# Mid-level Elements for Object Detection

Source: [Mid-level Elements for Object Detection](<https://www.sota2.com/research/paper/68fa61ce1e209131ce9f61d3>)

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

Data updated: 2025-10-25T20:06:28.249Z

Authors: Aayush Bansal, Abhinav Shrivastava, Carl Doersch, Abhinav Gupta

Published: 2015-04-27T21:41:01.000Z

## Abstract

Building on the success of recent discriminative mid-level elements, we propose a surprisingly simple approach for object detection which performs comparable to the current state-of-the-art approaches on PASCAL VOC comp-3 detection challenge (no external data). Through extensive experiments and ablation analysis, we show how our approach effectively improves upon the HOG-based pipelines by adding an intermediate mid-level representation for the task of object detection. This representation is easily interpretable and allows us to visualize what our object detector "sees". We also discuss the insights our approach shares with CNN-based methods, such as sharing representation between categories helps.

## 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/1504.07284>)

[PDF](<https://arxiv.org/pdf/1504.07284.pdf>)