SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition

By Haotong Zhang, Alexander C. Berg, Michael Maire, Jitendra Malik. 2006

1,376 citations recorded by the source corpus.

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

1. Trevor Darrell
2. Li Fei-Fei
3. Yoshua Bengio
4. Bernt Schiele
5. Quoc V. Le
6. Mohit Bansal
7. Andrew Zisserman
8. Abhinav Kumar Gupta

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Trevor Darrell
3. Dacheng Tao
4. Andrew Zisserman
5. Jitendra Malik
6. Xiaogang Wang
7. Ming-Hsuan Yang
8. Andrea Vedaldi

Citations in the corpus

• Ensemble of exemplar-SVMs for object detection and beyond (2011, methodology): “It is worthwhile pointing out some of the key differences between our approach and other related SVM-based techniques such as one-class SVMs [18, 5], multi-class kernel SVMs, kernel-learning approaches [20], and the KNNSVM algorithm [22].”
• Towards Open World Recognition (2014, background): “Incremental Learning: As SVMs rose to prominence in for object recognition applications [46, 22], many incremental extensions to SVMs were proposed.”
• Improving Generalization via Scalable Neighborhood Component Analysis (2018, background): “On the other hand, data association approaches [2,50,23,24] regard categories as data-driven entities emergent from connections between individual instances.”
• What, where and who? Classifying events by scene and object recognition (2007, background): “One could grossly divide the literature into those that use generative models (e.g. [23] [7] [11]) and those that use discriminative models or methods (e.g. [21] [27]).”
• FORMULA: FactORized MUlti-task LeArning for task discovery in personalized medical models (2015, background): “The drawback of locally weighted learning is that it needs to build one model for each testing data points [22].”
• Self-taught learning: transfer learning from unlabeled data (2007, result): “…test accuracy even with computer vision speci.c features (instead of raw pixel intensities).8 8 Since the time we ran our experiments, other re­searchers have reported better results using highly spe­cialized computer vision algorithms (Zhang et al., 2006: 59.1%; Lazebnik et al., 2006: 56.4%).”
• Recognition using regions (2009, methodology): “With 15 and 30 training images per category, our method outperforms [14], [15], [33], [13] and [19] but not [5].”
• Image Classification Using Super-Vector Coding of Local Image Descriptors (2010, methodology): “The previous work includes SVMs using pyramid matching kernels [4], biologically-inspired models [5][6], and KNN methods [7][8][9].”
• Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition (2007, methodology): “For reference, the best reported performance of 66.2% on this dataset was reported by Zhang et al. [21], who used a geometric blur local descriptor on interest points, and matching distance for a combined nearest neighbor and SVM. Lazebnik et al. [12] report 64.6% by matching multi-resolution…”