Sketch-Based Image Retrieval

22 papers with code • 3 benchmarks • 4 datasets

This task has no description! Would you like to contribute one?

Latest papers without code

Towards Unsupervised Sketch-based Image Retrieval

no code yet • 18 May 2021

Current supervised sketch-based image retrieval (SBIR) methods achieve excellent performance.

Sketch-Based Image Retrieval Unsupervised Representation Learning

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

no code yet • 22 Apr 2021

Architectures based on siamese networks with triplet loss have shown outstanding performance on the image-based similarity search problem.

Sketch-Based Image Retrieval

CrossATNet - A Novel Cross-Attention Based Framework for Sketch-Based Image Retrieval

no code yet • 20 Apr 2021

While we define a cross-modal triplet loss to ensure the discriminative nature of the shared space, an innovative cross-modal attention learning strategy is also proposed to guide feature extraction from the image domain exploiting information from the respective sketch counterpart.

Sketch-Based Image Retrieval Zero-Shot Learning

Compact and Effective Representations for Sketch-based Image Retrieval

no code yet • 20 Apr 2021

We show that UMAP allows us to have feature vectors of 16 bytes improving precision by more than 35%.

Dimensionality Reduction Sketch-Based Image Retrieval

StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval

no code yet • CVPR 2021

With this meta-learning framework, our model can not only disentangle the cross-modal shared semantic content for SBIR, but can adapt the disentanglement to any unseen user style as well, making the SBIR model truly style-agnostic.

Meta-Learning Sketch-Based Image Retrieval

An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval

no code yet • 8 Feb 2021

Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted the attention of the computer vision community due to it's real-world applications, and the more realistic and challenging setting than found in SBIR.

Content-Based Image Retrieval Domain Adaptation +3

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval

no code yet • 20 Jun 2020

Low-shot sketch-based image retrieval is an emerging task in computer vision, allowing to retrieve natural images relevant to hand-drawn sketch queries that are rarely seen during the training phase.

Sketch-Based Image Retrieval

Solving Mixed-Modal Jigsaw Puzzle for Fine-Grained Sketch-Based Image Retrieval

no code yet • CVPR 2020

ImageNet pre-training has long been considered crucial by the fine-grained sketch-based image retrieval (FG-SBIR) community due to the lack of large sketch-photo paired datasets for FG-SBIR training.

Sketch-Based Image Retrieval

Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval

no code yet • 22 Mar 2020

Specifically, with the supervision of original semantic knowledge, PDFD decomposes visual features into domain features and semantic ones, and then the semantic features are projected into common space as retrieval features for ZS-SBIR.

Cross-Modal Retrieval Sketch-Based Image Retrieval

Stacked Adversarial Network for Zero-Shot Sketch based Image Retrieval

no code yet • 18 Jan 2020

Conventional approaches to Sketch-Based Image Retrieval (SBIR) assume that the data of all the classes are available during training.

Sketch-Based Image Retrieval