OCC-MLLM-CoT-Alpha: Towards Multi-stage Occlusion Recognition Based on Large Language Models via 3D-Aware Supervision and Chain-of-Thoughts Guidance

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Chaoyi, Li, Baoqing, Di, Xinhan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912313015009280
author Wang, Chaoyi
Li, Baoqing
Di, Xinhan
author_facet Wang, Chaoyi
Li, Baoqing
Di, Xinhan
contents Comprehending occluded objects are not well studied in existing large-scale visual-language multi-modal models. Current state-of-the-art multi-modal large models struggles to provide satisfactory results in understanding occluded objects through universal visual encoders and supervised learning strategies. Therefore, we propose OCC-MLLM-CoT-Alpha, a multi-modal large vision language framework that integrates 3D-aware supervision and Chain-of-Thoughts guidance. Particularly, (1) we build a multi-modal large vision-language model framework which is consisted of a large multi-modal vision-language model and a 3D reconstruction expert model. (2) the corresponding multi-modal Chain-of-Thoughts is learned through a combination of supervised and reinforcement training strategies, allowing the multi-modal vision-language model to enhance the recognition ability with learned multi-modal chain-of-thoughts guidance. (3) A large-scale multi-modal chain-of-thoughts reasoning dataset, consisting of $110k$ samples of occluded objects held in hand, is built. In the evaluation, the proposed methods demonstrate decision score improvement of 15.75%,15.30%,16.98%,14.62%, and 4.42%,3.63%,6.94%,10.70% for two settings of a variety of state-of-the-art models.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04781
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OCC-MLLM-CoT-Alpha: Towards Multi-stage Occlusion Recognition Based on Large Language Models via 3D-Aware Supervision and Chain-of-Thoughts Guidance
Wang, Chaoyi
Li, Baoqing
Di, Xinhan
Computer Vision and Pattern Recognition
I.2.10; I.4.8
Comprehending occluded objects are not well studied in existing large-scale visual-language multi-modal models. Current state-of-the-art multi-modal large models struggles to provide satisfactory results in understanding occluded objects through universal visual encoders and supervised learning strategies. Therefore, we propose OCC-MLLM-CoT-Alpha, a multi-modal large vision language framework that integrates 3D-aware supervision and Chain-of-Thoughts guidance. Particularly, (1) we build a multi-modal large vision-language model framework which is consisted of a large multi-modal vision-language model and a 3D reconstruction expert model. (2) the corresponding multi-modal Chain-of-Thoughts is learned through a combination of supervised and reinforcement training strategies, allowing the multi-modal vision-language model to enhance the recognition ability with learned multi-modal chain-of-thoughts guidance. (3) A large-scale multi-modal chain-of-thoughts reasoning dataset, consisting of $110k$ samples of occluded objects held in hand, is built. In the evaluation, the proposed methods demonstrate decision score improvement of 15.75%,15.30%,16.98%,14.62%, and 4.42%,3.63%,6.94%,10.70% for two settings of a variety of state-of-the-art models.
title OCC-MLLM-CoT-Alpha: Towards Multi-stage Occlusion Recognition Based on Large Language Models via 3D-Aware Supervision and Chain-of-Thoughts Guidance
topic Computer Vision and Pattern Recognition
I.2.10; I.4.8
url https://arxiv.org/abs/2504.04781