Efficient PSD Constrained Asymmetric Metric Learning for Person Re-identification

Problems with existing metric learning methods

• Applying PSD: expensive
• No PSD: noisy
• pos/neg samples: largely unbalanced

Contributions

• APG solution to the PSD constrained logistic metric learning problem
• Asymmetric pos/neg sample weights to balance pos/neg costs

Advantages

• PSD+APG leads to low rank and smooth metric
• APG solution is fast in convergence
• PSD and asymmetric weights lead to notable improvements

Download

• Download: MLAPG.zip
• CMC curves: cmc_curves.zip

Results

Fig. 1. Fast rank shrinkage.	Fig. 2. Effect of low rank selection.
Fig. 3. Improvement by PSD.	Fig. 4. Improvement by weighting.

Table 1. Summary of results (%) for the proposed MLAPG algorithm

Note: CMC curves of the proposed MLAPG algorithm can be downloaded in cmc_curves.zip

Contact:

National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences.

References:

[1]Shengcai Liao and Stan Z. Li, “Efficient PSD Constrained Asymmetric Metric Learning for Person Re-identification.” In IEEE International Conference on Computer Vision (ICCV 2015), December 11-18, Santiago, Chile, 2015. [pdf] [poster]

Last updated: Dec. 8, 2015