Attention-based Joint Detection of Object and Semantic Part
In this paper, we address the problem of joint detection of objects like dog and its semantic parts like face, leg, etc. Our model is created on top of two Faster-RCNN models that share their features to perform a novel Attention-based feature fusion of related Object and Part features to get enhanced representations of both. These representations are used for final classification and bounding box regression separately for both models. Our experiments on the PASCAL-Part 2010 dataset show that joint detection can simultaneously improve both object detection and part detection in terms of mean Average Precision (mAP) at IoU=0.5.
PDF Abstract
Datasets
PASCAL-Part
Results from the Paper
Ranked #1 on
Object Detection
on PASCAL Part 2010 - Animals
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Object Detection | PASCAL Part 2010 - Animals | Attention-based Joint Detection of Object and Semantic Part | mAP@0.5 | 87.5 | # 1 | ||
| Semantic Part Detection | PASCAL Part 2010 - Animals | Attention-based Joint Detection of Object and Semantic Part | mAP@0.5 | 52.0 | # 1 |
