Multiple Instance Dictionary Learning using Functions of Multiple Instances

Jiao, Changzhe; Zare, Alina

doi:10.1109/icpr.2016.7900041

Cited by 7 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We now must define Pr(l + ij = +|B + i ) and Pr(l − ij = −|x − ij ). As in [7], each instance is modeled as a sparse linear combination of target and/or background signatures D, x j ≈ Dα j , where α j is the sparse vector of weights. Each positive bag contains at least one instance with target:…”

Section: Multiple Instance Hybrid Estimatormentioning

confidence: 99%

Multiple instance hybrid estimator for learning target signatures

Jiao

Zare

2017

2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

Self Cite

View full text Add to dashboard Cite

Signature-based detectors for hyperspectral target detection rely on knowing the specific target signature in advance. However, target signature are often difficult or impossible to obtain. Furthermore, common methods for obtaining target signatures, such as from laboratory measurements or manual selection from an image scene, usually do not capture the discriminative features of target class. In this paper, an approach for estimating a discriminative target signature from imprecise labels is presented. The proposed approach maximizes the response of the hybrid sub-pixel detector within a multiple instance learning framework and estimates a set of discriminative target signatures. After learning target signatures, any signature based detector can then be applied on test data. Both simulated and real hyperspectral target detection experiments are shown to illustrate the effectiveness of the method.

show abstract

Section: Multiple Instance Hybrid Estimatormentioning

confidence: 99%

Multiple instance hybrid estimator for learning target signatures

Jiao

Zare

2017

2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the beginning of this chapter, two Functions of Multiple Instances (FUMI) approaches, extended FUMI (eFUMI) [67][68][69][70] and Dictionary Learning using FUMI (DL-FUMI) [71,72], for learning representative target and non-target concepts are reviewed. Then, the discriminative target concept learning methods, multiple instance spectral matched filter (MI-SMF) and multiple instance adaptive cosine estimator (MI-ACE) [73] are investigated and discussed.…”

Section: Chapter 3 Previously Proposed Multiple Instance Concept Learning Algorithmsmentioning

confidence: 99%

“…The goal of DL-FUMI [71,72] is to leverage the benefits of dictionary learning approaches for problems in which only imprecise multiple instance learning type labels are available.…”

Section: Dictionary Learning Using Function Of Multiple Instancesmentioning

confidence: 99%

“…MI-HE is a discriminative target concept learning algorithm for problems with mixed data and label uncertainty. Quite different from the FUMI algorithms [69,71] that learn representative concept from reconstruction error, MI-HE learns discriminative target concept that maximizes the detection performance. Specifically, the estimated target concept by MI-HE maximizes the detection response of structured hybrid detector (HSD) [56,65] under a generalized mean model.…”

Section: Chapter 4 Multiple Instance Hybrid Estimatormentioning

confidence: 99%

“…Similar to DL-FUMI [71], here each instance is modeled as a sparse linear combination of target and/or background concepts D, x i ≈ Da i , where a i is the sparse vector of weights for instance x i . Each positive bag contains at least one instance composed of some target:…”

Section: Multiple Instance Hybrid Estimator Learning Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

Target concept learning from ambiguously labeled data

Jiao¹

Self Cite

View full text Add to dashboard Cite

The multiple instance learning problem addresses the case where training data comes with label ambiguity, i.e., the learner has access only to inaccurately labeled data. For example, in target detection from remotely sensed hyperspectral imagery, targets are usually sub-pixel and the ground truthing of the targets according to GPS coordinates could drift across several meters. Thus the locations of the targets corresponding to the hyperspectral image are inaccurate. Training a supervised algorithm or extracting target signatures from this kind of labels is intractable. This dissertation investigates the topic target concept learning from ambiguously labeled data comprehensively; reviews and proposes several methods that either learn a set of representative or discriminative target concepts. The multiple instance hybrid estimator (MI-HE) maximizes the response of the hybrid detector under a generalized mean framework and estimates a set of discriminative target concepts. MI-HE adopts a linear mixture model and iterates between estimating a set of discriminative target and non-target signatures and solving a sparse unmixing problem. MI-HE preserves bag-level label information for each positive bag and is able to estimate a target concept that is commonly shared among positive bags. Furthermore, MI-HE has the potential to learn multiple signatures to address signature variability. After learning target concept, signature based detector could be applied for target detection. The presented algorithms were tested in many applications including simulated and real hyperspectral target detection, heartbeat characterization from ballistocardiogram signals and tree species classification from remotely sensed data. The presented algorithms were proven to be effective in learning high-quality target signatures and consistently achieved superior performance over the state-of-the-art comparison algorithms.

show abstract

Multiple instance hybrid estimator for hyperspectral target characterization and sub-pixel target detection

Jiao

Chen

McGarvey

et al. 2018

ISPRS Journal of Photogrammetry and Remote Sensing

Self Cite

View full text Add to dashboard Cite

The Multiple Instance Hybrid Estimator for discriminative target characterization from imprecisely labeled hyperspectral data is presented. In many hyperspectral target detection problems, acquiring accurately labeled training data is difficult. Furthermore, each pixel containing target is likely to be a mixture of both target and non-target signatures (i.e., sub-pixel targets), making extracting a pure prototype signature for the target class from the data extremely difficult. The proposed approach addresses these problems by introducing a data mixing model and optimizing the response of the hybrid sub-pixel detector within a multiple instance learning framework. The proposed approach iterates between estimating a set of discriminative target and non-target signatures and solving a sparse unmixing problem. After learning target signatures, a signature based detector can then be applied on test data. Both simulated and real hyperspectral target detection experiments show the proposed algorithm is effective at learning discriminative target signatures and achieves superior performance over state-of-the-art comparison algorithms.

show abstract

Multiple Instance Dictionary Learning using Functions of Multiple Instances

Cited by 7 publications

References 23 publications

Multiple instance hybrid estimator for learning target signatures

Multiple instance hybrid estimator for learning target signatures

Target concept learning from ambiguously labeled data

Multiple instance hybrid estimator for hyperspectral target characterization and sub-pixel target detection

Contact Info

Product

Resources

About