# Dual-Modal Prompting for Sketch-Based Image Retrieval

arXiv: https://arxiv.org/abs/2404.18695 · HTML: https://mlsanity.com/paper/2404.18695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](https://mlsanity.com/paper/2204.08583/) (2022)
- [Frozen CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2208.03550/) (2022)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval](https://mlsanity.com/paper/1904.03451/) (2019)
- [CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not](https://mlsanity.com/paper/2303.13440/) (2023)
- [A Zero-Shot Framework for Sketch-based Image Retrieval](https://mlsanity.com/paper/1807.11724/) (2018)
- [Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval](https://mlsanity.com/paper/1703.05605/) (2017)
- [CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification](https://mlsanity.com/paper/2204.14244/) (2022)
- [Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval](https://mlsanity.com/paper/1903.03372/) (2019)
- [Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model](https://mlsanity.com/paper/2208.08340/) (2022)
- [Zero-Shot Sketch-Image Hashing](https://mlsanity.com/paper/1803.02284/) (2018)
- [Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/1904.03208/) (2019)
- [SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval](https://mlsanity.com/paper/1804.01401/) (2018)
- [Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval](https://mlsanity.com/paper/2308.07648/) (2023)
- [LiveSketch: Query Perturbations for Guided Sketch-based Visual Search](https://mlsanity.com/paper/1904.06611/) (2019)
- [Sketch3T: Test-Time Training for Zero-Shot SBIR](https://mlsanity.com/paper/2203.14691/) (2022)
- [Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style](https://mlsanity.com/paper/2303.14348/) (2023)
- [Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2003.09869/) (2020)

## Abstract (arXiv)

Sketch-based image retrieval (SBIR) associates hand-drawn sketches with their corresponding realistic images. In this study, we aim to tackle two major challenges of this task simultaneously: i) zero-shot, dealing with unseen categories, and ii) fine-grained, referring to intra-category instance-level retrieval. Our key innovation lies in the realization that solely addressing this cross-category and fine-grained recognition task from the generalization perspective may be inadequate since the knowledge accumulated from limited seen categories might not be fully valuable or transferable to unseen target categories. Inspired by this, in this work, we propose a dual-modal prompting CLIP (DP-CLIP) network, in which an adaptive prompting strategy is designed. Specifically, to facilitate the adaptation of our DP-CLIP toward unpredictable target categories, we employ a set of images within the target category and the textual category label to respectively construct a set of category-adaptive prompt tokens and channel scales. By integrating the generated guidance, DP-CLIP could gain valuable category-centric insights, efficiently adapting to novel categories and capturing unique discriminative clues for effective retrieval within each target category. With these designs, our DP-CLIP outperforms the state-of-the-art fine-grained zero-shot SBIR method by 7.3% in Acc.@1 on the Sketchy dataset. Meanwhile, in the other two category-level zero-shot SBIR benchmarks, our method also achieves promising performance.