Supervised translation-invariant sparse coding

Yang, Jianchao; Yu, Kai; Huang, Thomas S.

doi:10.1109/cvpr.2010.5539958

Cited by 299 publications

(245 citation statements)

References 18 publications

Supporting

Mentioning

243

Contrasting

Order By: Relevance

“…As shown by Yu et al [7], sparse coding is approximately a locally linear model, and thus the ScSPM method can achieve promising performance on various classification tasks with linear SVM. This architecture is further extended in [12], where the dictionary for sparse coding is trained with back-propagation to minimize the classification error.…”

Section: Introductionmentioning

confidence: 99%

“…Originally applied to modeling the human vision cortex [1] [2], sparse coding approximates the input signal, x ∈ R d , in terms of a sparse linear combination of an over-complete bases or dictionary B ∈ R d×D , where d < D. Among different ways of sparse coding, the one derived by 1 norm minimization attracts most popularity, due to its coding efficiency with linear programming, and also its relationship to the NPhard 0 norm in compressive sensing [3]. The applications of sparse coding range from image restorations [4] [5], machine learning [6] [7] [8], to various computer vision tasks [9] [10] [11] [12]. Many efficient algorithms aiming to find such a sparse representation have been proposed in the past several years [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Highly Over-Complete Sparse Coding Using a Mixture Model

Yang

Huang

2010

Computer Vision – ECCV 2010

Self Cite

View full text Add to dashboard Cite

Abstract. Sparse coding of sensory data has recently attracted notable attention in research of learning useful features from the unlabeled data. Empirical studies show that mapping the data into a significantly higherdimensional space with sparse coding can lead to superior classification performance. However, computationally it is challenging to learn a set of highly over-complete dictionary bases and to encode the test data with the learned bases. In this paper, we describe a mixture sparse coding model that can produce high-dimensional sparse representations very efficiently. Besides the computational advantage, the model effectively encourages data that are similar to each other to enjoy similar sparse representations. What's more, the proposed model can be regarded as an approximation to the recently proposed local coordinate coding (LCC), which states that sparse coding can approximately learn the nonlinear manifold of the sensory data in a locally linear manner. Therefore, the feature learned by the mixture sparse coding model works pretty well with linear classifiers. We apply the proposed model to PASCAL VOC 2007 and 2009 datasets for the classification task, both achieving stateof-the-art performances.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient Highly Over-Complete Sparse Coding Using a Mixture Model

Yang

Huang

2010

Computer Vision – ECCV 2010

Self Cite

View full text Add to dashboard Cite

show abstract

“…As in previous work [17], [26], [10], [28], the classification error of a linear predictive classifier is included in the objective function:…”

Section: Cross-domain Discriminative Dictionary Learningmentioning

confidence: 99%

“…The K-SVD method focuses on the reconstructive ability, however, since the learning process is unsupervised, the discriminative capability is not taken into consideration. Consequently, methods that incorporate the discriminative criteria into dictionary learning were proposed in [28], [26], [18], [17], [18], [2]. In addition to the discriminative capability of the learned dictionary, other criteria designed on top of the prototype dictionary learning objective function include multiple dictionary learning [29], category-specific dictionary learning [27], etc.…”

Section: Introductionmentioning

confidence: 99%

“…The K-SVD algorithm [1] is a popular and efficient dictionary learning method that focuses on minimizing the reconstruction error. Some discriminative approaches [28], [26], [18], [17], [16], [2] show their privilege over the K-SVD algorithm by incorporating extra discriminative terms into the objective function for dictionary learning. However, the discriminative terms appear to be introduced to these approaches without considering the data distribution of the training samples, i.e., samples with high confidence possess the same impact as those with low confidence.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Action Recognition by Cross-Domain Dictionary Learning

Zhu¹,

Shao²

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

We present a novel cross-dataset action recognition framework that utilizes relevant actions from other visual domains as auxiliary knowledge for enhancing the learning system in the target domain. The data distribution of relevant actions from a source dataset is adapted to match the data distribution of actions in the target dataset via a cross-domain discriminative dictionary learning method, through which a reconstructive, discriminative and domain-adaptive dictionary-pair can be learned. Using selected categories from the HMDB51 dataset as the source domain actions, the proposed framework achieves outstanding performance on the UCF YouTube dataset.

show abstract

Motion Enhanced Multi‐Level Tracker (MEMTrack): A Deep Learning‐Based Approach to Microrobot Tracking in Dense and Low‐Contrast Environments

Sawhney,

Karmarkar,

Leaman

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

Tracking microrobots is challenging due to their minute size and high speed. In biomedical applications, this challenge is exacerbated by the dense surrounding environments with feature sizes and shapes comparable to microrobots. Herein, Motion Enhanced Multi‐level Tracker (MEMTrack) is introduced for detecting and tracking microrobots in dense and low‐contrast environments. Informed by the physics of microrobot motion, synthetic motion features for deep learning‐based object detection and a modified Simple Online and Real‐time Tracking (SORT)algorithm with interpolation are used for tracking. MEMTrack is trained and tested using bacterial micromotors in collagen (tissue phantom), achieving precision and recall of 76% and 51%, respectively. Compared to the state‐of‐the‐art baseline models, MEMTrack provides a minimum of 2.6‐fold higher precision with a reasonably high recall. MEMTrack's generalizability to unseen (aqueous) media and its versatility in tracking microrobots of different shapes, sizes, and motion characteristics are shown. Finally, it is shown that MEMTrack localizes objects with a root‐mean‐square error of less than 1.84 μm and quantifies the average speed of all tested systems with no statistically significant difference from the laboriously produced manual tracking data. MEMTrack significantly advances microrobot localization and tracking in dense and low‐contrast settings and can impact fundamental and translational microrobotic research.

show abstract

Supervised translation-invariant sparse coding

Abstract: Abstract

Cited by 299 publications

References 18 publications

Efficient Highly Over-Complete Sparse Coding Using a Mixture Model

Efficient Highly Over-Complete Sparse Coding Using a Mixture Model

Enhancing Action Recognition by Cross-Domain Dictionary Learning

Motion Enhanced Multi‐Level Tracker (MEMTrack): A Deep Learning‐Based Approach to Microrobot Tracking in Dense and Low‐Contrast Environments

Contact Info

Product

Resources

About