Object Instance Mining for Weakly Supervised Object Detection
This work addresses the issue of incomplete object detection in WSOD for computer vision applications, representing an incremental improvement over prior methods.
The paper tackles the problem of weakly supervised object detection (WSOD) where existing methods often miss less discriminative object instances, leading to degraded performance. It introduces an object instance mining (OIM) framework that detects all possible instances using spatial and appearance graphs, achieving improved results on VOC 2007 and 2012 databases.
Weakly supervised object detection (WSOD) using only image-level annotations has attracted growing attention over the past few years. Existing approaches using multiple instance learning easily fall into local optima, because such mechanism tends to learn from the most discriminative object in an image for each category. Therefore, these methods suffer from missing object instances which degrade the performance of WSOD. To address this problem, this paper introduces an end-to-end object instance mining (OIM) framework for weakly supervised object detection. OIM attempts to detect all possible object instances existing in each image by introducing information propagation on the spatial and appearance graphs, without any additional annotations. During the iterative learning process, the less discriminative object instances from the same class can be gradually detected and utilized for training. In addition, we design an object instance reweighted loss to learn larger portion of each object instance to further improve the performance. The experimental results on two publicly available databases, VOC 2007 and 2012, demonstrate the efficacy of proposed approach.