Max-Margin Object Detection

By Davis E. King. 2015

181 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, methodology): “Given an image, we detected faces using the dlib 1 ’s CNN-based face detector [28] and ran the attribute classiﬁer on each face.”
FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation (2021, background): “net) CNN-based face detector [28] and ran the attribute classifier on each face.”
OpenFace 2.0: Facial Behavior Analysis Toolkit (2018, result): “This is in contrast to OpenFace which used a dlib face detector [37] which is not able to detect profile or highly occluded faces.”
DEEP eye contact detector: Robust eye contact bid detection using convolutional neural network (2017, methodology): “Adapting to partial facial occlusions, we do not use face detection but eye-region detection by using the max-margin object-detection algorithm [8].”
OpenFace: An open source facial behavior analysis toolkit (2016, methodology): “To initialize our CLNF model we use the face detector found in the dlib library [33, 34].”
DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild (2016, methodology): “Figure 7 (bottom) presents some self-evaluations in which we compare the quality of initialization for deformable modelling between DenseReg and two other standard face detection techniques (HOG-SVM [23], DPM [32]).”
Factorized Variational Autoencoders for Modeling Audience Reactions to Movies (2017, background): “[22] proposed ‘Max-Margin Object Detection’ (MMOD) which optimizes over all sub-windows to detect objects in images.”