AI Paper Atlas

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

Most and Least Retrievable Images in Visual-Language Query Systems

Liuwan Zhu, Rui Ning, Jiang Li, Chunsheng Xin, Hongyi Wu

ECCV 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 1 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
use APGD-R (random resize, pad and noise) instead of APGD for LRI against JPEG compression (ablation)LRI · ImageNet, ViT-B/32, JPEG defensemR@10 secret keyword: 0.4 -> 97.2Improved
use APGD-R instead of APGD for MRI against JPEG compression (ablation)MRI · ImageNet, ViT-B/32, JPEG defensemR@10: 0.4 -> 60.1Improved
use APGD-R instead of APGD for MRI against random resizing and padding (ablation)MRI · ImageNet, ViT-B/32, R&P defensemR@10: 0.2 -> 79.0Improved
use APGD optimizer instead of PGD for MRI (ablation)MRI · Paris, ViT-B/32, epsilon 0.03mR@1: PGD less than 15% -> APGD over 80%Improved
use APGD instead of PGD for LRI (ablation)LRI · Paris, ViT-B/32, epsilon 0.02mR@1 secret keyword: 80% -> approximately 98%Improved
use FGSM instead of APGD/PGD (ablation)MRI/LRI · Paris, ViT-B/32retrieval probability: MRI top-100 less than 3%, LRI less than 10%Hurt
increase MRI generation iterations from 300 to 1000 on ViT-B/32 (ablation)MRI · MSCOCO, ViT-B/32mR@1: less than 40% -> about 40% top-1; over 87% top-1 on ResNet50 at 1000Improved
use the proposed LRI loss instead of Fooling targeted attackLRI · Flickr30k, ResNet50x4mR@1 secret keyword: 3.2 -> 97.1Improved
use the proposed LRI loss instead of Fooling (image quality)LRI · L2 distortionL2 distortion: 28.85 -> 8.31Improved
switch target model from ResNet50 to ViT-B/32MRI · ImageNet keyword querymR@1: 87.3 -> 41.6Hurt

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