Sketch-QNet: A Quadruplet ConvNet for Color Sketch-based Image Retrieval

Fuentes, Aníbal Rodríguez; Saavedra, José M.

doi:10.1109/cvprw53098.2021.00242

Cited by 12 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A natural extension of SBIR is the case where the input sketch includes color information. Here, Fuentes and Saavedra [7] recently presented an interesting approach extending the notion of triplets to quadruplet-based training.…”

Section: Sketch-based Image Retrievalmentioning

confidence: 99%

“…For instance, the main computer vision conferences already include workshops to promote research and applications on this topic. In this vein, we have seen advances in a diversity of tasks like sketch classification [5,28,33], sketch-guided object localization [24], sketch-based image and video retrieval [2,4,7,19,20,23,32], sketch-to-photo translation [3,21], among others.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging Unlabeled Data for Sketch-based Understanding

Morales¹,

Murrugarra-Llerena²,

Saavedra³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Sketch-based understanding is a critical component of human cognitive learning and is a primitive communication means between humans. This topic has recently attracted the interest of the computer vision community as sketching represents a powerful tool to express static objects and dynamic scenes. Unfortunately, despite its broad application domains, the current sketch-based models strongly rely on labels for supervised training, ignoring knowledge from unlabeled data, thus limiting the underlying generalization and the applicability. Therefore, we present a study about the use of unlabeled data to improve a sketch-based model. To this end, we evaluate variations of VAE and semi-supervised VAE, and present an extension of BYOL to deal with sketches. Our results show the superiority of sketch-BYOL, which outperforms other self-supervised approaches increasing the retrieval performance for known and unknown categories. Furthermore, we show how other tasks can benefit from our proposal.

show abstract

Section: Sketch-based Image Retrievalmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Leveraging Unlabeled Data for Sketch-based Understanding

Morales¹,

Murrugarra-Llerena²,

Saavedra³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…To bridge the domain gap, extensive efforts have been devoted to learning common representations from different domains (Sangkloy et al 2016;Yu et al 2016;Sain et al 2021;Fuentes and Saavedra 2021). Although the existing crossdomain image retrieval methods have achieved promising performance, they implicitly assume that the multi-domain training data are annotated and aligned well.…”

Section: Introductionmentioning

confidence: 99%

Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval

Wang¹,

Peng²,

Yan³

et al. 2023

Preprint

View full text Add to dashboard Cite

Cross-domain image retrieval aims at retrieving images across different domains to excavate cross-domain classificatory or correspondence relationships. This paper studies a less-touched problem of cross-domain image retrieval, i.e., unsupervised cross-domain image retrieval, considering the following practical assumptions: (i) no correspondence relationship, and (ii) no category annotations. It is challenging to align and bridge distinct domains without cross-domain correspondence. To tackle the challenge, we present a novel Correspondence-free Domain Alignment (CoDA) method to effectively eliminate the cross-domain gap through Indomain Self-matching Supervision (ISS) and Cross-domain Classifier Alignment (CCA). To be specific, ISS is presented to encapsulate discriminative information into the latent common space by elaborating a novel self-matching supervision mechanism. To alleviate the cross-domain discrepancy, CCA is proposed to align distinct domain-specific classifiers. Thanks to the ISS and CCA, our method could encode the discrimination into the domain-invariant embedding space for unsupervised cross-domain image retrieval. To verify the effectiveness of the proposed method, extensive experiments are conducted on four benchmark datasets compared with six state-of-the-art methods.

show abstract