# Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization

arXiv: https://arxiv.org/abs/1704.04232 · HTML: https://mlsanity.com/paper/1704.04232/

## Key facts

- Cited by 207 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2017.

## Built on by (most cited first, 30 of 207)

- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut](https://mlsanity.com/paper/2202.11539/) (2022)
- [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.11183/) (2022)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.08896/) (2021)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling](https://mlsanity.com/paper/2111.12085/) (2021)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation](https://mlsanity.com/paper/2210.07506/) (2022)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Learning Affordance Grounding from Exocentric Images](https://mlsanity.com/paper/2203.09905/) (2022)
- [Complementary Patch for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.03852/) (2021)
- [A Closer Look at Weakly-Supervised Audio-Visual Source Localization](https://mlsanity.com/paper/2209.09634/) (2022)
- [CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning](https://mlsanity.com/paper/2103.16392/) (2021)
- [Improving Deep Learning Interpretability by Saliency Guided Training](https://mlsanity.com/paper/2111.14338/) (2021)
- [Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.09653/) (2022)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.05803/) (2023)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)
- [Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.04523/) (2021)
- [A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2101.00545/) (2021)
- [Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05029/) (2021)
- [Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation](https://mlsanity.com/paper/2210.17400/) (2022)
- [ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2203.15187/) (2022)
- [A Comprehensive Survey on Data Augmentation](https://mlsanity.com/paper/2405.09591/) (2024)
- [Weakly Supervised Temporal Adjacent Network for Language Grounding](https://mlsanity.com/paper/2106.16136/) (2021)
- [Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2209.07761/) (2022)
- [Shallow Feature Matters for Weakly Supervised Object Localization](https://mlsanity.com/paper/2108.00873/) (2021)
- [SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2111.13495/) (2021)

## Abstract (arXiv)

We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos. Most existing weakly-supervised methods localize only the most discriminative parts of an object rather than all relevant parts, which leads to suboptimal performance. Our key idea is to hide patches in a training image randomly, forcing the network to seek other relevant parts when the most discriminative part is hidden. Our approach only needs to modify the input image and can work with any network designed for object localization. During testing, we do not need to hide any patches. Our Hide-and-Seek approach obtains superior performance compared to previous methods for weakly-supervised object localization on the ILSVRC dataset. We also demonstrate that our framework can be easily extended to weakly-supervised action localization.