Weakly supervised object detection using pseudo-strong labels
This work addresses the challenge of achieving satisfactory object detection results with weak supervision, which is incremental as it builds on existing weakly supervised methods by refining their outputs.
The paper tackles the problem of improving object detection performance using only image-level labels by proposing a framework that uses weakly supervised method outputs as pseudo-strong labels to train a strongly supervised model, achieving a mean average precision of 43.4% on PASCAL VOC 2007 compared to 39.5% for the previous best result.
Object detection is an import task of computer vision.A variety of methods have been proposed,but methods using the weak labels still do not have a satisfactory result.In this paper,we propose a new framework that using the weakly supervised method's output as the pseudo-strong labels to train a strongly supervised model.One weakly supervised method is treated as black-box to generate class-specific bounding boxes on train dataset.A de-noise method is then applied to the noisy bounding boxes.Then the de-noised pseudo-strong labels are used to train a strongly object detection network.The whole framework is still weakly supervised because the entire process only uses the image-level labels.The experiment results on PASCAL VOC 2007 prove the validity of our framework, and we get result 43.4% on mean average precision compared to 39.5% of the previous best result and 34.5% of the initial method,respectively.And this frame work is simple and distinct,and is promising to be applied to other method easily.