REVIEW 5 cited by
The All-Seeing Project V2: Towards General Relation Comprehension of the Open World
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present the All-Seeing Project V2: a new model and dataset designed for understanding object relations in images. Specifically, we propose the All-Seeing Model V2 (ASMv2) that integrates the formulation of text generation, object localization, and relation comprehension into a relation conversation (ReC) task. Leveraging this unified task, our model excels not only in perceiving and recognizing all objects within the image but also in grasping the intricate relation graph between them, diminishing the relation hallucination often encountered by Multi-modal Large Language Models (MLLMs). To facilitate training and evaluation of MLLMs in relation understanding, we created the first high-quality ReC dataset ({AS-V2) which is aligned with the format of standard instruction tuning data. In addition, we design a new benchmark, termed Circular-based Relation Probing Evaluation (CRPE) for comprehensively evaluating the relation comprehension capabilities of MLLMs. Notably, our ASMv2 achieves an overall accuracy of 52.04 on this relation-aware benchmark, surpassing the 43.14 of LLaVA-1.5 by a large margin. We hope that our work can inspire more future research and contribute to the evolution towards artificial general intelligence. Our project is released at https://github.com/OpenGVLab/all-seeing.
Forward citations
Cited by 5 Pith papers
-
VoCap: Video Object Captioning and Segmentation from Any Prompt
VoCap jointly performs promptable video object segmentation and object captioning, and introduces a 50k-video pseudo-caption dataset that improves both tasks.
-
Docopilot: Improving Multimodal Models for Document-Level Understanding
A new academic-paper dataset and a retrieval-free fine-tuned InternVL2 model improve multi-page document QA accuracy and latency on several benchmarks.
-
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
Adding task-specific heads for tracking, grounding, and segmentation to multimodal LLMs via a three-stage training recipe improves both fine-grained visual tasks and general video understanding benchmarks.
-
The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities
Breeze2 continues pretraining Llama on a 900GB Traditional Chinese corpus, then adds LLaVA-style vision and function-calling fine-tuning, reporting top size-class scores on a mix of public and self-built benchmarks.
-
Visual Large Language Models for Generalized and Specialized Applications
This paper reviews and taxonomizes VLLM applications into vision-to-text, vision-to-action, and text-to-vision, adding ethics and future-work discussion.
Discussion (0). Continue with ORCID to comment.