# Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth

arXiv: https://arxiv.org/abs/2303.10937 · HTML: https://mlsanity.com/paper/2303.10937/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 20 Mar 2023.

## Builds on (most cited first, 25 of 25)

- [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)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Learning to Recover 3D Scene Shape from a Single Image](https://mlsanity.com/paper/2012.09365/) (2020)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)](https://mlsanity.com/paper/2205.01397/) (2022)
- [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks](https://mlsanity.com/paper/1907.06781/) (2019)
- [Multiple Instance Detection Network with Online Instance Classifier Refinement](https://mlsanity.com/paper/1704.00138/) (2017)
- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection](https://mlsanity.com/paper/2004.04725/) (2020)
- [JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection](https://mlsanity.com/paper/2004.08515/) (2020)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [Open Vocabulary Object Detection with Pseudo Bounding-Box Labels](https://mlsanity.com/paper/2111.09452/) (2021)
- [Siamese Network for RGB-D Salient Object Detection and Beyond](https://mlsanity.com/paper/2008.12134/) (2020)
- [RGBD Salient Object Detection via Deep Fusion](https://mlsanity.com/paper/1607.03333/) (2016)
- [Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection](https://mlsanity.com/paper/1907.10164/) (2019)
- [SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2207.07898/) (2022)
- [PDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detection](https://mlsanity.com/paper/1803.08636/) (2018)
- [GOOD: Exploring Geometric Cues for Detecting Objects in an Open World](https://mlsanity.com/paper/2212.11720/) (2022)
- [Salvage of Supervision in Weakly Supervised Object Detection](https://mlsanity.com/paper/2106.04073/) (2021)
- [Discover and Learn New Objects from Documentaries](https://mlsanity.com/paper/1707.09593/) (2017)
- [Pyramidal Attention for Saliency Detection](https://mlsanity.com/paper/2204.06788/) (2022)

## Built on by (most cited first, 4 of 4)

- [TITAN: Query-Token based Domain Adaptive Adversarial Learning](https://mlsanity.com/paper/2506.21484/) (2025)
- [Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion](https://mlsanity.com/paper/2409.09616/) (2024)
- [Context Aware Grounded Teacher for Source Free Object Detection](https://mlsanity.com/paper/2504.15404/) (2025)
- [Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection](https://mlsanity.com/paper/2605.13140/) (2026)

## Abstract (arXiv)

Despite recent attention and exploration of depth for various tasks, it is still an unexplored modality for weakly-supervised object detection (WSOD). We propose an amplifier method for enhancing the performance of WSOD by integrating depth information. Our approach can be applied to any WSOD method based on multiple-instance learning, without necessitating additional annotations or inducing large computational expenses. Our proposed method employs a monocular depth estimation technique to obtain hallucinated depth information, which is then incorporated into a Siamese WSOD network using contrastive loss and fusion. By analyzing the relationship between language context and depth, we calculate depth priors to identify the bounding box proposals that may contain an object of interest. These depth priors are then utilized to update the list of pseudo ground-truth boxes, or adjust the confidence of per-box predictions. Our proposed method is evaluated on six datasets (COCO, PASCAL VOC, Conceptual Captions, Clipart1k, Watercolor2k, and Comic2k) by implementing it on top of two state-of-the-art WSOD methods, and we demonstrate a substantial enhancement in performance.