Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm

Abstract

Object detection when provided image-level labels instead of instance-level labels (i.e., bounding boxes) during training is an important problem in computer vision, since large scale image datasets with instance-level labels are extremely costly to obtain. In this paper, we address this challenging problem by developing an Expectation-Maximization (EM) based object detection method using deep convolutional neural networks (CNNs). Our method is applicable to both the weakly-supervised and semi-supervised settings. Extensive experiments on PASCAL VOC 2007 benchmark show that (1) in the weakly supervised setting, our method provides significant detection performance improvement over current state-of-the-art methods, (2) having access to a small number of strongly (instance-level) annotated images, our method can almost match the performace of the fully supervised Fast RCNN. We share our source code at https://github.com/ZiangYan/EM-WSD.

9 pages

References in corpus (7)

• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Rich feature hierarchies for accurate object detection and semantic segmentation
• ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
• Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning
• Weakly supervised object detection using pseudo-strong labels

Cited by in corpus (10)

• Weakly and Semi Supervised Detection in Medical Imaging via Deep Dual Branch Net
• Interpolation-based semi-supervised learning for object detection
• Collaborative Learning for Weakly Supervised Object Detection
• Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark
• Points as Queries: Weakly Semi-supervised Object Detection by Points
• Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection
• A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision
• One-Click Annotation with Guided Hierarchical Object Detection
• Improving Object Detection with Selective Self-supervised Self-training
• EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement