SLIDE 1 Finding Four-Leaf Clovers: A Benchmark for Fine-Grained Object Localization
Gustavo Pérez*, Laura Bravo*, Alejandro Pardo*, Pablo Arbeláez
01/15
*Indicates equal contribution
SLIDE 2
Finding Four-Leaf Clovers
Goal: to create a reliable benchmark for fine-grained object localization problems Other fine-grained object localization problems: Cancer diagnosis (Medicine) Identifying cells in mitosis (Medicine) Detecting infected crops (Biology) Finding a specific person in a crowd (Industry)
Available at: tinyurl.com/yy9rbbsu
02/15
SLIDE 3
Finding Four-Leaf Clovers
High intra-class variability Low inter-class variability
Available at: tinyurl.com/yy9rbbsu
03/15
SLIDE 4
Finding Four-Leaf Clovers
Highly un-balanced
Available at: tinyurl.com/yy9rbbsu
04/15
SLIDE 5
Finding Four-Leaf Clovers
Available at: tinyurl.com/yy9rbbsu
05/15
SLIDE 6
Finding Four-Leaf Clovers
Available at: tinyurl.com/yy9rbbsu
06/15
SLIDE 7
The Four-Leaf Clover Dataset
Examples of the level of detail in segmentation annotations of the FLC dataset
Available at: tinyurl.com/yy9rbbsu
07/15
SLIDE 8
The Four-Leaf Clover Dataset
FLC dataset statistics. 4-leaf clover pixels and 4-leaf clover boundary pixels refer to the rate of the total of positive pixels over the total of pixels in the FLC dataset.
Available at: tinyurl.com/yy9rbbsu
08/15
SLIDE 9
Challenges of the FLC Dataset
Available at: tinyurl.com/yy9rbbsu
09/15
SLIDE 10
Tasks
Available at: tinyurl.com/yy9rbbsu
10/15
SLIDE 11
Experiments
Available at: tinyurl.com/yy9rbbsu
11/15
SLIDE 12
Experiments
Available at: tinyurl.com/yy9rbbsu
12/15
SLIDE 13
Experiments
Available at: tinyurl.com/yy9rbbsu
13/15
SLIDE 14
Experiments
Available at: tinyurl.com/yy9rbbsu
14/15
SLIDE 15
Thank you!
Available at: tinyurl.com/yy9rbbsu
15/15
8-leaf clover →
In case you wonder...
SLIDE 16
Comparison to Other Datasets
Comparison of FLC to major visual recognition datasets. Club (♣) indicates that a dataset allows to study a recognition problem at a fine-grained level, triangle (Δ) indicates that the version of the problem is not fine-grained, and (×) indicates that a dataset does not allow to study a problem.
Available at: tinyurl.com/yy9rbbsu