MILES: Multiple-Instance Learning via Embedded Instance Selection

By Yixin Chen, Jinbo Bi, James Ze Wang. 2006

786 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Signal Processing

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

In Signal Processing

Citations in the corpus

Deep Fragment Embeddings for Bidirectional Image Sentence Mapping (2014, methodology): “We now describe a Multiple Instance Learning (MIL) [38] extension of the objective C 0 that attempts to infer the latent alignment between fragments in corresponding image-sentence pairs.”
A review of multi-instance learning assumptions (2010, methodology): “The DD-SVM (Chen & Wang, 2004) algorithm and its successor multiple-instance learning via embedded instance selection (MILES) (Chen et al ., 2006) also use a generalized MI assumption, where bag-level class labels are determined based on the distance from each of a set of target points.”
Learning to recognize objects in egocentric activities (2011, methodology): “More recently, Multiple Instance Learning (MIL) has shown great promise as a method for weakly supervised learning in computer vision communities [1, 9, 5, 23, 6].”
Exploit Bounding Box Annotations for Multi-Label Object Recognition (2015, methodology): “Over the years, many multi-instance learning algorithms have been proposed, including miBoosting [29], miSVM [1], MILES [7] and miGraph [33].”
Using Neural Network Formalism to Solve Multiple-Instance Problems (2016, methodology): “All embedded space paradigm methods except Miles used a logistic regression classifier.”
Weakly-Supervised Evidence Pinpointing and Description (2017, methodology): “The evidence pinpointing task is reminiscent of the multiple-instance problem as described in [5] in which instances or features responsible for the classification are identified.”
Multi-Instance Learning With Emerging Novel Class (2021, methodology): “Many existing MIL works [1], [5], [6], [7], [8], [9] solve the binary MIL classiﬁcation problem.”
On Recognizing Actions in Still Images via Multiple Features (2012, methodology): “Given the extracted candidate bounding boxes, we adopt Multiple Instance Learning with Instance Selection (MILES) [17] algorithm for learning the related object regions.”
SMILE: A Similarity-Based Approach for Multiple Instance Learning (2010, methodology): “Over the last decade, multiple instance learning has attracted much attention in solving many real-world applications, ranging from drug activity prediction [1], image categorization [8], [9], and text categorization [3], [2] to image retrieval [10].”
MILEAGE: Multiple Instance LEArning with Global Embedding (2013, methodology): “To show the advantages of the proposed large margin method, we compare it with several baseline methods, including traditional large margin methods, SVM-B, SVM-I, and multiple instance learning methods: Citation KNN (Wang & Zucker, 2000), MISVM (Andrews et al., 2003), miSVM (Andrews et al., 2003), M”
A Bag-of-Features Framework to Classify Time Series (2013, background): “A BoF is also referred to as a bag-of-words (BoW) [31] in document classification, a bag-of-instances in multiple instance learning [32], [33], and a bag-of-frames in audio and speech recognition [34], [35].”
Multiple instance learning: A survey of problem characteristics and applications (2016, methodology): “MILES [4]: In Multiple-Instance Learning via Embedded instance Selection (MILES) an SVM classifies bags represented by a feature vectors containing maximal similarities to selected prototypes.”
A survey on still image based human action recognition (2014, neutral): “They considered the location of the center window j with respect to a coordinate frame defined by window i, labeled as the thick outlined box in Fig.”
Weakly Supervised Localization and Learning with Generic Knowledge (2012, neutral): “Our method is also related to multiple-instance learning [Andrews et al, 2002, Chen et al, 2006, Viola et al, 2005], if we represent an image as a bag and the windows therein as instances.”