Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection
This addresses a key challenge in weakly supervised object detection for computer vision applications, though it appears incremental as it builds on existing multiple instance learning methods.
The paper tackles the problem of weakly supervised object detection, where detectors often converge to discriminative parts rather than whole objects, by proposing a discovery-and-selection approach fused with multiple instance learning (DS-MIL) that finds and selects optimal solutions from local minima, resulting in state-of-the-art performance on benchmarks.
Weakly supervised object detection (WSOD) is a challenging task that requires simultaneously learn object classifiers and estimate object locations under the supervision of image category labels. A major line of WSOD methods roots in multiple instance learning which regards images as bags of instances and selects positive instances from each bag to learn the detector. However, a grand challenge emerges when the detector inclines to converge to discriminative parts of objects rather than the whole objects. In this paper, under the hypothesis that optimal solutions are included in local minima, we propose a discovery-and-selection approach fused with multiple instance learning (DS-MIL), which finds rich local minima and select optimal solution from multiple local minima. To implement DS-MIL, an attention module is proposed so that more context information can be captured by feature maps and more valuable proposals can be collected during training. With proposal candidates, a selection module is proposed to select informative instances for object detector. Experimental results on commonly used benchmarks show that our proposed DS-MIL approach can consistently improve the baselines, reporting state-of-the-art performance.