Главная
Study mode:
on
1
Einleitung
2
Axes of Robustness
3
The Numbers You See in Papers
4
The Reality
5
Back to the Drawing Board
6
It All Starts with Naming Things
7
Naming is for Communication
8
Human Human Communication
9
Object Spotting Game car
10
Task: Detect Everything!
11
Problem 2: Data Efficient Learning
12
Problem 1: Benchmarking
13
Building LVIS
14
PASCAL VOC and COCO were "easy" to Build
15
Troubles with 1000's of Categories
16
Facing These Problems, What Can We Do?
17
Federated Dataset Design to the Rescue
18
Annotation Pipeline
19
LVIS Annotations Quality
20
Where does the vocabulary come from?
21
Data Driven Category Discovery
22
The Long Tail is Inescapable! 100
23
Results on LVIS v1 validation set
24
Best Practices - Know What's Noise
25
The LVIS Challenge at ECCV 2020!
Description:
Explore a keynote address from the Robust Vision Challenge 2020 focusing on robustness across the data abundance spectrum. Delve into the challenges of modern computer vision, including data-efficient learning and benchmarking for large-scale datasets. Examine the development of LVIS (Large Vocabulary Instance Segmentation) and its innovative approach to federated dataset design. Learn about the difficulties in annotating thousands of categories and discover data-driven category discovery techniques. Gain insights into best practices for handling noise in datasets and get information about the LVIS Challenge at ECCV 2020.

Keynote: Ross Girshick - Robustness Across the Data Abundance Spectrum

Andreas Geiger
Add to list
0:00 / 0:00