AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

SLAN: Self-Locator Aided Network for Vision-Language Understanding

Jiang-Tian Zhai, Qi Zhang, Tong Wu, Xing-Yu Chen, Jiang-Jiang Liu, Ming-Ming Cheng

ICCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Self-distillation for vision-language pretraining · 2 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
replace frozen COCO-pretrained region proposal module with learnable self-locator (ablation)SLAN ViT-Base · COCO and Flickr30k retrievalTR@1 / IR@1: 68.5 -> 69.1 (COCO TR@1); 74.1 -> 76.2 (Flickr30k IR@1)Improved
increase number of region adaptors from 0 to 3 (ablation)SLAN ViT-Base · COCO retrievalTR@1: 69.1 -> 72.1Improved
increase number of region adaptors from 0 to 3 (ablation)SLAN ViT-Base · Flickr30k retrievalIR@1: 76.2 -> 78.9Improved
keep only top-K regions ranked by saliency (ablation)SLAN region filter · COCO retrievalTR@1: 69.4 -> 70.6Improved
add saliency score threshold to top-K region filter (ablation)SLAN region filter · COCO retrievalTR@1: 70.6 -> 72.1Improved
use SLAN with ViT-Huge versus Beit-3 on VQAv2SLAN · VQAv2 test-devVQA score: 84.2 -> 84.5Improved
use SLAN versus Beit-3 on NLVR2SLAN · NLVR2 devaccuracy: 91.5 -> 91.0No clear effect
scale vision backbone from ResNet50 to ViT-Huge (ablation)SLAN · COCO object detection fine-tuneAP: 59.2 -> 63.5Improved
use SLAN with ResNet50 versus larger vision backbones for retrievalSLAN ResNet50 · COCO retrievalTR@1: ResNet50 85.1 vs BLIP ViT-Large 82.4 with fewer parametersImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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