COS429 FINAL PROJECT Object Detection on PASCAL VOC 2012 Yinda - - PowerPoint PPT Presentation

▶
cos429 final project
SMART_READER_LITE
LIVE PREVIEW

COS429 FINAL PROJECT Object Detection on PASCAL VOC 2012 Yinda - - PowerPoint PPT Presentation

Feb 17, 2024 274 likes •460 views

COS429 FINAL PROJECT Object Detection on PASCAL VOC 2012 Yinda Zhang @ CS 105, Dec 18, 2015 WHAT TO DO Classification: Cat Detection: Cat + Bounding box CHALLENGING Appearance Viewpoint Occlusion Multiple objects MOST

slide-1
SLIDE 1

COS429 FINAL PROJECT

Object Detection on PASCAL VOC 2012 Yinda Zhang @ CS 105, Dec 18, 2015

slide-2
SLIDE 2

WHAT TO DO

Classification: Cat Detection: Cat + Bounding box

slide-3
SLIDE 3

CHALLENGING

  • Appearance
  • Viewpoint
  • Occlusion
  • Multiple objects
slide-4
SLIDE 4

MOST EXTREME CASE

slide-5
SLIDE 5

EVALUATE

slide-6
SLIDE 6

EVALUATE

slide-7
SLIDE 7

EVALUATE

Intersection Union > 0.5?

slide-8
SLIDE 8

AVERAGE PRECISION

Recall Precision Precision: % of detection that are correct; Recall: % of ground truth detected AP mAP: average of AP over multiple classes

slide-9
SLIDE 9

DATASET

  • 20 classes, 11530 images with 27450 objects labelled
  • Development toolkit
slide-10
SLIDE 10

BASELINE

  • Output center box, always classify as “cat”
  • Run image classification, and randomly generate a box
  • Sliding window: a window slides in image and perform

classification for each location (DPM)

  • Region proposal: generate some regions from image, and

perform classification on each.

slide-11
SLIDE 11

BASELINE

  • YOLO, http://arxiv.org/abs/1506.02640
  • ResidualNet, http://arxiv.org/abs/1512.03385
  • Faster RCNN, http://arxiv.org/abs/1506.01497
  • Fast RCNN, http://arxiv.org/abs/1504.08083
  • Inside-Outside Net, http://www.seanbell.ca/tmp/ion-bell2015.pdf
  • Exemplar SVM, http://www.cs.cmu.edu/~tmalisie/projects/iccv11/
  • DPM, http://www.cs.berkeley.edu/~rbg/latent/
  • RCNN, http://arxiv.org/abs/1311.2524
slide-12
SLIDE 12

TODO

✓Implement a detection system

  • From scratch: your own idea or previous work
  • Improve upon released code of previous work
  • “script_train.m”
  • load data, perform training, and save model
  • “script_test.m”
  • load data and model, perform testing, and visualize result
slide-13
SLIDE 13

TODO

✓Report

  • CVPR format: http://www.pamitc.org/cvpr16/

author_guidelines.php

  • Group members, name + ID
  • Methods
  • Evaluation: APs, mAP

, PR curve, succ/fail detection result

  • Discussion
  • Job Assignment: Who did what
slide-14
SLIDE 14

TODO

✓Evaluate on eval set. Only on test set for extra bonus ✓Proposal deadline: Dec 18 ✓Project deadline: Jan 12 ✓Name your submission

  • xj_yindaz_mingru_cos429fp.pdf
  • xj_yindaz_mingru_cos429fp.zip
slide-15
SLIDE 15

GRADING

✓Implementation (40%)

  • The amount of working codes
  • The data/result visualization/analysis
  • Any existing codes does not count

✓Correctness (20%)

  • “script_train.m” and “script_test.m” are runnable
  • mAP > 20%
slide-16
SLIDE 16

GRADING

✓Report Writing (10%)

  • Right format
  • All required contents

✓Code Clearness (10%)

  • Codes is clean, well-organized, easy to read

✓Algorithm Novelty (10%)

  • Create your own idea
  • Improve your baseline by something
slide-17
SLIDE 17

GRADING

✓Performance (10%)

  • Rank mAP on eval set from all groups

✓Extra Bonus (a looooot of marks)

  • If your mAP is above 70%
  • Evaluate on testing set as a proof