# Improving Object Detection and Attribute Recognition by Feature Entanglement Reduction

Source: [Improving Object Detection and Attribute Recognition by Feature Entanglement Reduction](<https://www.sota2.com/research/paper/68fa6a961e209131cea291bf>)

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

Data updated: 2025-10-25T23:28:26.804Z

Authors: Zhaoheng Zheng, Arka Sadhu, Ram Nevatia

Published: 2021-08-25T22:27:06.000Z

## Abstract

We explore object detection with two attributes: color and material. The task aims to simultaneously detect objects and infer their color and material. A straight-forward approach is to add attribute heads at the very end of a usual object detection pipeline. However, we observe that the two goals are in conflict: Object detection should be attribute-independent and attributes be largely object-independent. Features computed by a standard detection network entangle the category and attribute features; we disentangle them by the use of a two-stream model where the category and attribute features are computed independently but the classification heads share Regions of Interest (RoIs). Compared with a traditional single-stream model, our model shows significant improvements over VG-20, a subset of Visual Genome, on both supervised and attribute transfer 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/2108.11501>)

[PDF](<https://arxiv.org/pdf/2108.11501.pdf>)