BIER — Boosting Independent Embeddings Robustly

Opitz, Michael; Waltner, Georg; Possegger, Horst; Bischof, Horst

doi:10.1109/iccv.2017.555

Cited by 137 publications

(125 citation statements)

References 24 publications

Supporting

Mentioning

125

Contrasting

Order By: Relevance

“…The sampling of the training tuples receive plenty of attention [18,22,23], either through mining [7,22], proxy based approximations [16,17] or hard negative generation [4,13]. Finally, ensemble methods have recently become an increasingly popular way of improving the performances of DML architectures [11,19,33,35]. Our proposed HORDE regularizer is a complementary approach.…”

Section: Related Workmentioning

confidence: 99%

Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

Jacob¹,

Picard²,

Histace³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Learning an effective similarity measure between image representations is key to the success of recent advances in visual search tasks (e.g. verification or zero-shot learning). Although the metric learning part is well addressed, this metric is usually computed over the average of the extracted deep features. This representation is then trained to be discriminative. However, these deep features tend to be scattered across the feature space. Consequently, the representations are not robust to outliers, object occlusions, background variations, etc. In this paper, we tackle this scattering problem with a distribution-aware regularization named HORDE 1 . This regularizer enforces visually-close images to have deep features with the same distribution which are well localized in the feature space. We provide a theoretical analysis supporting this regularization effect. We also show the effectiveness of our approach by obtaining state-of-the-art results on 4 well-known datasets (Cub-200-2011, Cars-196, Stanford Online Products and Inshop Clothes Retrieval).

show abstract

Section: Related Workmentioning

confidence: 99%

Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

Jacob¹,

Picard²,

Histace³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…This clearly shows the advantage of the proposed SBDL loss and its inherent property of treating training samples based on their degree of information. Our method also outperforms the attribute-aware attention model (A 3 M ) and other ensemble based method such as hard-aware cascaded (HDC) network [53], gradient-boosted BIER, A-BIER [41], [42]. Moreover, SGML outperforms the state-of-the-art attentionbased ensemble (ABE) method [1] by +1.3% Recall@1.…”

Section: Results: Deepfashion Dataset 1) Comparison With State-of-mentioning

confidence: 81%

“…Compared to these methods, SGML allows interactions between the tasks and hence inherently considers different granularities of semantic similarity. The top-performing methods such as hardaware cascaded network (HDC) [53], gradient-boosted embeddings (BIER, A-BIER) [42], [41] are recently proposed methods that used ensemble techniques to boost the retrieval performance. Different from these, SGML uses a single model while achieving Recall@1 of 91.8%, outperforming these ensemblebased methods.…”

Section: Results: Deepfashion Dataset 1) Comparison With State-of-mentioning

confidence: 99%

See 1 more Smart Citation

Dynamically Modulated Deep Metric Learning for Visual Search

Manandhar

Baştan

Yap

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Deep metric learning applied to various multimedia applications has shown promising results in tasks such identification, retrieval and recognition. Existing metric learning methods often do not consider different granularity in visual similarity. However, in many domain applications, images exhibit similarity at multiple granularities with visual semantic concepts, e.g. fashion demonstrates similarity ranging from clothing of the exact same instance to similar looks/design or a common category. Therefore, training image triplets/pairs used for metric learning inherently possess different degree of information. However, the existing methods often treats them with equal importance during training. This hinders capturing the underlying granularities in feature similarity which is required for effective visual search.In view of this, we propose a new deep semantic granularity metric learning (SGML) that develops a novel idea of detecting and leveraging attribute semantic space to capture different granularity of similarity, and then integrate this information into deep metric learning. The proposed framework simultaneously learns image attributes and embeddings using multitask CNNs with shared parameters. The two tasks are not only jointly optimized but are further linked by the semantic granularity similarity mappings to leverage the correlations between the tasks. To this end, we propose a new soft-binomial deviance loss that effectively integrates the degree of information in training samples, which helps to capture visual similarity at multiple granularities. Compared to recent ensemble-based methods, our framework is conceptually elegant, computationally simple and provides better performance. We perform extensive experiments on benchmark metric learning datasets and demonstrate that our method outperforms recent state-of-the-art methods, e.g. , 1-4.5% improvement in Recall@1 over the previous state-of-the-arts [1], [2] on DeepFashion In-Shop dataset.

show abstract

“…Metric learning. Our work is also related to general deep metric learning [36,56,26,37,54]. However, they only conducted experiments on InShop clothes retrieval dataset while our work focuses on customer-to-shop clothes retrieval which is much more challenging as analyzed in [34].…”

Section: Datasetsmentioning

confidence: 99%

Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid

Kuang¹,

Gao

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Matching clothing images from customers and online shopping stores has rich applications in E-commerce. Existing algorithms encoded an image as a global feature vector and performed retrieval with the global representation. However, discriminative local information on clothes are submerged in this global representation, resulting in suboptimal performance. To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both global and local representations in multiple scales. The similarity pyramid is represented by a Graph of similarity, where nodes represent similarities between clothing components at different scales, and the final matching score is obtained by message passing along edges. In GRNet, graph reasoning is solved by training a graph convolutional network, enabling to align salient clothing components to improve clothing retrieval. To facilitate future researches, we introduce a new benchmark FindFashion, containing rich annotations of bounding boxes, views, occlusions, and cropping. Extensive experiments show that GRNet obtains new state-of-the-art results on two challenging benchmarks, e.g. pushing the top-1, top-20, and top-50 accuracies on DeepFashion to 26%, 64%, and 75% (i.e. 4%, 10%, and 10% absolute improvements), outperforming competitors with large margins. On FindFashion, GRNet achieves considerable improvements on all empirical settings.

show abstract

BIER — Boosting Independent Embeddings Robustly

Cited by 137 publications

References 24 publications

Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

Dynamically Modulated Deep Metric Learning for Visual Search

Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid

Contact Info

Product

Resources

About