Timezone: »

Bilinear classifiers for visual recognition
Hamed Pirsiavash · Deva Ramanan · Charless Fowlkes

Wed Dec 09 07:00 PM -- 11:59 PM (PST) @

We describe an algorithm for learning bilinear SVMs. Bilinear classifiers are a discriminative variant of bilinear models, which capture the dependence of data on multiple factors. Such models are particularly appropriate for visual data that is better represented as a matrix or tensor, rather than a vector. Matrix encodings allow for more natural regularization through rank restriction. For example, a rank-one scanning-window classifier yields a separable filter. Low-rank models have fewer parameters and so are easier to regularize and faster to score at run-time. We learn low-rank models with bilinear classifiers. We also use bilinear classifiers for transfer learning by sharing linear factors between different classification tasks. Bilinear classifiers are trained with biconvex programs. Such programs are optimized with coordinate descent, where each coordinate step requires solving a convex program - in our case, we use a standard off-the-shelf SVM solver. We demonstrate bilinear SVMs on difficult problems of people detection in video sequences and action classification of video sequences, achieving state-of-the-art results in both.

Author Information

Hamed Pirsiavash (University of California Irvine)
Deva Ramanan
Charless Fowlkes (UC Irvine)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors