# C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

arXiv: https://arxiv.org/abs/1904.05647 · HTML: https://mlsanity.com/paper/1904.05647/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2019.

## Built on by (most cited first, 30 of 71)

- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection](https://mlsanity.com/paper/2207.03482/) (2022)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [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)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.04523/) (2021)
- [CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2310.16667/) (2023)
- [Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning](https://mlsanity.com/paper/2104.07268/) (2021)
- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [3D Spatial Recognition without Spatially Labeled 3D](https://mlsanity.com/paper/2105.06461/) (2021)
- [Self-supervised object detection from audio-visual correspondence](https://mlsanity.com/paper/2104.06401/) (2021)
- [Taming Self-Training for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2308.06412/) (2023)
- [Group R-CNN for Weakly Semi-supervised Object Detection with Points](https://mlsanity.com/paper/2205.05920/) (2022)
- [CLIM: Contrastive Language-Image Mosaic for Region Representation](https://mlsanity.com/paper/2312.11376/) (2023)
- [Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters](https://mlsanity.com/paper/2108.01499/) (2021)
- [Robust Object Detection With Inaccurate Bounding Boxes](https://mlsanity.com/paper/2207.09697/) (2022)
- [Object Localization under Single Coarse Point Supervision](https://mlsanity.com/paper/2203.09338/) (2022)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Object Discovery via Contrastive Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2208.07576/) (2022)
- [Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction](https://mlsanity.com/paper/2204.09204/) (2022)
- [Weakly Supervised Open-Vocabulary Object Detection](https://mlsanity.com/paper/2312.12437/) (2023)
- [Computer Vision for Primate Behavior Analysis in the Wild](https://mlsanity.com/paper/2401.16424/) (2024)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [Open-Vocabulary Object Detection via Language Hierarchy](https://mlsanity.com/paper/2410.20371/) (2024)
- [Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization](https://mlsanity.com/paper/2207.07818/) (2022)
- [W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection](https://mlsanity.com/paper/2207.12104/) (2022)
- [Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild](https://mlsanity.com/paper/2304.04875/) (2023)
- [Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring](https://mlsanity.com/paper/2605.30834/) (2026)

## Abstract (arXiv)

Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors. Many WSOD approaches adopt multiple instance learning (MIL) and have non-convex loss functions which are prone to get stuck into local minima (falsely localize object parts) while missing full object extent during training. In this paper, we introduce a continuation optimization method into MIL and thereby creating continuation multiple instance learning (C-MIL), with the intention of alleviating the non-convexity problem in a systematic way. We partition instances into spatially related and class related subsets, and approximate the original loss function with a series of smoothed loss functions defined within the subsets. Optimizing smoothed loss functions prevents the training procedure falling prematurely into local minima and facilitates the discovery of Stable Semantic Extremal Regions (SSERs) which indicate full object extent. On the PASCAL VOC 2007 and 2012 datasets, C-MIL improves the state-of-the-art of weakly supervised object detection and weakly supervised object localization with large margins.