# Attention-based Joint Detection of Object and Semantic Part

arXiv: https://arxiv.org/abs/2007.02419 · HTML: https://mlsanity.com/paper/2007.02419/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [Personalize Segment Anything Model with One Shot](https://mlsanity.com/paper/2305.03048/) (2023)
- [Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching](https://mlsanity.com/paper/2305.13310/) (2023)
- [Bridge the Points: Graph-based Few-shot Segment Anything Semantically](https://mlsanity.com/paper/2410.06964/) (2024)
- [A Simple Image Segmentation Framework via In-Context Examples](https://mlsanity.com/paper/2410.04842/) (2024)
- [Towards Training-free Open-world Segmentation via Image Prompt Foundation Models](https://mlsanity.com/paper/2310.10912/) (2023)
- [PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects](https://mlsanity.com/paper/2407.16696/) (2024)
- [Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models](https://mlsanity.com/paper/2505.07209/) (2025)
- [Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation](https://mlsanity.com/paper/2306.07404/) (2023)
- [Unlocking the Power of SAM 2 for Few-Shot Segmentation](https://mlsanity.com/paper/2505.14100/) (2025)
- [CoVA: Context-aware Visual Attention for Webpage Information Extraction](https://mlsanity.com/paper/2110.12320/) (2021)
- [NubbleDrop: A Simple Way to Improve Matching Strategy for Prompted One-Shot Segmentation](https://mlsanity.com/paper/2405.11476/) (2024)

## Abstract (arXiv)

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.