# Combinational Class Activation Maps for Weakly Supervised Object Localization

arXiv: https://arxiv.org/abs/1910.05518 · HTML: https://mlsanity.com/paper/1910.05518/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2019.

## Built on by (most cited first, 24 of 24)

- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Class Attention Transfer Based Knowledge Distillation](https://mlsanity.com/paper/2304.12777/) (2023)
- [Shallow Feature Matters for Weakly Supervised Object Localization](https://mlsanity.com/paper/2108.00873/) (2021)
- [Visual Explanations from Spiking Neural Networks using Interspike Intervals](https://mlsanity.com/paper/2103.14441/) (2021)
- [F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling](https://mlsanity.com/paper/2109.07069/) (2021)
- [Background Activation Suppression for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.00580/) (2021)
- [Improving Weakly-supervised Object Localization via Causal Intervention](https://mlsanity.com/paper/2104.10351/) (2021)
- [CAM-loss: Towards Learning Spatially Discriminative Feature Representations](https://mlsanity.com/paper/2109.01359/) (2021)
- [Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2209.09209/) (2022)
- [TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2208.14542/) (2022)
- [Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization](https://mlsanity.com/paper/2207.07818/) (2022)
- [Negative Evidence Matters in Interpretable Histology Image Classification](https://mlsanity.com/paper/2201.02445/) (2022)
- [DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2310.06196/) (2023)
- [Privacy-Preserving Person Detection Using Low-Resolution Infrared Cameras](https://mlsanity.com/paper/2209.11335/) (2022)
- [CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2303.09044/) (2023)
- [Spatial-Aware Token for Weakly Supervised Object Localization](https://mlsanity.com/paper/2303.10438/) (2023)
- [Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey](https://mlsanity.com/paper/2105.12694/) (2021)
- [Background-aware Classification Activation Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.14379/) (2021)
- [A Realistic Protocol for Evaluation of Weakly Supervised Object Localization](https://mlsanity.com/paper/2404.10034/) (2024)
- [Knowledge-guided Causal Intervention for Weakly-supervised Object Localization](https://mlsanity.com/paper/2301.01060/) (2023)
- [MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization](https://mlsanity.com/paper/2104.14375/) (2021)
- [Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization](https://mlsanity.com/paper/2305.15354/) (2023)
- [Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label](https://mlsanity.com/paper/2404.09475/) (2024)
- [Reading Radiology Imaging Like The Radiologist](https://mlsanity.com/paper/2307.05921/) (2023)

## Abstract (arXiv)

Weakly supervised object localization has recently attracted attention since it aims to identify both class labels and locations of objects by using image-level labels. Most previous methods utilize the activation map corresponding to the highest activation source. Exploiting only one activation map of the highest probability class is often biased into limited regions or sometimes even highlights background regions. To resolve these limitations, we propose to use activation maps, named combinational class activation maps (CCAM), which are linear combinations of activation maps from the highest to the lowest probability class. By using CCAM for localization, we suppress background regions to help highlighting foreground objects more accurately. In addition, we design the network architecture to consider spatial relationships for localizing relevant object regions. Specifically, we integrate non-local modules into an existing base network at both low- and high-level layers. Our final model, named non-local combinational class activation maps (NL-CCAM), obtains superior performance compared to previous methods on representative object localization benchmarks including ILSVRC 2016 and CUB-200-2011. Furthermore, we show that the proposed method has a great capability of generalization by visualizing other datasets.