# Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection

arXiv: https://arxiv.org/abs/2110.07511 · HTML: https://mlsanity.com/paper/2110.07511/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 62 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [End-to-end people detection in crowded scenes](https://mlsanity.com/paper/1506.04878/) (2015)
- [Multiple Instance Detection Network with Online Instance Classifier Refinement](https://mlsanity.com/paper/1704.00138/) (2017)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation](https://mlsanity.com/paper/1503.00848/) (2015)
- [Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks](https://mlsanity.com/paper/1512.04143/) (2015)
- [Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection](https://mlsanity.com/paper/2004.04725/) (2020)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection](https://mlsanity.com/paper/1909.04972/) (2019)
- [Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection](https://mlsanity.com/paper/2010.12023/) (2020)
- [Weakly Supervised Cascaded Convolutional Networks](https://mlsanity.com/paper/1611.08258/) (2016)
- [Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2106.04054/) (2021)
- [Min-Entropy Latent Model for Weakly Supervised Object Detection](https://mlsanity.com/paper/1902.06057/) (2019)
- [Semantic Object Parsing with Graph LSTM](https://mlsanity.com/paper/1603.07063/) (2016)
- [ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization](https://mlsanity.com/paper/1609.04331/) (2016)
- [SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection](https://mlsanity.com/paper/2006.12884/) (2020)
- [Weakly Supervised Object Detection with Segmentation Collaboration](https://mlsanity.com/paper/1904.00551/) (2019)
- [Dissimilarity Coefficient based Weakly Supervised Object Detection](https://mlsanity.com/paper/1811.10016/) (2018)
- [C-WSL: Count-guided Weakly Supervised Localization](https://mlsanity.com/paper/1711.05282/) (2017)
- [Object Instance Mining for Weakly Supervised Object Detection](https://mlsanity.com/paper/2002.01087/) (2020)
- [Attentive Contexts for Object Detection](https://mlsanity.com/paper/1603.07415/) (2016)

## Built on by (most cited first, 1 of 1)

- [Negative Prototypes Guided Contrastive Learning for WSOD](https://mlsanity.com/paper/2406.18576/) (2024)

## Abstract (arXiv)

Weakly supervised object detection (WSOD) has attracted more and more attention since it only uses image-level labels and can save huge annotation costs. Most of the WSOD methods use Multiple Instance Learning (MIL) as their basic framework, which regard it as an instance classification problem. However, these methods based on MIL tends to converge only on the most discriminate regions of different instances, rather than their corresponding complete regions, that is, insufficient integrity. Inspired by the habit of observing things by the human, we propose a new method by comparing the initial proposals and the extension ones to optimize those initial proposals. Specifically, we propose one new strategy for WSOD by involving contrastive proposal extension (CPE), which consists of multiple directional contrastive proposal extensions (D-CPE), and each D-CPE contains encoders based on LSTM network and corresponding decoders. Firstly, the boundary of initial proposals in MIL is extended to different positions according to well-designed sequential order. Then, CPE compares the extended proposal and the initial proposal by extracting the feature semantics of them using the encoders, and calculates the integrity of the initial proposal to optimize the score of the initial proposal. These contrastive contextual semantics will guide the basic WSOD to suppress bad proposals and improve the scores of good ones. In addition, a simple two-stream network is designed as the decoder to constrain the temporal coding of LSTM and improve the performance of WSOD further. Experiments on PASCAL VOC 2007, VOC 2012 and MS-COCO datasets show that our method has achieved the state-of-the-art results.