# Back To The Drawing Board: Rethinking Scene-Level Sketch-Based Image Retrieval Source: [Back To The Drawing Board: Rethinking Scene-Level Sketch-Based Image Retrieval]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:35:42.317Z Authors: Emil Demi\\'c, Luka \\v{C}ehovin Zajc Published: 2025-09-08T11:26:40.000Z ## Abstract The goal of Scene-level Sketch-Based Image Retrieval is to retrieve natural images matching the overall semantics and spatial layout of a free-hand sketch. Unlike prior work focused on architectural augmentations of retrieval models, we emphasize the inherent ambiguity and noise present in real-world sketches. This insight motivates a training objective that is explicitly designed to be robust to sketch variability. We show that with an appropriate combination of pre-training, encoder architecture, and loss formulation, it is possible to achieve state-of-the-art performance without the introduction of additional complexity. Extensive experiments on a challenging FS-COCO and widely-used SketchyCOCO datasets confirm the effectiveness of our approach and underline the critical role of training design in cross-modal retrieval tasks, as well as the need to improve the evaluation scenarios of scene-level SBIR. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()