Matches in SemOpenAlex for { <https://semopenalex.org/work/W3154171217> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3154171217 abstract "In this paper, we utilize deep visual Representation Learning to address the problem of identification of color variants. In particular, we address color variants identification in fashion products, which refers to the problem of identifying fashion products that match exactly in their design (or style), but only to differ in their color. Firstly, we solve this problem by obtaining manual annotations depicting whether two products are color variants. Having obtained such annotations, we train a triplet loss based neural network model to learn deep representations of fashion products. However, for large scale real-world industrial datasets such as addressed in our paper, it is infeasible to obtain annotations for the entire dataset. Hence, we rather explore the use of self-supervised learning to obtain the representations. We observed that existing state-of-the-art self-supervised methods do not perform competitive against the supervised version of our color variants model. To address this, we additionally propose a novel contrastive loss based self-supervised color variants model. Intuitively, our model focuses on different parts of an object in a fixed manner, rather than focusing on random crops typically used for data augmentation in existing methods. We evaluate our method both quantitatively and qualitatively to show that it outperforms existing self-supervised methods, and at times, the supervised model as well." @default.
- W3154171217 created "2021-04-26" @default.
- W3154171217 creator A5036468404 @default.
- W3154171217 creator A5038904282 @default.
- W3154171217 creator A5044925610 @default.
- W3154171217 creator A5067539952 @default.
- W3154171217 date "2021-04-17" @default.
- W3154171217 modified "2023-09-27" @default.
- W3154171217 title "Color Variants Identification via Contrastive Self-Supervised Representation Learning." @default.
- W3154171217 hasPublicationYear "2021" @default.
- W3154171217 type Work @default.
- W3154171217 sameAs 3154171217 @default.
- W3154171217 citedByCount "0" @default.
- W3154171217 crossrefType "posted-content" @default.
- W3154171217 hasAuthorship W3154171217A5036468404 @default.
- W3154171217 hasAuthorship W3154171217A5038904282 @default.
- W3154171217 hasAuthorship W3154171217A5044925610 @default.
- W3154171217 hasAuthorship W3154171217A5067539952 @default.
- W3154171217 hasConcept C108583219 @default.
- W3154171217 hasConcept C116834253 @default.
- W3154171217 hasConcept C119857082 @default.
- W3154171217 hasConcept C136389625 @default.
- W3154171217 hasConcept C153180895 @default.
- W3154171217 hasConcept C154945302 @default.
- W3154171217 hasConcept C17744445 @default.
- W3154171217 hasConcept C199539241 @default.
- W3154171217 hasConcept C204321447 @default.
- W3154171217 hasConcept C2776359362 @default.
- W3154171217 hasConcept C2781238097 @default.
- W3154171217 hasConcept C41008148 @default.
- W3154171217 hasConcept C50644808 @default.
- W3154171217 hasConcept C59404180 @default.
- W3154171217 hasConcept C59822182 @default.
- W3154171217 hasConcept C86803240 @default.
- W3154171217 hasConcept C94625758 @default.
- W3154171217 hasConceptScore W3154171217C108583219 @default.
- W3154171217 hasConceptScore W3154171217C116834253 @default.
- W3154171217 hasConceptScore W3154171217C119857082 @default.
- W3154171217 hasConceptScore W3154171217C136389625 @default.
- W3154171217 hasConceptScore W3154171217C153180895 @default.
- W3154171217 hasConceptScore W3154171217C154945302 @default.
- W3154171217 hasConceptScore W3154171217C17744445 @default.
- W3154171217 hasConceptScore W3154171217C199539241 @default.
- W3154171217 hasConceptScore W3154171217C204321447 @default.
- W3154171217 hasConceptScore W3154171217C2776359362 @default.
- W3154171217 hasConceptScore W3154171217C2781238097 @default.
- W3154171217 hasConceptScore W3154171217C41008148 @default.
- W3154171217 hasConceptScore W3154171217C50644808 @default.
- W3154171217 hasConceptScore W3154171217C59404180 @default.
- W3154171217 hasConceptScore W3154171217C59822182 @default.
- W3154171217 hasConceptScore W3154171217C86803240 @default.
- W3154171217 hasConceptScore W3154171217C94625758 @default.
- W3154171217 hasLocation W31541712171 @default.
- W3154171217 hasOpenAccess W3154171217 @default.
- W3154171217 hasPrimaryLocation W31541712171 @default.
- W3154171217 hasRelatedWork W1600847575 @default.
- W3154171217 hasRelatedWork W2246822104 @default.
- W3154171217 hasRelatedWork W2552369821 @default.
- W3154171217 hasRelatedWork W2798991696 @default.
- W3154171217 hasRelatedWork W2804707815 @default.
- W3154171217 hasRelatedWork W2900503687 @default.
- W3154171217 hasRelatedWork W2940581368 @default.
- W3154171217 hasRelatedWork W2951292523 @default.
- W3154171217 hasRelatedWork W2951851780 @default.
- W3154171217 hasRelatedWork W2962889261 @default.
- W3154171217 hasRelatedWork W2980772114 @default.
- W3154171217 hasRelatedWork W2985966260 @default.
- W3154171217 hasRelatedWork W3008930492 @default.
- W3154171217 hasRelatedWork W3034373787 @default.
- W3154171217 hasRelatedWork W3039616371 @default.
- W3154171217 hasRelatedWork W3044881747 @default.
- W3154171217 hasRelatedWork W3126641641 @default.
- W3154171217 hasRelatedWork W3151194466 @default.
- W3154171217 hasRelatedWork W3207527868 @default.
- W3154171217 hasRelatedWork W3094292185 @default.
- W3154171217 isParatext "false" @default.
- W3154171217 isRetracted "false" @default.
- W3154171217 magId "3154171217" @default.
- W3154171217 workType "article" @default.