Learning Exemplar-Represented Manifolds in Latent Space for Classification

Kong, Shu; Wang, Donghui

doi:10.1007/978-3-642-40994-3_16

Cited by 3 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section we introduce and analyze the loss we use for learning pixel embeddings. This problem is broadly related to supervised distance metric learning [86,48,50] and clustering [49] but adapted to the specifics of instance labeling where the embedding vectors are treated as labels for a variable number of objects in each image.…”

Section: Pairwise Loss For Pixel Embeddingsmentioning

confidence: 99%

Recurrent Pixel Embedding for Instance Grouping

Kong

Fowlkes

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

176

132

View full text Add to dashboard Cite

We introduce a differentiable, end-to-end trainable framework for solving pixel-level grouping problems such as instance segmentation consisting of two novel components. First, we regress pixels into a hyper-spherical embedding space so that pixels from the same group have high cosine similarity while those from different groups have similarity below a specified margin. We analyze the choice of embedding dimension and margin, relating them to theoretical results on the problem of distributing points uniformly on the sphere. Second, to group instances, we utilize a variant of mean-shift clustering, implemented as a recurrent neural network parameterized by kernel bandwidth. This recurrent grouping module is differentiable, enjoys convergent dynamics and probabilistic interpretability. Backpropagating the group-weighted loss through this module allows learning to focus on only correcting embedding errors that won't be resolved during subsequent clustering. Our framework, while conceptually simple and theoretically abundant, is also practically effective and computationally efficient. We demonstrate substantial improvements over stateof-the-art instance segmentation for object proposal generation, as well as demonstrating the benefits of grouping loss for classification tasks such as boundary detection and semantic segmentation.

show abstract

Section: Pairwise Loss For Pixel Embeddingsmentioning

confidence: 99%

Recurrent Pixel Embedding for Instance Grouping

Kong

Fowlkes

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

176

132

View full text Add to dashboard Cite

show abstract

“…Their method, known as sparse embedding (SE), can be extended to a non-linear version via kernel tricks and also adopts a novel classification schema leading to great performance. However, it fails to consider the discrimination power among the separately learned classspecific dictionaries, such that it is not guaranteed to produce improved classification performance [24]. Ptucha et al [13] integrated manifold-based DR and sparse representation within a single framework and presented a variant of the K-SVD algorithm by exploiting a linear extension of graph embedding (LGE).…”

Section: Related Workmentioning

confidence: 99%

Object Classification With Joint Projection and Low-Rank Dictionary Learning

Foroughi

Ray

Zhang

2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

For an object classification system, the most critical obstacles toward real-world applications are often caused by large intra-class variability, arising from different lightings, occlusion, and corruption, in limited sample sets. Most methods in the literature would fail when the training samples are heavily occluded, corrupted or have significant illumination or viewpoint variations. Besides, most of the existing methods and especially deep learning-based methods, need large training sets to achieve a satisfactory recognition performance. Although using the pre-trained network on a generic large-scale data set and fine-tune it to the small-sized target data set is a widely used technique, this would not help when the content of base and target data sets are very different. To address these issues simultaneously, we propose a joint projection and low-rank dictionary learning method using dual graph constraints. Specifically, a structured class-specific dictionary is learned in the low-dimensional space, and the discrimination is further improved by imposing a graph constraint on the coding coefficients, that maximizes the intra-class compactness and inter-class separability. We enforce structural incoherence and low-rank constraints on sub-dictionaries to reduce the redundancy among them, and also make them robust to variations and outliers. To preserve the intrinsic structure of data, we introduce a supervised neighborhood graph into the framework to make the proposed method robust to small-sized and high-dimensional data sets. Experimental results on several benchmark data sets verify the superior performance of our method for object classification of small-sized data sets, which include a considerable amount of different kinds of variation, and may have high-dimensional feature vectors.

show abstract

“…Their method, known as sparse embedding (SE) can be extended to a non-linear version via kernel tricks and also adopts a novel classification schema leading to great performance. Nevertheless, it fails to consider the discrimination power among the separately learned class-specific dictionaries, such that it is not guaranteed to produce improved classification performance [11]. Ptucha et al [4] integrated manifold-based DR and sparse representation within a single framework and presented a variant of the K-SVD algorithm by exploiting a linear extension of graph embedding (LGE).…”

Section: Introductionmentioning

confidence: 99%

Joint Projection and Dictionary Learning using Low-rank Regularization and Graph Constraints

Foroughi,

Ray,

Zhang

2016

Preprint

View full text Add to dashboard Cite

In this paper, we aim at learning simultaneously a discriminative dictionary and a robust projection matrix from noisy data. The joint learning, makes the learned projection and dictionary a better fit for each other, so a more accurate classification can be obtained. However, current prevailing joint dimensionality reduction and dictionary learning methods, would fail when the training samples are noisy or heavily corrupted. To address this issue, we propose a joint projection and dictionary learning using low-rank regularization and graph constraints (JPDL-LR). Specifically, the discrimination of the dictionary is achieved by imposing Fisher criterion on the coding coefficients. In addition, our method explicitly encodes the local structure of data by incorporating a graph regularization term, that further improves the discriminative ability of the projection matrix. Inspired by recent advances of low-rank representation for removing outliers and noise, we enforce a low-rank constraint on sub-dictionaries of all classes to make them more compact and robust to noise. Experimental results on several benchmark datasets verify the effectiveness and robustness of our method for both dimensionality reduction and image classification, especially when the data contains considerable noise or variations.

show abstract

Learning Exemplar-Represented Manifolds in Latent Space for Classification

Cited by 3 publications

References 19 publications

Recurrent Pixel Embedding for Instance Grouping

Recurrent Pixel Embedding for Instance Grouping

Object Classification With Joint Projection and Low-Rank Dictionary Learning

Joint Projection and Dictionary Learning using Low-rank Regularization and Graph Constraints

Contact Info

Product

Resources

About