This paper proposes a gradient-based feature selection approach for online boosting in computer vision.
Boosting has been widely applied in computer vision, especially after Viola and Jones's seminal work. The marriage of rectangular features and integral-image- enabled fast computation makes boosting attractive for many vision applications; however, this popular way of applying boosting normally employs an exhaustive feature selection scheme from a very large hypothesis pool, which results in a less-efficient learning process. Furthermore, this poses additional constraint on applying boosting in an online fashion, where feature re-selection is often necessary because of varying data characteristic, but impractical due to the huge hypothesis pool. The authors’ approach iteratively updates each feature using the gradient descent, by minimizing the weighted least square error between the estimated feature response and the true label. In addition, this approach integrates the gradient-based feature selection with an online boosting framework. This new online boosting algorithm not only provides an efficient way of updating the discriminative feature set, but also presents a unified objective for both feature selection and weak classifier updating. Experiments on the person detection and tracking applications demonstrate the effectiveness of the authors’ proposal. (Publisher abstract provided)
Similar Publications
- Exploring CLIP for Real World, Text-based Image Retrieval
- Examining the Black Box: A Formative and Evaluability Assessment of Cross-Sectoral Approaches for Intimate Partner and Sexual Violence
- Lessons Learned Implementing Gunshot Detection Technology: Results of a Process Evaluation in Three Major Cities