Implementation:Open compass VLMEvalKit M4Bench

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Multi-Image Understanding

Overview

Benchmark dataset implementation for M4Bench evaluation in VLMEvalKit.

Description

M4Bench inherits from ImageBaseDataset and implements the M4Bench benchmark for multi-image understanding across five tasks: State Invariance, State Comparison, Spatial Perception, Instance Comparison, and Detailed Difference. The TYPE field is set to 'M4Bench'.

Usage

Registered in vlmeval/dataset/__init__.py and invoked through build_dataset() by benchmark name.

Code Reference

Source: vlmeval/dataset/m4bench.py, Lines: L1-193
Import: from vlmeval.dataset.m4bench import M4Bench

Signature:

class M4Bench(ImageBaseDataset):
    TYPE = 'M4Bench'
    DATASET_URL = {...}
    DATASET_MD5 = {...}
    ...

I/O Contract

Direction	Description
Inputs	TSV dataset file with image/video paths and questions
Outputs	Evaluation results DataFrame with scores per category

Usage Examples

from vlmeval.dataset import build_dataset
dataset = build_dataset('State_Invariance')

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment