Attention-based Joint Detection of Object and Semantic Part

5 Jul 2020 Keval Morabia Jatin Arora Tara Vijaykumar

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... (read more)

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Object Detection on PASCAL Part 2010 - Animals (using extra training data)

     Get a GitHub badge
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

Methods used in the Paper


METHOD TYPE
Additive Attention
Attention Mechanisms
Single-Headed Attention
Attention Modules
RPN
Region Proposal
Softmax
Output Functions
Convolution
Convolutions
RoIPool
RoI Feature Extractors
Faster R-CNN
Object Detection Models