mlsanityData to 7 Oct 2026

WAD-CMSN: Wasserstein Distance based Cross-Modal Semantic Network for Zero-Shot Sketch-Based Image Retrieval

arXiv 2202.05465 ↗First posted 11 Feb 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Zero-shot sketch-based image retrieval (ZSSBIR), as a popular studied branch of computer vision, attracts wide attention recently. Unlike sketch-based image retrieval (SBIR), the main aim of ZSSBIR is to retrieve natural images given free hand-drawn sketches that may not appear during training. Previous approaches used semantic aligned sketch-image pairs or utilized memory expensive fusion layer for projecting the visual information to a low dimensional subspace, which ignores the significant heterogeneous cross-domain discrepancy between highly abstract sketch and relevant image. This may yield poor performance in the training phase. To tackle this issue and overcome this drawback, we propose a Wasserstein distance based cross-modal semantic network (WAD-CMSN) for ZSSBIR. Specifically, it first projects the visual information of each branch (sketch, image) to a common low dimensional semantic subspace via Wasserstein distance in an adversarial training manner. Furthermore, identity matching loss is employed to select useful features, which can not only capture complete semantic knowledge, but also alleviate the over-fitting phenomenon caused by the WAD-CMSN model. Experimental results on the challenging Sketchy (Extended) and TU-Berlin (Extended) datasets indicate the effectiveness of the proposed WAD-CMSN model over several competitors.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 11 Feb 2022.

Builds on

22 of 42 references.

References · 22

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  3. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  4. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  5. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  6. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  7. 2015Label-Embedding for Image Classificationcited by 164
  8. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  9. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  10. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  11. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  12. 2018A Zero-Shot Framework for Sketch-based Image Retrievalcited by 70
10 more
  1. 2017Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrievalcited by 68
  2. 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
  3. 2019Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrievalcited by 57
  4. 2018Zero-Shot Sketch-Image Hashingcited by 43
  5. 2015Zero-Shot Learning via Joint Latent Similarity Embeddingcited by 39
  6. 2017Generating Visual Representations for Zero-Shot Classificationcited by 37
  7. 2016Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learningcited by 30
  8. 2020Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrievalcited by 10
  9. 2015Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identificationcited by 7
  10. 2018Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrievalcited by 2

Built on by

Not cited yet.