics like data augmentation and optimized architectures for computer vision. We explore advances in optical flow estimation networks, cross-model, and stage knowledge distillation for efficient 3D object detection, and zero-shot learning via language models for fine-grained labeling. We also discuss generative AI advancements and computer vision optimization for running large models on edge devices. Finally, we discuss objective functions, architecture design choices for neural networks, and efficiency and accuracy improvements in AI models via the techniques introduced in the papers.

Data Augmentation and Optimized Architectures for Computer Vision with Fatih Porikli - #635

Today we kick off our annual coverage of the CVPR conference joined by Fatih Porikli, Senior Director of Engineering at Qualcomm AI Research. In our conversation with Fatih, we explore a trio of CVPR-accepted papers, as well as a pair of upcoming workshops at the event. The first paper, Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation, presents a novel framework to integrate semantic and instance contexts for panoptic segmentation. Next up, we discuss Imposing Consistency for Optical Flow Estimation, a paper that introduces novel and effective consistency strategies for optical flow estimation. The final paper we discuss is IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes, which proposes a transformer architecture to simultaneously estimate depths, normals, spatially-varying albedo, roughness, and lighting from a single image of an indoor scene. For each paper, we explore the motivations and challenges and get concrete examples to demonstrate each problem and solution presented.The complete show notes for this episode can be found at twimlai.com/go/579

Today we kick off our annual coverage of the CVPR conference joined by Fatih Porikli, Senior Director of Engineering at Qualcomm AI Research. In our conversation with Fatih, we explore a trio of CVPR-accepted papers, as well as a pair of upcoming workshops at the event. The first paper, <a href="https://arxiv.org/abs/2204.05370" rel="nofollow" target="_blank">Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation</a>, presents a novel framework to integrate semantic and instance contexts for panoptic segmentation. Next up, we discuss <a href="https://arxiv.org/abs/2204.07262" rel="nofollow" target="_blank">Imposing Consistency for Optical Flow Estimation</a>, a paper that introduces novel and effective consistency strategies for optical flow estimation. The final paper we discuss is <a href="http://www.porikli.com/mysite/pdfs/porikli%202022%20-%20IRISformer%20Dense%20vision%20transformers%20for%20single-image%20inverse%20rendering%20in%20indoor%20scenes.pdf" rel="nofollow" target="_blank">IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes</a>, which proposes a transformer architecture to simultaneously estimate depths, normals, spatially-varying albedo, roughness, and lighting from a single image of an indoor scene. For each paper, we explore the motivations and challenges and get concrete examples to demonstrate each problem and solution presented. The complete show notes for this episode can be found at <a href="twimlai.com/go/579" rel="nofollow" target="_blank">twimlai.com/go/579</a>