# Evaluating Weakly Supervised Object Localization Methods Right

arXiv: https://arxiv.org/abs/2001.07437 · HTML: https://mlsanity.com/paper/2001.07437/

## Key facts

- Cited by 105 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2020.

## Built on by (most cited first, 30 of 105)

- [Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut](https://mlsanity.com/paper/2202.11539/) (2022)
- [Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2105.08965/) (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)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [AutoMix: Unveiling the Power of Mixup for Stronger Classifiers](https://mlsanity.com/paper/2103.13027/) (2021)
- [Weakly Supervised Semantic Segmentation using Out-of-Distribution Data](https://mlsanity.com/paper/2203.03860/) (2022)
- [Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective](https://mlsanity.com/paper/2110.03095/) (2021)
- [Large-Scale Unsupervised Object Discovery](https://mlsanity.com/paper/2106.06650/) (2021)
- [Mix and Localize: Localizing Sound Sources in Mixtures](https://mlsanity.com/paper/2211.15058/) (2022)
- [DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis](https://mlsanity.com/paper/2204.10437/) (2022)
- [Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation](https://mlsanity.com/paper/2104.13243/) (2021)
- [Object-aware Contrastive Learning for Debiased Scene Representation](https://mlsanity.com/paper/2108.00049/) (2021)
- [F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling](https://mlsanity.com/paper/2109.07069/) (2021)
- [Opti-CAM: Optimizing saliency maps for interpretability](https://mlsanity.com/paper/2301.07002/) (2023)
- [Background Activation Suppression for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.00580/) (2021)
- [MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2308.03005/) (2023)
- [Background-Click Supervision for Temporal Action Localization](https://mlsanity.com/paper/2111.12449/) (2021)
- [OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning](https://mlsanity.com/paper/2209.04851/) (2022)
- [Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration](https://mlsanity.com/paper/2207.10447/) (2022)
- [Normalization Matters in Weakly Supervised Object Localization](https://mlsanity.com/paper/2107.13221/) (2021)
- [Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation](https://mlsanity.com/paper/2309.12943/) (2023)
- [Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?](https://mlsanity.com/paper/2309.06891/) (2023)
- [Keep CALM and Improve Visual Feature Attribution](https://mlsanity.com/paper/2106.07861/) (2021)
- [Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models](https://mlsanity.com/paper/2410.20155/) (2024)
- [Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2209.09209/) (2022)
- [Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization](https://mlsanity.com/paper/2204.04890/) (2022)
- [On Label Granularity and Object Localization](https://mlsanity.com/paper/2207.10225/) (2022)
- [Domain-robust VQA with diverse datasets and methods but no target labels](https://mlsanity.com/paper/2103.15974/) (2021)
- [What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs](https://mlsanity.com/paper/2206.09358/) (2022)

## Abstract (arXiv)

Weakly-supervised object localization (WSOL) has gained popularity over the last years for its promise to train localization models with only image-level labels. Since the seminal WSOL work of class activation mapping (CAM), the field has focused on how to expand the attention regions to cover objects more broadly and localize them better. However, these strategies rely on full localization supervision to validate hyperparameters and for model selection, which is in principle prohibited under the WSOL setup. In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set. We observe that, under our protocol, the five most recent WSOL methods have not made a major improvement over the CAM baseline. Moreover, we report that existing WSOL methods have not reached the few-shot learning baseline, where the full-supervision at validation time is used for model training instead. Based on our findings, we discuss some future directions for WSOL.