# Exploring Bottom-up and Top-down Cues with Attentive Learning for Webly Supervised Object Detection

arXiv: https://arxiv.org/abs/2003.09790 · HTML: https://mlsanity.com/paper/2003.09790/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [Learning Meta-class Memory for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.02958/) (2021)
- [Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification](https://mlsanity.com/paper/2106.06133/) (2021)
- [Webly Supervised Concept Expansion for General Purpose Vision Models](https://mlsanity.com/paper/2202.02317/) (2022)
- [MV-TON: Memory-based Video Virtual Try-on network](https://mlsanity.com/paper/2108.07502/) (2021)
- [Visual Understanding of Complex Table Structures from Document Images](https://mlsanity.com/paper/2111.07129/) (2021)
- [Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation](https://mlsanity.com/paper/2207.09084/) (2022)
- [Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation](https://mlsanity.com/paper/2108.07413/) (2021)
- [Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation](https://mlsanity.com/paper/2303.05164/) (2023)
- [Long-tailed Recognition by Learning from Latent Categories](https://mlsanity.com/paper/2206.01010/) (2022)

## Abstract (arXiv)

Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly supervised object detection (WebSOD) method for novel classes which only requires the web images without further annotations. Our proposed method combines bottom-up and top-down cues for novel class detection. Within our approach, we introduce a bottom-up mechanism based on the well-trained fully supervised object detector (i.e. Faster RCNN) as an object region estimator for web images by recognizing the common objectiveness shared by base and novel classes. With the estimated regions on the web images, we then utilize the top-down attention cues as the guidance for region classification. Furthermore, we propose a residual feature refinement (RFR) block to tackle the domain mismatch between web domain and the target domain. We demonstrate our proposed method on PASCAL VOC dataset with three different novel/base splits. Without any target-domain novel-class images and annotations, our proposed webly supervised object detection model is able to achieve promising performance for novel classes. Moreover, we also conduct transfer learning experiments on large scale ILSVRC 2013 detection dataset and achieve state-of-the-art performance.