Abstract
Learning visual concepts from images is an important yet challenging problem in computer vision and multimedia research areas. Multiple kernel learning (MKL) methods have shown great advantages in visual concept learning. As a visual concept often exhibits great appearance variance, a canonical MKL approach may not generate satisfactory results when a uniform kernel combination is applied over the input space. In this paper, we propose a per-sample multiple kernel learning (PS-MKL) approach to take into account intraclass diversity for improving discrimination. PS-MKL determines sample-wise kernel weights according to kernel functions and training samples. Kernel weights as well as kernel-based classifiers are jointly learned. For efficient learning, PS-MKL employs a sample selection strategy. Extensive experiments are carried out over three benchmarking datasets of different characteristics including Caltech101, WikipediaMM, and Pascal VOC'07. PS-MKL has achieved encouraging performance, comparable to the state of the art, which has outperformed a canonical MKL.
Highlights
Visual concept learning is an important topic in image and video indexing and retrieval
We propose a per-sample multiple kernel learning (PS-Multiple kernel learning (MKL)) approach to take into account intraclass diversity for improving discrimination
Instead of a uniform kernel combination in a canonical MKL, we propose a samplebased formulation of MKL, namely, PS-MKL
Summary
Visual concept learning is an important topic in image and video indexing and retrieval. Its image instances are often assumed to produce similarity in different attributes (e.g., scale, shape, color, and texture). An instance of a concept may produce various appearances due to the imaging issues like viewpoint, luminance, or occlusion. Different instances of a concept could produce intra-class variance in appearance (see Figure 1(b)) from the pattern classification point of view. In other words, training instances of a visual concept could be redundant while in different feature spaces a bag of instances would produce distinct intra-class variations.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
