Soft Proposal Networks for Weakly Supervised Object Localization

Abstract

Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training. Object proposal is an effective component in localization, but often computationally expensive and incapable of joint optimization with some of the remaining modules. In this paper, to the best of our knowledge, we for the first time integrate weakly supervised object proposal into convolutional neural networks (CNNs) in an end-to-end learning manner. We design a network component, Soft Proposal (SP), to be plugged into any standard convolutional architecture to introduce the nearly cost-free object proposal, orders of magnitude faster than state-of-the-art methods. In the SP-augmented CNNs, referred to as Soft Proposal Networks (SPNs), iteratively evolved object proposals are generated based on the deep feature maps then projected back, and further jointly optimized with network parameters, with image-level supervision only. Through the unified learning process, SPNs learn better object-centric filters, discover more discriminative visual evidence, and suppress background interference, significantly boosting both weakly supervised object localization and classification performance. We report the best results on popular benchmarks, including PASCAL VOC, MS COCO, and ImageNet.

ICCV 2017

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Going Deeper with Convolutions
• Object Detectors Emerge in Deep Scene CNNs
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

Cited by in corpus (11)

• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• Weakly Supervised Instance Segmentation using Class Peak Response
• SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images
• Attention-based Dropout Layer for Weakly Supervised Object Localization
• Inter-Image Communication for Weakly Supervised Localization
• C-WSL: Count-guided Weakly Supervised Localization
• Learning Intelligent Dialogs for Bounding Box Annotation
• LID 2020: The Learning from Imperfect Data Challenge Results
• Tell Me What They're Holding: Weakly-supervised Object Detection with Transferable Knowledge from Human-object Interaction
• AutoLoc: Weakly-supervised Temporal Action Localization
• W-TALC: Weakly-supervised Temporal Activity Localization and Classification