# WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection

arXiv: https://arxiv.org/abs/1909.04972 · HTML: https://mlsanity.com/paper/1909.04972/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2019.

## Built on by (most cited first, 30 of 51)

- [Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning](https://mlsanity.com/paper/2104.03135/) (2021)
- [Weakly Supervised Temporal Adjacent Network for Language Grounding](https://mlsanity.com/paper/2106.16136/) (2021)
- [Point-to-Box Network for Accurate Object Detection via Single Point Supervision](https://mlsanity.com/paper/2207.06827/) (2022)
- [Self-supervised object detection from audio-visual correspondence](https://mlsanity.com/paper/2104.06401/) (2021)
- [Fine-grained Visual Classification with High-temperature Refinement and Background Suppression](https://mlsanity.com/paper/2303.06442/) (2023)
- [Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters](https://mlsanity.com/paper/2108.01499/) (2021)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Object Discovery via Contrastive Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2208.07576/) (2022)
- [Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations](https://mlsanity.com/paper/2303.16891/) (2023)
- [Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes](https://mlsanity.com/paper/2407.11464/) (2024)
- [Weakly Supervised Open-Vocabulary Object Detection](https://mlsanity.com/paper/2312.12437/) (2023)
- [Reference-based Defect Detection Network](https://mlsanity.com/paper/2108.04456/) (2021)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection](https://mlsanity.com/paper/2207.12104/) (2022)
- [Salvage of Supervision in Weakly Supervised Object Detection](https://mlsanity.com/paper/2106.04073/) (2021)
- [ALWOD: Active Learning for Weakly-Supervised Object Detection](https://mlsanity.com/paper/2309.07914/) (2023)
- [DAP: Detection-Aware Pre-training with Weak Supervision](https://mlsanity.com/paper/2103.16651/) (2021)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [Learning Remote Sensing Object Detection with Single Point Supervision](https://mlsanity.com/paper/2305.14141/) (2023)
- [Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey](https://mlsanity.com/paper/2105.12694/) (2021)
- [Complete Instances Mining for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2402.07633/) (2024)
- [CaT: Weakly Supervised Object Detection with Category Transfer](https://mlsanity.com/paper/2108.07487/) (2021)
- [Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation](https://mlsanity.com/paper/2110.09674/) (2021)
- [Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information](https://mlsanity.com/paper/2204.10068/) (2022)
- [Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection](https://mlsanity.com/paper/2308.05991/) (2023)
- [OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning](https://mlsanity.com/paper/2108.03704/) (2021)
- [Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection](https://mlsanity.com/paper/2108.01785/) (2021)
- [Self-Supervised Object Detection via Generative Image Synthesis](https://mlsanity.com/paper/2110.09848/) (2021)
- [Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information](https://mlsanity.com/paper/2405.04913/) (2024)
- [Online Active Proposal Set Generation for Weakly Supervised Object Detection](https://mlsanity.com/paper/2101.07929/) (2021)

## Abstract (arXiv)

We study on weakly-supervised object detection (WSOD) which plays a vital role in relieving human involvement from object-level annotations. Predominant works integrate region proposal mechanisms with convolutional neural networks (CNN). Although CNN is proficient in extracting discriminative local features, grand challenges still exist to measure the likelihood of a bounding box containing a complete object (i.e., "objectness"). In this paper, we propose a novel WSOD framework with Objectness Distillation (i.e., WSOD^2) by designing a tailored training mechanism for weakly-supervised object detection. Multiple regression targets are specifically determined by jointly considering bottom-up (BU) and top-down (TD) objectness from low-level measurement and CNN confidences with an adaptive linear combination. As bounding box regression can facilitate a region proposal learning to approach its regression target with high objectness during training, deep objectness representation learned from bottom-up evidences can be gradually distilled into CNN by optimization. We explore different adaptive training curves for BU/TD objectness, and show that the proposed WSOD^2 can achieve state-of-the-art results.