Deep metric learning via subtype fuzzy clustering

Ren, Chuan-Xian; Li, Juzheng; Ge, Pengfei; Xu, Xiaolin

doi:10.1016/j.patcog.2019.01.037

Cited by 10 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leveraging explicit relationships between training images for representation learning is widely studied using different orders of constraints (e.g. binary similarities [29], ranking constraints [24]). All these methods use label information or strong pretraining as the performance of such task heavily depends on the quality of the pairwise constraints.…”

Section: Related Workmentioning

confidence: 99%

“…The massive drop of 8.6% in performance can be explained by the dependence of such frameworks on hard-negative mining strategies. Since reliable constraints are only based on high similarities and dissimilarities, the ranking framework obviously has no access to hard constraints, which are very difficult to find reliably without supervision [33] or strong pretraining [24]. Note that we are using triplet constraints only for transferring already learned information to refine our representations φ k (Sec.…”

Section: Ablation Studiesmentioning

confidence: 99%

“…2 Mail: https://hci.iwr.uni-heidelberg.de/compvis. [29] or sample ordering constraints [24], a dataset of N training samples gives rise to N 2 pairwise relations, exploitable for learning our representation. In the absence of supervisory information, these relations need to be automatically inferred during training.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised representation learning by discovering reliable image relations

Milbich

Ghori

Diego

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

Learning robust representations that allow to reliably establish relations between images is of paramount importance for virtually all of computer vision. Annotating the quadratic number of pairwise relations between training images is simply not feasible, while unsupervised inference is prone to noise, thus leaving the vast majority of these relations to be unreliable. To nevertheless find those relations which can be reliably utilized for learning, we follow a divide-and-conquer strategy: We find reliable similarities by extracting compact groups of images and reliable dissimilarities by partitioning these groups into subsets, converting the complicated overall problem into few reliable local subproblems. For each of the subsets we obtain a representation by learning a mapping to a target feature space so that their reliable relations are kept. Transitivity relations between the subsets are then exploited to consolidate the local solutions into a concerted global representation. While iterating between grouping, partitioning, and learning, we can successively use more and more reliable relations which, in turn, improves our image representation. In experiments, our approach shows state-of-the-art performance on unsupervised classification on ImageNet with 46.0% and competes favorably on different transfer learning tasks on PASCAL VOC.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Ablation Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised representation learning by discovering reliable image relations

Milbich

Ghori

Diego

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…In general, the main idea of most image set feature learning approaches are to make the inter-classes more separable and the intra-classes more compact [9], [12], [13], [29]. Moreover, feature extractors based on CNNs show higher accuracies than traditional hand-crafted methods [17], [19], [20], [30]. However, neural networks are black boxes and they are lack of adequate interpretations.…”

Section: Related Workmentioning

confidence: 99%

Discriminative Residual Analysis for Image Set Classification With Posture and Age Variations

Ren

Luo

et al. 2020

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Image set recognition has been widely applied in many practical problems like real-time video retrieval and image caption tasks. Due to its superior performance, it has grown into a significant topic in recent years. However, images with complicated variations, e.g., postures and human ages, are difficult to address, as these variations are continuous and gradual with respect to image appearance. Consequently, the crucial point of image set recognition is to mine the intrinsic connection or structural information from the image batches with variations. In this work, a Discriminant Residual Analysis (DRA) method is proposed to improve the classification performance by discovering discriminant features in related and unrelated groups. Specifically, DRA attempts to obtain a powerful projection which casts the residual representations into a discriminant subspace. Such a projection subspace is expected to magnify the useful information of the input space as much as possible, then the relation between the training set and the test set described by the given metric or distance will be more precise in the discriminant subspace. We also propose a nonfeasance strategy by defining another approach to construct the unrelated groups, which help to reduce furthermore the cost of sampling errors. Two regularization approaches are used to deal with the probable small sample size problem. Extensive experiments are conducted on benchmark databases, and the results show superiority and efficiency of the new methods.

show abstract

“…A S a fundamental task in pattern recognition and machine learning, clustering [1]- [4] is an effective approach for exploring the structure of unlabeled data and extracting the classification information within. However, it is quite challenging since classification information is always entangled with other information such as style and background.…”

Section: Introductionmentioning

confidence: 99%

Dual Adversarial Auto-Encoders for Clustering

Ge,

Ren,

Feng

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

As a powerful approach for exploratory data analysis, unsupervised clustering is a fundamental task in computer vision and pattern recognition. Many clustering algorithms have been developed, but most of them perform unsatisfactorily on the data with complex structures. Recently, Adversarial Auto-Encoder (AAE) shows effectiveness on tackling such data by combining Auto-Encoder (AE) and adversarial training, but it cannot effectively extract classification information from the unlabeled data. In this work, we propose Dual Adversarial Auto-encoder (Dual-AAE) which simultaneously maximizes the likelihood function and mutual information between observed examples and a subset of latent variables. By performing variational inference on the objective function of Dual-AAE, we derive a new reconstruction loss which can be optimized by training a pair of Auto-encoders. Moreover, to avoid mode collapse, we introduce the clustering regularization term for the category variable. Experiments on four benchmarks show that Dual-AAE achieves superior performance over state-of-the-art clustering methods. Besides, by adding a reject option, the clustering accuracy of Dual-AAE can reach that of supervised CNN algorithms. Dual-AAE can also be used for disentangling style and content of images without using supervised information.

show abstract

Deep metric learning via subtype fuzzy clustering

Cited by 10 publications

References 13 publications

Unsupervised representation learning by discovering reliable image relations

Unsupervised representation learning by discovering reliable image relations

Discriminative Residual Analysis for Image Set Classification With Posture and Age Variations

Dual Adversarial Auto-Encoders for Clustering

Contact Info

Product

Resources

About