![Datasets
● [Try] Collect new dataset according to task.
● [Try] Get labels as accurate as possible.
● If not, use public datasets:
○ MSCOCO: 80 objects, 300K images, 5 captions per image.
○ Pascal VOC: 20 objects, ~20K images
○ LSVRC: 200 objects, ~470K images](https://image.slidesharecdn.com/tmlk172-170303075210/85/Image-Object-Detection-Pipeline-16-320.jpg)
![Datasets
● [Try] Collect new dataset according to task.
● [Try] Get labels as accurate as possible.
● If not, use public datasets:
○ MSCOCO: 80 objects, 300K images, 5 captions per image.
○ Pascal VOC: 20 objects, ~20K images
○ LSVRC: 200 objects, ~470K images](https://image.slidesharecdn.com/tmlk172-170303075210/75/Image-Object-Detection-Pipeline-16-2048.jpg)
Uploaded byAbhinav Dadhich
Image Object Detection Pipeline
The document discusses object detection pipelines. It begins by defining object detection as identifying objects in images and locating them with bounding boxes. The main components of an object detection pipeline are datasets, preprocessing, model selection and training, testing and evaluation. Popular models discussed are Faster R-CNN, R-FCN, and SSD which use deep convolutional neural networks as feature extractors and classifiers. Key evaluation metrics are mean average precision and prediction time/memory usage. Popular datasets mentioned are MSCOCO, Pascal VOC, and LSVRC. The document provides information on preprocessing, training including fine-tuning pre-trained models, and codes/models available on GitHub.
More Related Content
![[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection](https://cdn.slidesharecdn.com/ss_thumbnails/yolo-170616085751-thumbnail.jpg?width=600ounds&width=560&fit=bounds)
Similar to Image Object Detection Pipeline
Image Object Detection Pipeline
- 1. Object Detection Pipeline AbhinavDadhich, ABEJA, Inc. Tokyo Machine Learning Kitchen, 2017
- 2. Outline 1. What isObject Detection? Components? 2. Models for detection 3. Train, Test & Evaluate 4. FAQs
- 3. Object Detection http://cs231n.stanford.edu/slides/winter1516_lecture8.pdf Q: Whatobject is in image? A: Cat
- 4. Object Detection http://cs231n.stanford.edu/slides/winter1516_lecture8.pdf Q: Wherethe object is in image? A: bounding box or coordinates
- 5.
- 6. Components of a Detection ●Dataset of images and target labels ● Pre-Processing images and labels ● Model selection and modifications ● Training ● Testing and Evaluation ● Deploying final model
- 7.
- 8. Why Deep NeuralNetwork? “Fast R-CNN” Ross Girshick, ICCV’15
- 9. Model Architecture Feature Extractor Classifier Object Classification Bounding Box DeepCNN Architecture ● VGG ● Inception ● Resnet
- 10. Faster Region basedConvNets (Faster-RCNN) Girshick et al. ICCV 2015. Fig: Huang et al. 2016, arXiv:1611.10012v1 ● 2 Step Process ● Higher Accuracy ● Slower per sample prediction wrt similar models. ● Large image size
- 11. Region based FullyConvolutional Network(R-FCN) Dai et al. , NIPS 2016. ● 2 Step Process ● Faster per sample prediction time wrt Faster-RCNN Fig: Huang et al. 2016, arXiv:1611.10012v1
- 12. Single Shot Detector(SSD) Liuet al. , ECCV 2016 ● 1 step Process ● Faster per sample prediction time ● Small images, large objects Fig: Huang et al. 2016, arXiv:1611.10012v1
- 13. Training ● Pre-trained modelsare available for major deep learning frameworks. ● Fine tune existing model Feature Layers CNNs FCs Classification Layers
- 14. Training ● Pre-trained modelsare available for major deep learning frameworks. ● Fine tune existing model, re-initializing output layers. Feature Layers CNNs FCs Re-initialized Classification Layers
- 15. Evaluation Metrics &Tests ● Mean Average Precision(mAP): ○ Thresholding based on Intersection over Union(IoU) score. ○ Average over all class predictions. ○ Higher is better. ● Prediction Time : pre-processing + prediction time per image ● Memory Usage : model’s gpu/cpu memory usage while prediction
- 16. Datasets ● [Try] Collectnew dataset according to task. ● [Try] Get labels as accurate as possible. ● If not, use public datasets: ○ MSCOCO: 80 objects, 300K images, 5 captions per image. ○ Pascal VOC: 20 objects, ~20K images ○ LSVRC: 200 objects, ~470K images
- 17. Pre-processing ● Image resizing. ●Image pixel normalization. ● Data Augmentation: ○ Flip ○ Random rotations
- 18. Codes and Pre-trainedModels ● Faster-RCNN: https://github.com/rbgirshick/py-faster-rcnn (Caffe) ● R-FCN : https://github.com/Orpine/py-R-FCN (Caffe) ● SSD: https://github.com/weiliu89/caffe/tree/ssd (Caffe)
- 19.