• Corpus ID: 246016317

BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR

  title={BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR},
  author={Ushasi Chaudhuri and Ruchika Chavan and Biplab Banerjee and Anjan Dutta and Zeynep Akata},
The efficacy of zero-shot sketch-based image retrieval (ZS-SBIR) models is governed by two challenges. The immense distributions-gap between the sketches and the images requires a proper domain alignment. Moreover, the fine-grained nature of the task and the high intra-class variance of many categories necessitates a class-wise discriminative mapping among the sketch, image, and the semantic spaces. Under this premise, we propose BDA-SketRet, a novel ZS-SBIR framework performing a bi-level… 
Zero-Shot Sketch Based Image Retrieval using Graph Transformer
A novelgraph transformer based zero-shot sketch-based image retrieval (GTZSR) framework for solving ZS-SBIR tasks which uses a novel graph transformer to preserve the topology of the classes in the semantic space and propagates the context-graph of theclasses within the embedding features of the visual space.


Zero-Shot Sketch-Based Image Retrieval via Graph Convolution Network
A SketchGCN model utilizing the graph convolution network, which simultaneously considers both the visual information and the semantic information is proposed, which can effectively narrow the domain gap and transfer the knowledge.
Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-Based Image Retrieval
A semantically aligned paired cycle-consistent generative adversarial network (SEM-PCYC) for any-shot SBIR, where each branch of the generative adversary maps the visual information from sketch and image to a common semantic space via adversarial training.
Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval
  • Anjan Dutta, Zeynep Akata
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
A semantically aligned paired cycle-consistent generative (SEM-PCYC) model for zero-shot SBIR, where each branch maintains a cycle consistency that only requires supervision at category levels, and avoids the need of highly-priced aligned sketch-image pairs.
Stacked Adversarial Network for Zero-Shot Sketch based Image Retrieval
A generative approach based on the Stacked Adversarial Network (SAN) and the advantage of Siamese Network (SN) for ZS-SBIR is proposed and a significant improvement in standard ZSL as well as in a more challenging generalized ZSL setting (GZSL) for SBIR.
Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval
This paper designs an approach named Semantic-Aware Knowledge prEservation (SAKE), which fine-tunes the pre-trained model in an economical way and leverages semantic information, e.g., inter-class relationship, to achieve the goal of knowledge preservation.
Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval
A Progressive Domain-independent Feature Decomposition (PDFD) network for ZS-SBIR is proposed, 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 SBIR.
Style-Guided Zero-Shot Sketch-based Image Retrieval
This work proposes a novel framework which decomposes each image and sketch into its domainindependent content and a domain, as well as data-dependent variation/style component, and utilizes the image specific styles to guide the generation of fake images using the query content to be used for retrieval.
Adaptive Margin Diversity Regularizer for Handling Data Imbalance in Zero-Shot SBIR
A novel framework AMDReg (Adaptive Margin Diversity Regularizer) is proposed, which ensures that the embeddings of the sketch and images in the latent space are not only semantically meaningful, but they are also separated according to their class-representations in the training set.
Generative Domain-Migration Hashing for Sketch-to-Image Retrieval
A Generative Domain-migration Hashing approach, which for the first time generates hashing codes from synthetic natural images that are migrated from sketches that can migrate sketches to their indistinguishable image counterparts while preserving the domain-invariant information of sketches.