Timezone: »

A Maximum Margin Multi-Instance Learning Framework for Image Categorization
Hua Wang · Heng Huang · Farhad Kamangar · Feiping Nie · Chris Ding

Mon Dec 12 10:00 AM -- 02:59 PM (PST) @ None #None

Multi-instance learning (MIL) considers input as bags of instances, in which labels are assigned to the bags. MIL is useful in many real-world applications. For example, in image categorization semantic meanings (labels) of an image mostly arise from its regions (instances) instead of the entire image (bag). Existing MIL methods typically build their models using the Bag-to-Bag (B2B) distance, which are often computationally expensive and may not truly reflect the semantic similarities. To tackle this, in this paper we approach MIL problems from a new perspective using the Class-to-Bag (C2B) distance, which directly assesses the relationships between the classes and the bags. Taking into account the two major challenges in MIL, high heterogeneity on data and weak label association, we propose a novel Maximum Margin Multi-Instance Learning (M3I) approach to parameterize the C2B distance by introducing the class specific distance metrics and the locally adaptive significance coefficients. We apply our new approach to the automatic image categorization tasks on three (one single-label and two multi-label) benchmark data sets. Extensive experiments have demonstrated promising results that validate the proposed method.

Author Information

Hua Wang (Univ. of Texas at Arlington)
Heng Huang (Electrical and Computer Engineering University of Pittsburgh)
Farhad Kamangar (University of Texas at Arlington)
Feiping Nie (University of Texas Arlington)
Chris Ding (University of Texas at Arlington)

More from the Same Authors