Large Scale Visual Recognition Challenge ILSVRC 2013 Detection spotlights Toronto A team Latent Hierarchical Model with GPU Inference for Object Detection Yukun Zhu Jun Zhu Alan Yuille UCLA Computer Vision Lab ID: 409621
Download Presentation The PPT/PDF document " 409621" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Large Scale Visual Recognition Challenge (ILSVRC) 2013:Detection spotlightsSlide2
Toronto A teamSlide3Slide4
Latent Hierarchical Model with GPU Inference for Object Detection
Yukun Zhu, Jun Zhu, Alan Yuille
UCLA Computer Vision Lab
ILSVRC 2013 Spotlight
Thank L. Zhu, Y. Chen, A. Yuille and W. Freeman for the
work
“
Latent hierarchical structural learning for object detection
”
in CVPR 2010.Slide5
Root-Part Configuration
Model for Horse
Model for Car
Hierarchical Model
Latent Hierarchical Model with GPU
Inference for Object DetectionSlide6
Latent Hierarchical Model with GPU Inference for Object Detection
The latent hierarchical model encoding holistic object and parts
w.r.t
. viewpoint variations
Support richer appearance features: HOG, color, etc.
Fast training with incremental concave-convex procedure (iCCCP) algorithmQuick model inference via GPU (CUDA) implementationSlide7
[1] Felzenszwalb P, McAllester D, Ramanan D, “A discriminatively trained, multiscale, deformable part model,” Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on. IEEE, 2008: 1-8.
[2]
Felzenszwalb P F, Girshick R B, McAllester D, “Cascade object detection with deformable part models,” Computer vision and pattern recognition (CVPR), 2010 IEEE conference on. IEEE, 2010: 2241-2248.
Latent Hierarchical Model with GPU
Inference for Object DetectionSlide8
ILSVRC2013 Task 1: DetectionTeam name: DeltaMembers: Che-Rung Lee, Hwann-Tzong
Chen,
Hao
-Ping Kang, Tzu-Wei Huang,
Ci
-Hong Deng, Hao-Che KaoNational Tsing Hua UniversitySlide9
Generic Object Detector
ConvNet
Multiclass Classifier
~ 15 proposals per image
each proposal gets one of the
(200+backgrounds) class-labels
Multiclass classifier: cuda-convnet [Krizhevsky et al.] Training: 590,000 bounding boxes, 3 days using 2 GPUs0.5 error rate for classifying the validation bounding boxesGeneric object d
etector:
“What
is an
object” + salient region segmentation
0.28
mAP
on the validation images (ignoring class labels)
Overall:
0.057
mAP
on validation data,
0.06
mAP
on test dataSlide10
8:30 Classification&localization
10:30
Detection
Noon Discussion panel14:00 Invited talk by Vittorio Ferrari: Auto-annotation and self-assessment in ImageNet14:40 Fine-Grained Challenge 2013
Agendahttp://www.image-net.org/challenges/LSVRC/2013/iccv2013
8:50
9:05
9:20
9:35
9:50
Spotlights
10:50
11:10
11:30
11:40
Spotlights