AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Freeview Sketching: View-Aware Fine-Grained Sketch-Based Image Retrieval

Aneeshan Sain, Pinaki Nath Chowdhury, Subhadeep Koley, Ayan Kumar Bhunia, Yi-Zhe Song

ECCV 2024 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add disentangled view feature and view-specific retrieval objective in place of a single shared featureFG-SBIR baseline · pilot study, chairs, view-mismatched galleryAcc@1: 58.25 then a drop of 27.15%Hurt
add view-specific triplet loss L_Tri^VS (ablation)Ours VGG-16 · Chairs view-specificTop-1: 21.12 -> 60.71Improved
add view-agnostic triplet loss L_Tri^VA (ablation)Ours VGG-16 · Chairs view-agnosticmAP@all: 0.104 -> 0.615Improved
add instance-consistency loss on multi-view projections (ablation)Ours VGG-16 · Chairs view-agnosticmAP@all: 0.520 -> 0.615Improved
add view-consistency loss between sketch and photo views (ablation)Ours VGG-16 · Chairs view-specificTop-1: 55.69 -> 60.71Improved
add cross-view reconstruction loss L_VR (ablation)Ours VGG-16 · Chairs view-specificTop-1: 56.26 -> 60.71Improved
use multi-view 2D projections of 3D shapes during training (ablation)Ours VGG-16 · Chairs view-specificTop-1: 50.79 -> 60.71Improved
use one disentangled model instead of two separate models per paradigm (ablation)Ours VGG-16 · Chairs view-agnosticmAP@all: 0.421 -> 0.615Improved
use shared encoder instead of separate content and view encoders (ablation)Ours VGG-16 · Chairs view-specificTop-1: 54.32 -> 60.71Improved
reconstruct photo instead of edgemap in view reconstruction (ablation)Ours VGG-16 · Chairs view-specificTop-1: 57.68 -> 60.71Improved
replace PVT backbone with VGG-16 backbone (ablation)Ours · Chairs view-agnosticmAP@all: 0.689 -> 0.615Hurt
add colour augmentation on rendered projections (ablation)Ours VGG-16 · ChairsmAP / Acc@1: 0.065 mAP, 2.85% Acc@1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy