# Soft Proposal Networks for Weakly Supervised Object Localization

arXiv: https://arxiv.org/abs/1709.01829 · HTML: https://mlsanity.com/paper/1709.01829/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2017.

## Built on by (most cited first, 21 of 21)

- [SOON: Scenario Oriented Object Navigation with Graph-based Exploration](https://mlsanity.com/paper/2103.17138/) (2021)
- [Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation](https://mlsanity.com/paper/2210.07506/) (2022)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Points as Queries: Weakly Semi-supervised Object Detection by Points](https://mlsanity.com/paper/2104.07434/) (2021)
- [ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues](https://mlsanity.com/paper/2201.06696/) (2022)
- [LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.05291/) (2021)
- [Group R-CNN for Weakly Semi-supervised Object Detection with Points](https://mlsanity.com/paper/2205.05920/) (2022)
- [RICA2: Rubric-Informed, Calibrated Assessment of Actions](https://mlsanity.com/paper/2408.02138/) (2024)
- [TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2208.14542/) (2022)
- [Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues](https://mlsanity.com/paper/2402.00281/) (2024)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2303.09044/) (2023)
- [Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey](https://mlsanity.com/paper/2105.12694/) (2021)
- [Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels](https://mlsanity.com/paper/2202.07422/) (2022)
- [An Efficient Ensemble Explainable AI (XAI) Approach for Morphed Face Detection](https://mlsanity.com/paper/2304.14509/) (2023)
- [Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos](https://mlsanity.com/paper/2407.06018/) (2024)
- [Fine-Grained Attention for Weakly Supervised Object Localization](https://mlsanity.com/paper/2104.04952/) (2021)
- [Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis](https://mlsanity.com/paper/2109.07509/) (2021)
- [Guided Generative Models using Weak Supervision for Detecting Object Spatial Arrangement in Overhead Images](https://mlsanity.com/paper/2112.05786/) (2021)
- [UnseenNet: Fast Training Detector for Any Unseen Concept](https://mlsanity.com/paper/2203.08759/) (2022)

## Abstract (arXiv)

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.