Improving Object Detection and Attribute Recognition by Feature Entanglement Reduction

TL;DR

This paper proposes a two-stream model to disentangle category and attribute features in object detection, leading to improved accuracy in detecting objects and their attributes like color and material.

Contribution

The paper introduces a novel two-stream architecture that reduces feature entanglement between object categories and attributes, enhancing detection performance.

Findings

Significant improvements on VG-20 dataset.

Effective disentanglement of category and attribute features.

Enhanced attribute transfer capabilities.

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.