Learning relative features through adaptive pooling for image classification

Ming Shao, Sheng Li, Tongliang Liu, Dacheng Tao, Thomas S. Huang, Yun Fu

Research output: Contribution to journalConference articlepeer-review


Bag-of-Feature (BoF) representations and spatial constraints have been popular in image classification research. One of the most successful methods uses sparse coding and spatial pooling to build discriminative features. However, minimizing the reconstruction error by sparse coding only considers the similarity between the input and codebooks. In contrast, this paper describes a novel feature learning approach for image classification by considering the dissimilarity between inputs and prototype images, or what we called reference basis (RB). First, we learn the feature representation by max-margin criterion between the input and the RB. The learned hyperplane is stored as the relative feature. Second, we propose an adaptive pooling technique to assemble multiple relative features generated by different RBs under the SVM framework, where the classifier and the pooling weights are jointly learned. Experiments based on three challenging datasets: Caltech-101, Scene 15 and Willow-Actions, demonstrate the effectiveness and generality of our framework.

Original languageEnglish (US)
Article number6890269
JournalProceedings - IEEE International Conference on Multimedia and Expo
Issue numberSeptmber
StatePublished - Sep 3 2014
Event2014 IEEE International Conference on Multimedia and Expo, ICME 2014 - Chengdu, China
Duration: Jul 14 2014Jul 18 2014


  • Image classification
  • adaptive pooling
  • feature learning
  • reference basis

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications


Dive into the research topics of 'Learning relative features through adaptive pooling for image classification'. Together they form a unique fingerprint.

Cite this