10
CS-F441: S ELECTED TOPICS FROM COMPUTER S CIENCE (DEEP L EARNING FOR NLP & CV) Lecture-KT-14: Segmentation (U-Net), Object Detection (Yolo) Dr. Kamlesh Tiwari, Assistant Professor, Department of Computer Science and Information Systems, BITS Pilani, Rajasthan-333031 INDIA Nov 20, 2019 (Campus @ BITS-Pilani July-Dec 2019)

CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

  • Upload
    others

  • View
    2

  • Download
    0

Embed Size (px)

Citation preview

Page 1: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

CS-F441: SELECTED TOPICS FROM COMPUTER

SCIENCE (DEEP LEARNING FOR NLP & CV)

Lecture-KT-14: Segmentation (U-Net), Object Detection (Yolo)

Dr. Kamlesh Tiwari,Assistant Professor,

Department of Computer Science and Information Systems,BITS Pilani, Rajasthan-333031 INDIA

Nov 20, 2019 (Campus @ BITS-Pilani July-Dec 2019)

Page 2: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

Segmentation

ISBI challenge for segmentation of neuronal structures in electronmicroscopic stacksWorks with very few training images (30/application) and touchingboundary. Yield more precise segmentationData augmentation is essential (mainly shift, rotation and elasticdeformation)

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 2 / 8

Page 3: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

U-Net1

ISBI DIC-HeLa achieved 77.6% iou as compared to 46.0% secondISBI Cell tracking 2015, achieved 92% IoU as compared to 83%second

1Cite 9576 O. Ronneberger and P.Fischer and T. Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation,

Medical Image Computing and Computer-Assisted Intervention (MICCAI), LNCS-9351, pages 234–241, Springer-2015

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 3 / 8

Page 4: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

Object Detection

What is there andwhere?

Deformative PartModel, andF-RCNN

Apply the model to an image at multiple locations and scales.High scoring regions are considered detections.

Yolo: apply a single neural network to the full image that divides it intoregions and predicts bounding boxes and probabilities for each region

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 4 / 8

Page 5: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

Object Detection

What is there andwhere?

Deformative PartModel, andF-RCNN

Apply the model to an image at multiple locations and scales.High scoring regions are considered detections.

Yolo: apply a single neural network to the full image that divides it intoregions and predicts bounding boxes and probabilities for each region

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 4 / 8

Page 6: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

Object Detection

What is there andwhere?

Deformative PartModel, andF-RCNN

Apply the model to an image at multiple locations and scales.High scoring regions are considered detections.

Yolo: apply a single neural network to the full image that divides it intoregions and predicts bounding boxes and probabilities for each region

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 4 / 8

Page 7: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

Yolo 2

Conditional probability mapSee https://pjreddie.com/darknet/yolo/

2Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only look once: Unified,

real-time object detection, IEEE conference on computer vision and pattern recognition (CVPR), pages 779–788, 2016

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 5 / 8

Page 8: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

Yolo

S × S segments, gives B bounding boxes with confidence, and Cclass probabilities. So S × S × (B × 5 + C) values. S:7, B:2, C:20

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 6 / 8

Page 9: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

Yolo

It is fastSpeed comes at the price of accuracy. Improved to 69%Generalizes wellLatest version YOLOv3 2018

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 7 / 8

Page 10: CS-F441: Selected Topics from Computer Science (Deep ... › dl › lecture-12-kt-cv.pdf2 Cite 6375 Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali, You only

Thank You!

Thank you very much for your attention3 !

Queries ?

3Credit: https://www.youtube.com/watch?v=NM6lrxy0bxs

STCS-DL4NLP&CV (CS-F441) Campus @ BITS-Pilani Lecture-KT-14 (Nov 20, 2019) 8 / 8