0%

(CVPR 2017) Improving pairwise ranking for multi-label image classification

Posted on In ,

Keyword [Pairwise Ranking]

Li Y, Song Y, Luo J. Improving pairwise ranking for multi-label image classification[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 3617-3625.8.


1. Overview

1.1. Motivation

  • hinge loss is non-smooth and difficult to optimize
  • simple heuristics (top-k, threshhold) limits the use in the real world

In this paper,

  • propose smooth pairwise ranking loss
  • incorporate label decision into model

1.2.1. Objective

  • exact match


  1. Y^. predicted labels of i-th sample
  2. Y. GT

  • Hamming distance



  • Ranking objective




2. Algorithm



  • f. label prediction, d–>K (K. all labels)
  • g. label decision, K–>k (k＜K)

2.1. Label Prediction

2.1.1. Pairwise Loss (PWE)



2.1.2. Log-Sum-Exp



  • sample at most t pairs


2.2. Label Decision

  • estimate label count
  • estimate optimal thresholds for each class
    • g. MLP on top of f’(x) (final CNN layer) (FC-ReLU, FC-ReLU) + two different branch

2.2.1. Label Count Estimation



  • n-way classification
  • Cross Entropy

2.2.2. Threshold Estimation



2.3. Details

  • label prediction model
    • VGG16 replace Softmax loss with LSEP loss
    • finetune 10 epoches
  • label decision model
    • maximum number count = 4
    • first FC-100, second FC-10
    • count FC-4, threshold FC-14


3. Experiments