paper-with-me

Papers

Modality-Aware Representation Learning for Zero-shot Sketch-based Image Retrieval

2024-01-10 · Eunyi Lyou, Doyeon Lee, Jooeun Kim, Joonseok Lee

Zero-shot learning offers an efficient solution for a machine learning model to treat unseen categories, avoiding exhaustive data collection. Zero-shot Sketch-based Image Retrieval (ZS-SBIR) simulates real-world scenarios where it is hard and costly to collect paired sketch-photo samples. We propose a novel framework that indirectly aligns sketches and photos by contrasting them through texts, removing the necessity of access to sketch-photo pairs. With an explicit modality encoding learned from data, our approach disentangles modality-agnostic semantics from modality-specific information, bridging the modality gap and enabling effective cross-modal content retrieval within a joint latent space. From comprehensive experiments, we verify the efficacy of the proposed model on ZS-SBIR, and it can be also applied to generalized and fine-grained settings.

📄 PDF Abstract BibTeX arXiv:2401.04860

Code (1)

eunyi-lyou/MA-ZS-SBIR 공식 구현 pytorch

Tasks

Image RetrievalRepresentation LearningRetrievalSketch-Based Image RetrievalZero-Shot Learning

Similar Papers 제목 키워드 기반

Ontology-aware Network for Zero-shot Sketch-based Image Retrieval

2023-02-20 · Haoxiang Zhang, He Jiang, Ziqiang Wang, Deqiang Cheng

Zero-Shot Sketch-Based Image Retrieval (ZSSBIR) is an emerging task. The pioneering work focused on the modal gap but ignored inter-class information. Although recent work has begun to consider the triplet-based or contr…

Image RetrievalRetrievalSketch-Based Image RetrievalTriplet

Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval

2021-12-15 · Zongheng Huang, Yifan Sun, Chuchu Han, Changxin Gao 외

This paper tackles the Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) problem from the viewpoint of cross-modality metric learning. This task has two characteristics: 1) the zero-shot setting requires a metric space wi…

Image RetrievalMetric LearningRetrievalSketch-Based Image Retrieval+1

Symmetrical Bidirectional Knowledge Alignment for Zero-Shot Sketch-Based Image Retrieval

2023-12-16 · Decheng Liu, Xu Luo, Chunlei Peng, Nannan Wang 외

This paper studies the problem of zero-shot sketch-based image retrieval (ZS-SBIR), which aims to use sketches from unseen categories as queries to match the images of the same category. Due to the large cross-modality d…

Image RetrievalKnowledge DistillationRetrievalSketch-Based Image Retrieval

A Zero-Shot Sketch-based Inter-Modal Object Retrieval Scheme for Remote Sensing Images

2020-08-12 · Ushasi Chaudhuri, Biplab Banerjee, Avik Bhattacharya, Mihai Datcu

Conventional existing retrieval methods in remote sensing (RS) are often based on a uni-modal data retrieval framework. In this work, we propose a novel inter-modal triplet-based zero-shot retrieval scheme utilizing a sk…

RetrievalTriplet

On Learning Semantic Representations for Million-Scale Free-Hand Sketches

2020-07-07 · Peng Xu, Yongye Huang, Tongtong Yuan, Tao Xiang 외

In this paper, we study learning semantic representations for million-scale free-hand sketches. This is highly challenging due to the domain-unique traits of sketches, e.g., diverse, sparse, abstract, noisy. We propose a…

Deep HashingLearning Semantic RepresentationsRetrievalZero-Shot Learning