CVIRJul 29, 2020

Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval

arXiv:2007.15103v261 citations
AI Analysis

This work improves retrieval accuracy for users searching images with sketches, but it is incremental as it builds on prior methods by adding hierarchical modeling.

The paper tackled the problem of fine-grained sketch-based image retrieval by addressing the hierarchical nature of sketches, where details vary by level, and achieved state-of-the-art performance with significant improvements on benchmarks.

Sketch as an image search query is an ideal alternative to text in capturing the fine-grained visual details. Prior successes on fine-grained sketch-based image retrieval (FG-SBIR) have demonstrated the importance of tackling the unique traits of sketches as opposed to photos, e.g., temporal vs. static, strokes vs. pixels, and abstract vs. pixel-perfect. In this paper, we study a further trait of sketches that has been overlooked to date, that is, they are hierarchical in terms of the levels of detail -- a person typically sketches up to various extents of detail to depict an object. This hierarchical structure is often visually distinct. In this paper, we design a novel network that is capable of cultivating sketch-specific hierarchies and exploiting them to match sketch with photo at corresponding hierarchical levels. In particular, features from a sketch and a photo are enriched using cross-modal co-attention, coupled with hierarchical node fusion at every level to form a better embedding space to conduct retrieval. Experiments on common benchmarks show our method to outperform state-of-the-arts by a significant margin.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes