# Correlation of Object Detection Performance with Visual Saliency and Depth Estimation

arXiv: https://arxiv.org/abs/2411.02844 · HTML: https://mlsanity.com/paper/2411.02844/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 8 of 8)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [DIODE: A Dense Indoor and Outdoor DEpth Dataset](https://mlsanity.com/paper/1908.00463/) (2019)
- [Multi-Task Learning for Visual Scene Understanding](https://mlsanity.com/paper/2203.14896/) (2022)
- [Integrating Saliency Ranking and Reinforcement Learning for Enhanced Object Detection](https://mlsanity.com/paper/2408.06803/) (2024)

## Built on by (most cited first, 3 of 3)

- [DTFSal: Audio-Visual Dynamic Token Fusion for Video Saliency Prediction](https://mlsanity.com/paper/2504.10070/) (2025)
- [Learning Using Privileged Information for Litter Detection](https://mlsanity.com/paper/2508.04124/) (2025)
- [Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach](https://mlsanity.com/paper/2601.02016/) (2026)

## Abstract (arXiv)

As object detection techniques continue to evolve, understanding their relationships with complementary visual tasks becomes crucial for optimising model architectures and computational resources. This paper investigates the correlations between object detection accuracy and two fundamental visual tasks: depth prediction and visual saliency prediction. Through comprehensive experiments using state-of-the-art models (DeepGaze IIE, Depth Anything, DPT-Large, and Itti's model) on COCO and Pascal VOC datasets, we find that visual saliency shows consistently stronger correlations with object detection accuracy (mAρ up to 0.459 on Pascal VOC) compared to depth prediction (mAρ up to 0.283). Our analysis reveals significant variations in these correlations across object categories, with larger objects showing correlation values up to three times higher than smaller objects. These findings suggest incorporating visual saliency features into object detection architectures could be more beneficial than depth information, particularly for specific object categories. The observed category-specific variations also provide insights for targeted feature engineering and dataset design improvements, potentially leading to more efficient and accurate object detection systems.