# Max-Margin Object Detection

arXiv: https://arxiv.org/abs/1502.00046 · HTML: https://mlsanity.com/paper/1502.00046/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2015.

## Built on by (most cited first, 15 of 15)

- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition](https://mlsanity.com/paper/2303.15889/) (2023)
- [DSAP: Analyzing Bias Through Demographic Comparison of Datasets](https://mlsanity.com/paper/2312.14626/) (2023)
- [Less can be more: representational vs. stereotypical gender bias in facial expression recognition](https://mlsanity.com/paper/2406.17405/) (2024)
- [Resolve Domain Conflicts for Generalizable Remote Physiological Measurement](https://mlsanity.com/paper/2404.07855/) (2024)
- [GroupGazer: A Tool to Compute the Gaze per Participant in Groups with integrated Calibration to Map the Gaze Online to a Screen or Beamer Projection](https://mlsanity.com/paper/2201.07692/) (2022)
- [Automatic Main Character Recognition for Photographic Studies](https://mlsanity.com/paper/2106.09064/) (2021)
- [BYHE: A Simple Framework for Boosting End-to-end Video-based Heart Rate Measurement Network](https://mlsanity.com/paper/2207.01697/) (2022)
- [Automatic 3D Registration of Dental CBCT and Face Scan Data using 2D Projection Images](https://mlsanity.com/paper/2305.10132/) (2023)
- [Biased Heritage: How Datasets Shape Models in Facial Expression Recognition](https://mlsanity.com/paper/2503.03446/) (2025)
- [WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range](https://mlsanity.com/paper/2101.03826/) (2021)
- [Fast Eye Detector Using Siamese Network for NIR Partial Face Images](https://mlsanity.com/paper/2202.10671/) (2022)
- [A Trustworthiness Score to Evaluate DNN Predictions](https://mlsanity.com/paper/2301.08839/) (2023)
- [SecurePose: Automated Face Blurring and Human Movement Kinematics Extraction from Videos Recorded in Clinical Settings](https://mlsanity.com/paper/2402.14143/) (2024)
- [FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing](https://mlsanity.com/paper/2502.03826/) (2025)

## Abstract (arXiv)

Most object detection methods operate by applying a binary classifier to sub-windows of an image, followed by a non-maximum suppression step where detections on overlapping sub-windows are removed. Since the number of possible sub-windows in even moderately sized image datasets is extremely large, the classifier is typically learned from only a subset of the windows. This avoids the computational difficulty of dealing with the entire set of sub-windows, however, as we will show in this paper, it leads to sub-optimal detector performance. In particular, the main contribution of this paper is the introduction of a new method, Max-Margin Object Detection (MMOD), for learning to detect objects in images. This method does not perform any sub-sampling, but instead optimizes over all sub-windows. MMOD can be used to improve any object detection method which is linear in the learned parameters, such as HOG or bag-of-visual-word models. Using this approach we show substantial performance gains on three publicly available datasets. Strikingly, we show that a single rigid HOG filter can outperform a state-of-the-art deformable part model on the Face Detection Data Set and Benchmark when the HOG filter is learned via MMOD.