Multiple Instance Detection Network with Online Instance Classifier Refinement

Abstract

Of late, weakly supervised object detection is with great importance in object recognition. Based on deep learning, weakly supervised detectors have achieved many promising results. However, compared with fully supervised detection, it is more challenging to train deep network based detectors in a weakly supervised manner. Here we formulate weakly supervised detection as a Multiple Instance Learning (MIL) problem, where instance classifiers (object detectors) are put into the network as hidden nodes. We propose a novel online instance classifier refinement algorithm to integrate MIL and the instance classifier refinement procedure into a single deep network, and train the network end-to-end with only image-level supervision, i.e., without object location information. More precisely, instance labels inferred from weak supervision are propagated to their spatially overlapped instances to refine instance classifier online. The iterative instance classifier refinement procedure is implemented using multiple streams in deep network, where each stream supervises its latter stream. Weakly supervised object detection experiments are carried out on the challenging PASCAL VOC 2007 and 2012 benchmarks. We obtain 47% mAP on VOC 2007 that significantly outperforms the previous state-of-the-art.

Accepted by CVPR 2017, IEEE Conference on Computer Vision and Pattern Recognition 2017

References in corpus (5)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Multi-Scale Context Aggregation by Dilated Convolutions
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

Cited by in corpus (8)

• Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology
• Where are the Masks: Instance Segmentation with Image-level Supervision
• Collaborative Learning for Weakly Supervised Object Detection
• Angular Visual Hardness
• Min-max Entropy for Weakly Supervised Pointwise Localization
• Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection
• Weakly Supervised 3D Object Detection from Point Clouds
• Weakly Supervised Instance Segmentation by Deep Community Learning