masc.cs.gmu.edu Sparselet Models for Efficient Multiclass Object Detection Present by Guilin Liu
Jan 05, 2016
masc.cs.gmu.edu
Sparselet Models for Efficient Multiclass Object Detection
Present by Guilin Liu
Key Idea
Use sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements.
Reconstruction of original part filter responses via sparse matrix-vector product
GPU implementation
masc.cs.gmu.edu
Problem/motivation
Individual model become redundant as the number of categories grow------Sparse Coding
Learn basis parts so reconstructing the response of a target model is efficient
masc.cs.gmu.edu
Overview
masc.cs.gmu.edu
System pipeline
masc.cs.gmu.edu
Overview
masc.cs.gmu.edu
1. Sparse reconstruction
Find a generic dictionary approximate the part filters pooled from a set of training models, subject to a sparsity constraint
masc.cs.gmu.edu
1. Sparse reconstruction
Solve the optimization problem busing the Orthogonal Matching Pursuit algorithm(OMP)Two steps:a.Fixed D, optimize αb.Fixex α, optimize D
masc.cs.gmu.edu
2. Precomputation & efficient reconstruction
masc.cs.gmu.edu
2. Precomputation & efficient reconstruction
1. Precompute convolutions for all sparselets2. Approximate t convolution response by linear
combination of the activation vectors from step 1.
masc.cs.gmu.edu
3. Implementation(CPU, GPU)
The independence and parallelizablity of:Convolution, HOG computation and distance transforms
1. CPU implementation: CPU cach miss limited the overall speedup
2. GPU implementation: a. Compute image pyramids and HOG featuresb. Compute filter responses to root, part or part basis
filter
masc.cs.gmu.edu
4. Experiments
1. Reconstruction error
masc.cs.gmu.edu
4. Experiments
2. held-out evaluation
masc.cs.gmu.edu
4. Experiments
3. Average precision
masc.cs.gmu.edu