Density-Based Region Search with Arbitrary Shape for Object Localization
This addresses a specific issue in weakly-supervised object localization for computer vision applications, offering a novel approach to handle arbitrary shapes, but it is incremental as it builds on existing region search methods.
The paper tackles the problem of object localization where traditional region search methods fail when classifier scores are mostly positive, leading to meaningless results by localizing nearly entire images. It proposes LS-MWCS, which searches for regions with the densest scores rather than maximal scores, achieving superior performance in weakly-supervised object localization compared to state-of-the-art methods.
Region search is widely used for object localization. Typically, the region search methods project the score of a classifier into an image plane, and then search the region with the maximal score. The recently proposed region search methods, such as efficient subwindow search and efficient region search, %which localize objects from the score distribution on an image are much more efficient than sliding window search. However, for some classifiers and tasks, the projected scores are nearly all positive, and hence maximizing the score of a region results in localizing nearly the entire images as objects, which is meaningless. In this paper, we observe that the large scores are mainly concentrated on or around objects. Based on this observation, we propose a method, named level set maximum-weight connected subgraph (LS-MWCS), which localizes objects with arbitrary shapes by searching regions with the densest score rather than the maximal score. The region density can be controlled by a parameter flexibly. And we prove an important property of the proposed LS-MWCS, which guarantees that the region with the densest score can be searched. Moreover, the LS-MWCS can be efficiently optimized by belief propagation. The method is evaluated on the problem of weakly-supervised object localization, and the quantitative results demonstrate the superiorities of our LS-MWCS compared to other state-of-the-art methods.