Analysis of Large-Scale Visual Recognition - Bay Area Vision Meeting
Offered By: Meta via YouTube
Course Description
Overview
Explore the evolution and challenges of large-scale visual recognition in this 40-minute Meta conference talk from the Bay Area Vision Meeting. Dive into the IMAGENET Large Scale Visual Recognition Challenge (ILSVRC) from 2010-2012, examining its diverse object classes and two main tasks: Classification and Classification + Localization. Analyze the performance of various systems, including SuperVision (SV) and VGG, across different scales and object types. Investigate the impact of clutter, texture, and scale on recognition accuracy. Conclude with insights into the ILSVRC 2013 large-scale object detection task, gaining a comprehensive understanding of the field's progress and future directions.
Syllabus
Intro
Large-scale recognition
IMAGENET Large Scale Visual Recognition Challenge (ILSVRC) 2010-2012
Variety of object classes in ILSVRC
ILSVRC Task 1: Classification
ILSVRC Task 2: Classification + Localization
ILSVRC (2012)
Chance Performance of Localization
Level of clutter
SuperVision (SV)
Difference in accuracy: SV versus VGG
Cumulative accuracy across scales Classification only
Textured objects (ILSVRC-500)
Textured objects (416 classes)
Localizing textured objects (416 classes, same average object scale at each level of texture)
ILSVRC 2013 with large-scale object detection
Taught by
Meta Developers
Related Courses
Inference with Torch-TensorRT Deep Learning Prediction for Beginners - CPU vs CUDA vs TensorRTPython Simplified via YouTube AlexNet and ImageNet Explained
James Briggs via YouTube Introduction to Neural Networks for Computer Vision - Part I
University of Central Florida via YouTube Evaluating Neural Network Robustness - Targeted Attacks and Defenses
University of Central Florida via YouTube Fast Is Better Than Free: Revisiting Adversarial Training - CAP6412 Spring 2021
University of Central Florida via YouTube