# Data-Driven Scene Understanding with Adaptively Retrieved Exemplars

Source: [Data-Driven Scene Understanding with Adaptively Retrieved Exemplars](<https://www.sota2.com/research/paper/68fa61b01e209131ce9f54e2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:03:28.249Z

Authors: Xionghao Liu, Wei Yang, Liang Lin, Qing Wang, Zhaoquan Cai, Jianhuang Lai

Published: 2015-02-03T06:04:14.000Z

## Abstract

This article investigates a data-driven approach for semantically scene understanding, without pixelwise annotation and classifier training. Our framework parses a target image with two steps: (i) retrieving its exemplars (i.e. references) from an image database, where all images are unsegmented but annotated with tags; (ii) recovering its pixel labels by propagating semantics from the references. We present a novel framework making the two steps mutually conditional and bootstrapped under the probabilistic Expectation-Maximization (EM) formulation. In the first step, the references are selected by jointly matching their appearances with the target as well as the semantics (i.e. the assigned labels of the target and the references). We process the second step via a combinatorial graphical representation, in which the vertices are superpixels extracted from the target and its selected references. Then we derive the potentials of assigning labels to one vertex of the target, which depend upon the graph edges that connect the vertex to its spatial neighbors of the target and to its similar vertices of the references. Besides, the proposed framework can be naturally applied to perform image annotation on new test images. In the experiments, we validate our approach on two public databases, and demonstrate superior performances over the state-of-the-art methods in both semantic segmentation and image annotation tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1502.00749>)

[PDF](<https://arxiv.org/pdf/1502.00749.pdf>)
