# Generalisation and Sharing in Triplet Convnets for Sketch based Visual Search

arXiv: https://arxiv.org/abs/1611.05301 · HTML: https://mlsanity.com/paper/1611.05301/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2016.

## Built on by (most cited first, 4 of 4)

- [Edge Augmentation for Large-Scale Sketch Recognition without Sketches](https://mlsanity.com/paper/2202.13164/) (2022)
- [Transformers and CNNs both Beat Humans on SBIR](https://mlsanity.com/paper/2209.06629/) (2022)
- [Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification](https://mlsanity.com/paper/2410.13582/) (2024)
- [A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation](https://mlsanity.com/paper/2305.18988/) (2023)

## Abstract (arXiv)

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 ~10 Tb, when trained on the 250 category TU-Berlin classification dataset augmented with 25k corresponding photographs harvested from the Internet.