AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Retrieval-driven Reasoning for Deliberative Visual Classification

Jianye Xie, Lianyong Qi, Fan Wang, Anqi Wang, Wenjuan Gong, Danxin Wang, Wanchun Dou, Yang Cao, Shichao Pei, Xiaokang Zhou

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a retrieval-driven deliberative reasoning approach for visual classification with VLMs, aiming to improve generalization and provide explanations for category choices.

Problem

Existing methods for improving VLM visual classification rely heavily on direct category-to-image matching, which limits generalization and gives no rationale for why a category is chosen.

Approach

Introduces a deliberative reasoning framework for visual classification that is driven by retrieval rather than direct category-to-image matching, so the model reasons over retrieved evidence before choosing a category.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add descriptor-based deliberative reasoning pipeline to CLIPCLIP ViT-B/32 · ImageNetaccuracy (%): 58.46 -> 70.28Improved
use image-descriptor matching instead of category-name prompts (RdR vs CBD)RdR · ImageNet, ViT-B/32accuracy (%): 62.97 -> 70.28Improved
retrieve 2 descriptors rather than 1 (ablation)RdR · ImageNet, ViT-B/16accuracy (%): 74.52 -> 75.05Improved
retrieve more descriptors (K=2 to K=5) (ablation)RdR · ImageNet, ViT-B/16accuracy (%): 75.05 -> 73.36Hurt
retrieve more descriptors (K=2 to K=5) (ablation)RdR · ImageNet, ResNet-50accuracy (%): 68.19 -> 63.09Hurt
separate visual and contextual descriptor sets instead of one unified set (ablation)RdR · 11 datasets average, ViT-B/16accuracy (%)Improved
add descriptor deliberation step (fine-tuned MLLM refines retrieved descriptors) (ablation)RdR · 11 datasets average, ViT-B/16, K=2accuracy (%): 73.29 -> 76.89Improved
add explicit deliberative reasoning before the final category (ablation)RdR · 11 datasets average, ViT-B/16, K=2accuracy (%): 73.95 -> 76.89Improved

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