# TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection

arXiv: https://arxiv.org/abs/1807.04897 · HTML: https://mlsanity.com/paper/1807.04897/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2018.

## Built on by (most cited first, 22 of 22)

- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Robust Object Detection With Inaccurate Bounding Boxes](https://mlsanity.com/paper/2207.09697/) (2022)
- [Improving Weakly-supervised Object Localization via Causal Intervention](https://mlsanity.com/paper/2104.10351/) (2021)
- [CAM-loss: Towards Learning Spatially Discriminative Feature Representations](https://mlsanity.com/paper/2109.01359/) (2021)
- [DAP: Detection-Aware Pre-training with Weak Supervision](https://mlsanity.com/paper/2103.16651/) (2021)
- [Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey](https://mlsanity.com/paper/2105.12694/) (2021)
- [Knowledge-guided Causal Intervention for Weakly-supervised Object Localization](https://mlsanity.com/paper/2301.01060/) (2023)
- [Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection](https://mlsanity.com/paper/2308.05991/) (2023)
- [Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2304.09059/) (2023)
- [Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization](https://mlsanity.com/paper/2305.15354/) (2023)
- [Distributed Attention for Grounded Image Captioning](https://mlsanity.com/paper/2108.01056/) (2021)
- [Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes](https://mlsanity.com/paper/2308.12017/) (2023)
- [Online Active Proposal Set Generation for Weakly Supervised Object Detection](https://mlsanity.com/paper/2101.07929/) (2021)
- [Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)](https://mlsanity.com/paper/2210.12989/) (2022)
- [Self-Classification Enhancement and Correction for Weakly Supervised Object Detection](https://mlsanity.com/paper/2505.16294/) (2025)
- [Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2110.09060/) (2021)
- [Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection](https://mlsanity.com/paper/2204.06899/) (2022)
- [Weakly-Supervised Action Detection Guided by Audio Narration](https://mlsanity.com/paper/2205.05895/) (2022)
- [Online progressive instance-balanced sampling for weakly supervised object detection](https://mlsanity.com/paper/2206.10324/) (2022)
- [HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection](https://mlsanity.com/paper/2406.19394/) (2024)
- [Dual-Thresholded Heatmap-Guided Proposal Clustering and Negative Certainty Supervision with Enhanced Base Network for Weakly Supervised Object Detection](https://mlsanity.com/paper/2509.08289/) (2025)

## Abstract (arXiv)

This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C). We observe that object candidates mined through current multiple instance learning methods are usually trapped to discriminative object parts, rather than the entire object. TS2C leverages surrounding segmentation context derived from weakly-supervised segmentation to suppress such low-quality distracting candidates and boost the high-quality ones. Specifically, TS2C is developed based on two key properties of desirable bounding boxes: 1) high purity, meaning most pixels in the box are with high object response, and 2) high completeness, meaning the box covers high object response pixels comprehensively. With such novel and computable criteria, more tight candidates can be discovered for learning a better object detector. With TS2C, we obtain 48.0% and 44.4% mAP scores on VOC 2007 and 2012 benchmarks, which are the new state-of-the-arts.