Generalisation And Sharing In Triplet Convnets For Sketch Based Visual Search

Abstract

We propose and evaluate several triplet CNN architectures for measuring the similarity between sketches and photographs, within the context of the sketch based image retrieval (SBIR) task. In contrast to recent fine-grained SBIR work, we study the ability of our networks to generalise across diverse object categories from limited training data, and explore in detail strategies for weight sharing, pre-processing, data augmentation and dimensionality reduction. We exceed the performance of pre-existing techniques on both the Flickr15k category level SBIR benchmark by \(18%\), and the TU-Berlin SBIR benchmark by \(\sim10 \mathcal\{T\}_b\), when trained on the 250 category TU-Berlin classification dataset augmented with 25k corresponding photographs harvested from the Internet.

Stats

• citations55
• S2 citations—
• github stars0
• HF likes0
• heat score13.11
• arxiv keybui2016generalisation

Related papers

• Instance-level Sketch-based Retrieval By Deep Triplet Classification Siamese Network (2018)0.00
• Transformers And Cnns Both Beat Humans On SBIR (2022)0.00
• A Recipe For Efficient SBIR Models: Combining Relative Triplet Loss With Batch Normalization And Knowledge Distillation (2023)0.00
• Exploiting Unlabelled Photos For Stronger Fine-grained SBIR (2023)10.61
• Sketchtriplet: Self-supervised Scenarized Sketch-text-image Triplet Generation (2024)4.52
• Domain-smoothing Network For Zero-shot Sketch-based Image Retrieval (2021)13.92
• Semi-heterogeneous Three-way Joint Embedding Network For Sketch-based Image Retrieval (2019)12.47
• Cross-modal Subspace Learning For Fine-grained Sketch-based Image Retrieval (2017)13.34