paper-with-me

홈 › Papers

"Does it come in black?" CLIP-like models are zero-shot recommenders

2022-04-05 · Patrick John Chia, Jacopo Tagliabue, Federico Bianchi, Ciro Greco, Diogo Goncalves

Product discovery is a crucial component for online shopping. However, item-to-item recommendations today do not allow users to explore changes along selected dimensions: given a query item, can a model suggest something similar but in a different color? We consider item recommendations of the comparative nature (e.g. "something darker") and show how CLIP-based models can support this use case in a zero-shot manner. Leveraging a large model built for fashion, we introduce GradREC and its industry potential, and offer a first rounded assessment of its strength and weaknesses.

📄 PDF Abstract BibTeX arXiv:2204.02473

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

FashionCLIP FashionCLIP is a fine-tuned CLIP model on fashion data (more than 800K pairs). It is the first foundation model for Fashion.

Similar Papers 제목 키워드 기반

“Does it come in black?” CLIP-like models are zero-shot recommenders

2022-05-01 · ECNLP (ACL) 2022 5 · Patrick John Chia, Jacopo Tagliabue, Federico Bianchi, Ciro Greco 외

Product discovery is a crucial component for online shopping. However, item-to-item recommendations today do not allow users to explore changes along selected dimensions: given a query item, can a model suggest something…

VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection

2025-03-28 · Bin Zhang, Xiaoyang Qu, Guokuan Li, Jiguang Wan 외

As object detectors are increasingly deployed as black-box cloud services or pre-trained models with restricted access to the original training data, the challenge of zero-shot object-level out-of-distribution (OOD) dete…

ObjectOut of Distribution (OOD) Detection

CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning

2023-05-26 · Zhaoheng Zheng, Haidong Zhu, Ram Nevatia

In this paper, we study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts. Recent researchers focus on applying large-scale Visio…

AttributeCompositional Zero-Shot LearningZero-Shot Learning

CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification

2025-02-25 · Mingkun Zhang, Keping Bi, Wei Chen, Jiafeng Guo 외

In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image wi…

Denoisingzero-shot-classificationZero-Shot Learning

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?

2023-10-14 · Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge 외

Foundation models like CLIP are trained on hundreds of millions of samples and effortlessly generalize to new tasks and inputs. Out of the box, CLIP shows stellar zero-shot and few-shot capabilities on a wide range of ou…

AttributeOut-of-Distribution Generalization