Download presentation
Presentation is loading. Please wait.
Published byHope Francis Modified over 9 years ago
1
Model comparison and challenges II Compositional bias of salient object detection benchmarking Xiaodi Hou K-Lab, Computation and Neural Systems California Institute of Technology for the Crash Course on Visual Saliency Modeling: Behavioral Findings and Computational Models CVPR 2013
2
Schedule
3
On detecting salient objects Learning to Detect A Salient Object [Liu et. al., CVPR 07] Frequency-tuned Salient Region Detection [Achanta et. al., CVPR 09]
4
The progress! Some top performers: – [PCA] – [PCA] What makes a patch distinct [Margolin et. al., CVPR 13] – [SF] – [SF]Saliency filters [Perazzi et. al., CVPR 12]: F-Measure: 0.84 – [GC]/[GC-seg] – [GC]/[GC-seg]Global contrast-based salient region detection [Cheng et. al., CVPR 11] F-Measure: 0.75 – [FT] – [FT] Frequency Tuned Salient Region Detection [Achanta et. a.l., CVPR 09] : 0.65 by [Achanta et. al., CVPR 09]. Image from [Perazzi et. al., CVPR 2012]
5
The progress? Salient objects in PASCAL VOC? – 850 images from VOC 2013 validation set. – Intersection of main challenge and segmentation challenge. – Answers more questions: Where is your algorithm (in salient object detection)? Where is salient object detection (in computer vision). Where is salient object detection (in computer vision).
6
The progress FT: 0.28 GC: 0.39 SF: 0.35 PCA: 0.40 GC-seg: 0.38 55% performance drop!!
7
The arguments No!! These objects are not salient! images with salient objects Our algorithm works on images with salient objects only!
8
The paradox of salient object detection But hey, what is a “salient object”?
9
COMPOSITIONAL BIAS
10
Before we proceed… Google Image Search: “science” – Rutherford atomic model (9) – Test tubes (10) – Microscopes (4) – Double helix (3) – Old guys with crazy hair and glasses (3)
11
How to compose a biased salient object detection dataset Decide to build a new salient object dataset! So what is saliency? Searching for unambiguous examples of saliency… Found one! Add to my dataset! Job done! Let other people play with my dataset!
12
The compositional bias Compositional bias composition Compositional bias: Biases introduced during the composition of a dataset: – Exaggerating on stereotypical attributes. Limited variability in positive samples. Lack of negative samples at all. Unlike datasets in machine learning, where the dataset is the world, computer vision datasets are supposed to be a representation of the world. ---- [Torralba and Efros: Unbiased look at Dataset bias]
13
Compositional bias: the statistics Object number
14
Compositional bias: the statistics Object eccentricity
15
Compositional bias: the statistics Global foreground and background contrast
16
Compositional bias: the statistics Local foreground/background contrast (contour strength)
17
TOWARDS A BETTER SALIENT OBJECT DATASET
18
The new project salient object detection object detection Build a salient object detection dataset from a good object detection dataset (e.g. PASCAL VOC). Let the eye fixations pick up those salient objects!
19
Data collection (in process) SR Research EyeLink 1000 2-sec viewing time. “Free-viewing” instruction (will mention it later). 3 subjects (more subjects on the way).
20
What makes an object salient Unit conversion: – From fixation maps – To object fixation score sum of blurred fixation map intensity within the object mask.
21
Object size and saliency Large objects attract more fixations. Small objects receive denser fixations.
22
Object size and saliency
23
Objects, salient objects, and the most salient objects Salient objects: – Fixation score higher than mean (67.3% objects). Most salient objects: – Fixation score higher than mean*2 (27.8% objects). Image with fixationObject labelingSalient objectsMost salient object(s)
24
Salient objects and salient object detection Guess how does the algorithms perform on “salient objects” and “most salient objects”? On all objects: FT: 0.28 GC: 0.39 SF: 0.35 PC: 0.38
25
Testing on salient objects Salient objects on PASCAL VOC 60% performance drop!! FT: 0.22 GC: 0.35 SF: 0.31 PCA: 0.38 GC-seg: 0.39
26
Testing on most salient objects Most salient objects on PASCAL VOC FT: 0.10 GC: 0.20 SF: 0.15 PCA: 0.26 GC-seg: 0.23 79.8% performance drop!!
27
Something is wrong, seriously!
28
DISCUSSIONS
29
The role of saliency in a visual system Bad performance because of boundary detection? Bad performance because of unpredictability of human “free will”?
30
Saliency as an oracle Oracle selecting the best segment – CPMC: 78% from 154 segments – gPB: 61% from 1286 segments * coverage = intersect/union
31
Saliency and tasks Build a salient object detection dataset from an egocentric object dataset. Let the eye-fixation speaks Eye Tracker Forward-looking Camera Learning to recognize daily actions using gaze, [Fathi et. al. ECCV 12]
32
What makes an object salient? TaskObjectSaliency Object in egocentric actions Fixated object == Manipulated object?
33
THANKS
34
Acknowledgement Joint work with Yin Li @ Gatech. Special thanks to Nathan Faivre for his kind help on eye tracking.
35
Open discussions
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.