Multi Object Detection with YOLO on Artwork Dataset

GitHub - yihui-he/Objects-Detection-with-YOLO-on-Artwork-Dataset: Objects Detection with YOLO on Artwork Dataset ( you only look once system)

You can't perform that action at this time. You signed in with another tab or window. You signed out in another tab or window. Reload to refresh your session. Reload to refresh your session.

https://github.com/yihui-he/Objects-Detection-with-YOLO-on-Artwork-Dataset

Report_Yihui.pdf is my Report

code Folder include my codes

resource Folder are some references

Below are just some notes

writeup

dataset

features

partition

classification scheme

cross validation

precision vs recall

accuracy

lessons learned

#faster RCNN RCNN - Spatial pyramid pooling - Region proposal

useful link

Tutorial on Tools for Efficient Object Detection

segmentation

Kmeans

mean shift

Graph

If external diff > minimal internal, different graphs. Then run greedy based on edge weight 3 times for R,G,B. Gradually merge pixels.

Distance measure:

Nearest neghbor

8 neighbors around one pixel

Localization

SIFT

“neocognitron”

sliding window

bounding box regression

What is backgound windows?

use the pool5 features to compute a new bounding box? Make bbox bigger towards the ground truth.

detection

latent SVM

convNet

Classifier

softmax

KNN?

ablation study

pool5 is better than fc6 without fine-tuning fc sort of stands for domain specified knowledges

evaluation

mean average precision

detection analysis tool

visualization

using first layer

single out a feature and figure out all max response pictures

other approach

overfeat

spatial pyramid

RCNN main steps

Generate regions using selective search

Extract features on each region

classification on features

one class bounding box regression on features

non-maximum suppression http://videolectures.net/iccv2015_girshick_fast_r_cnn/