# A Zero-Shot Framework for Sketch-based Image Retrieval

arXiv: https://arxiv.org/abs/1807.11724 · HTML: https://mlsanity.com/paper/1807.11724/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2018.

## Built on by (most cited first, 30 of 71)

- [MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions](https://mlsanity.com/paper/2403.19651/) (2024)
- [CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not](https://mlsanity.com/paper/2303.13440/) (2023)
- [StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval](https://mlsanity.com/paper/2103.15706/) (2021)
- [More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval](https://mlsanity.com/paper/2103.13990/) (2021)
- [Sketch3T: Test-Time Training for Zero-Shot SBIR](https://mlsanity.com/paper/2203.14691/) (2022)
- [SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text](https://mlsanity.com/paper/2204.11964/) (2022)
- [Probabilistic Compositional Embeddings for Multimodal Image Retrieval](https://mlsanity.com/paper/2204.05845/) (2022)
- [Training-free Video Temporal Grounding using Large-scale Pre-trained Models](https://mlsanity.com/paper/2408.16219/) (2024)
- [Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval](https://mlsanity.com/paper/2203.14817/) (2022)
- [Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style](https://mlsanity.com/paper/2303.14348/) (2023)
- [Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis](https://mlsanity.com/paper/2104.05703/) (2021)
- [Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches](https://mlsanity.com/paper/2203.14843/) (2022)
- [What Can Human Sketches Do for Object Detection?](https://mlsanity.com/paper/2303.15149/) (2023)
- [Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings](https://mlsanity.com/paper/2303.11502/) (2023)
- [An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2102.04016/) (2021)
- [Adaptive Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2207.01723/) (2022)
- [Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR](https://mlsanity.com/paper/2303.13779/) (2023)
- [Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2106.11841/) (2021)
- [Operator SVD with Neural Networks via Nested Low-Rank Approximation](https://mlsanity.com/paper/2402.03655/) (2024)
- [You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval](https://mlsanity.com/paper/2403.07222/) (2024)
- [Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval](https://mlsanity.com/paper/2202.11948/) (2022)
- [CrossATNet - A Novel Cross-Attention Based Framework for Sketch-Based Image Retrieval](https://mlsanity.com/paper/2104.09918/) (2021)
- [BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR](https://mlsanity.com/paper/2201.06570/) (2022)
- [Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers](https://mlsanity.com/paper/2403.07214/) (2024)
- [Zero-Shot Sketch Based Image Retrieval using Graph Transformer](https://mlsanity.com/paper/2201.10185/) (2022)
- [Image Search with Text Feedback by Additive Attention Compositional Learning](https://mlsanity.com/paper/2203.03809/) (2022)
- [Data-Free Sketch-Based Image Retrieval](https://mlsanity.com/paper/2303.07775/) (2023)
- [Universal Cross-Domain Retrieval: Generalizing Across Classes and Domains](https://mlsanity.com/paper/2108.08356/) (2021)
- ['CADSketchNet' -- An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks](https://mlsanity.com/paper/2107.06212/) (2021)
- [SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval](https://mlsanity.com/paper/2111.05814/) (2021)

## Abstract (arXiv)

Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image database that correspond to a given hand-drawn sketch. Ideally, an SBIR model should learn to associate components in the sketch (say, feet, tail, etc.) with the corresponding components in the image having similar shape characteristics. However, current evaluation methods simply focus only on coarse-grained evaluation where the focus is on retrieving images which belong to the same class as the sketch but not necessarily having the same shape characteristics as in the sketch. As a result, existing methods simply learn to associate sketches with classes seen during training and hence fail to generalize to unseen classes. In this paper, we propose a new benchmark for zero-shot SBIR where the model is evaluated in novel classes that are not seen during training. We show through extensive experiments that existing models for SBIR that are trained in a discriminative setting learn only class specific mappings and fail to generalize to the proposed zero-shot setting. To circumvent this, we propose a generative approach for the SBIR task by proposing deep conditional generative models that take the sketch as an input and fill the missing information stochastically. Experiments on this new benchmark created from the "Sketchy" dataset, which is a large-scale database of sketch-photo pairs demonstrate that the performance of these generative models is significantly better than several state-of-the-art approaches in the proposed zero-shot framework of the coarse-grained SBIR task.