# Distribution Aligned Feature Clustering for Zero-Shot Sketch-Based Image Retrieval

arXiv: https://arxiv.org/abs/2301.06685 · HTML: https://mlsanity.com/paper/2301.06685/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 42 references that are in the map.
- First posted on arXiv 17 Jan 2023.

## Builds on (most cited first, 8 of 8)

- [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)
- [Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval](https://mlsanity.com/paper/1903.03372/) (2019)
- [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)
- [Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment](https://mlsanity.com/paper/2006.12770/) (2020)
- [Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2106.11841/) (2021)
- [Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2112.07966/) (2021)

## Built on by (most cited first, 1 of 1)

- [Symmetrical Bidirectional Knowledge Alignment for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2312.10320/) (2023)

## Abstract (arXiv)

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a challenging cross-modal retrieval task. In prior arts, the retrieval is conducted by sorting the distance between the query sketch and each image in the gallery. However, the domain gap and the zero-shot setting make neural networks hard to generalize. This paper tackles the challenges from a new perspective: utilizing gallery image features. We propose a Cluster-then-Retrieve (ClusterRetri) method that performs clustering on the gallery images and uses the cluster centroids as proxies for retrieval. Furthermore, a distribution alignment loss is proposed to align the image and sketch features with a common Gaussian distribution, reducing the domain gap. Despite its simplicity, our proposed method outperforms the state-of-the-art methods by a large margin on popular datasets, e.g., up to 31% and 39% relative improvement of mAP@all on the Sketchy and TU-Berlin datasets.