# Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps

arXiv: https://arxiv.org/abs/2006.05220 · HTML: https://mlsanity.com/paper/2006.05220/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2020.

## Built on by (most cited first, 15 of 15)

- [Conformer: Local Features Coupling Global Representations for Visual Recognition](https://mlsanity.com/paper/2105.03889/) (2021)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.04523/) (2021)
- [Background Activation Suppression for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.00580/) (2021)
- [CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping](https://mlsanity.com/paper/2205.13922/) (2022)
- [Weakly Supervised Object Localization as Domain Adaption](https://mlsanity.com/paper/2203.01714/) (2022)
- [Re-Attention Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2208.01838/) (2022)
- [Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization](https://mlsanity.com/paper/2207.07818/) (2022)
- [Background-aware Classification Activation Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.14379/) (2021)
- [Weakly Supervised Semantic Segmentation of Remote Sensing Images for Tree Species Classification Based on Explanation Methods](https://mlsanity.com/paper/2201.07495/) (2022)
- [SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost](https://mlsanity.com/paper/2111.03392/) (2021)
- [Dual Progressive Transformations for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2209.15211/) (2022)
- [Unsupervised Object Localization with Representer Point Selection](https://mlsanity.com/paper/2309.04172/) (2023)
- [Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection](https://mlsanity.com/paper/2108.01785/) (2021)
- [Learning a Weight Map for Weakly-Supervised Localization](https://mlsanity.com/paper/2111.14131/) (2021)

## Abstract (arXiv)

Recently, remarkable progress has been made in weakly supervised object localization (WSOL) to promote object localization maps. The common practice of evaluating these maps applies an indirect and coarse way, i.e., obtaining tight bounding boxes which can cover high-activation regions and calculating intersection-over-union (IoU) scores between the predicted and ground-truth boxes. This measurement can evaluate the ability of localization maps to some extent, but we argue that the maps should be measured directly and delicately, i.e., comparing the maps with the ground-truth object masks pixel-wisely. To fulfill the direct evaluation, we annotate pixel-level object masks on the ILSVRC validation set. We propose to use IoU-Threshold curves for evaluating the real quality of localization maps. Beyond the amended evaluation metric and annotated object masks, this work also introduces a novel self-enhancement method to harvest accurate object localization maps and object boundaries with only category labels as supervision. We propose a two-stage approach to generate the localization maps by simply comparing the similarity of point-wise features between the high-activation and the rest pixels. Based on the predicted localization maps, we explore to estimate object boundaries on a very large dataset. A hard-negative suppression loss is proposed for obtaining fine boundaries. We conduct extensive experiments on the ILSVRC and CUB benchmarks. In particular, the proposed Self-Enhancement Maps achieve the state-of-the-art localization accuracy of 54.88% on ILSVRC. The code and the annotated masks are released at https://github.com/xiaomengyc/SEM.