Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution
This addresses the problem of localizing objects in images without strong supervision for researchers in computer vision, but it is incremental as it builds on existing co-localization and detection methods.
The paper tackles image co-localization by learning a common object detector that mimics the confidence score distribution of a strongly supervised detector, using an entropy-based objective to enforce high scores on few proposals. The approach outperforms state-of-the-art methods, though no specific numbers are provided.
Given a set of images containing objects from the same category, the task of image co-localization is to identify and localize each instance. This paper shows that this problem can be solved by a simple but intriguing idea, that is, a common object detector can be learnt by making its detection confidence scores distributed like those of a strongly supervised detector. More specifically, we observe that given a set of object proposals extracted from an image that contains the object of interest, an accurate strongly supervised object detector should give high scores to only a small minority of proposals, and low scores to most of them. Thus, we devise an entropy-based objective function to enforce the above property when learning the common object detector. Once the detector is learnt, we resort to a segmentation approach to refine the localization. We show that despite its simplicity, our approach outperforms state-of-the-art methods.