AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Grounding Language Models for Visual Entity Recognition

Zilin Xiao, Ming Gong, Paola Cascante-Bonilla, Xingyao Zhang, Jie Wu, Vicente Ordonez

ECCV 2024 · Vision-language and multimodal › Visual question answering · approach: Vision-language model VQA evaluation · 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
use retrieval-augmented constrained decoding MLLM (AutoVER) vs PaLI-17BAutoVER-7B · OVEN-Wiki val Entity seenaccuracy: 30.6 -> 61.5Improved
add retrieval to constrained decoding (ablation)AutoVER-7B-0.1 · OVEN-Wiki val Entity unseenaccuracy: 0.6 -> 19.0Improved
add retrieval to constrained decoding (ablation)AutoVER-7B-0.1 · OVEN-Wiki val Entity seenaccuracy: 50.7 -> 48.9Hurt
add constrained decoding over the trie (ablation)AutoVER-7B-0.1 · OVEN-Wiki val Entity seenaccuracy: 46.8 -> 50.7Improved
use LoRA (rank 128) instead of full tuning (ablation)AutoVER-7B-0.1 · OVEN-Wiki val Entity seenaccuracy: 48.9 -> 43.5Hurt
replace generative framework with a [CLS] classifier over 20,549 entities (ablation)AutoVER-7B-0.1 · OVEN-Wiki val Entity splitharmonic mean: 27.4 -> 0.2Hurt
scale base MLLM from 7B to 13BAutoVER · OVEN-Wiki val overallharmonic mean: 36.8 -> 39.2Improved
use AutoVER vs zero-shot GPT-4V on Query unseenAutoVER-13B · OVEN-Wiki val Query unseenaccuracy: 32.3 vs 52.7Hurt
apply retrieval-constrained decoding zero-shot to A-OKVQA-Ent vs fine-tuned LLaVA-v1.5AutoVER-7B · A-OKVQA-Ent multi-choiceoverall accuracy: 62.8 vs 72.8Hurt
apply AutoVER vs fine-tuned LLaVA-v1.5 under entity matchAutoVER-7B · A-OKVQA-Ent entity matchoverall hit rate: 46.2 -> 55.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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