# A Realistic Protocol for Evaluation of Weakly Supervised Object Localization arXiv: https://arxiv.org/abs/2404.10034 ยท HTML: https://mlsanity.com/paper/2404.10034/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 38 of its 66 references that are in the map. - First posted on arXiv 15 Apr 2024. ## Builds on (most cited first, 30 of 38) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015) - [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021) - [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016) - [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015) - [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019) - [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016) - [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018) - [Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization](https://mlsanity.com/paper/1704.04232/) (2017) - [Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis](https://mlsanity.com/paper/1804.06353/) (2018) - [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018) - [Attention-based Dropout Layer for Weakly Supervised Object Localization](https://mlsanity.com/paper/1908.10028/) (2019) - [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021) - [CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2212.09506/) (2022) - [Evaluating Weakly Supervised Object Localization Methods Right](https://mlsanity.com/paper/2001.07437/) (2020) - [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022) - [Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density](https://mlsanity.com/paper/2108.10860/) (2021) - [Early Stopping without a Validation Set](https://mlsanity.com/paper/1703.09580/) (2017) - [A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification](https://mlsanity.com/paper/2104.00679/) (2021) - [Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey](https://mlsanity.com/paper/1909.03354/) (2019) - [F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling](https://mlsanity.com/paper/2109.07069/) (2021) - [Combinational Class Activation Maps for Weakly Supervised Object Localization](https://mlsanity.com/paper/1910.05518/) (2019) - [Early Stopping is Nonparametric Variational Inference](https://mlsanity.com/paper/1504.01344/) (2015) - [Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration](https://mlsanity.com/paper/2207.10447/) (2022) - [Weakly Supervised Object Localization Using Size Estimates](https://mlsanity.com/paper/1608.04314/) (2016) - [Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation](https://mlsanity.com/paper/2305.01281/) (2023) - [Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?](https://mlsanity.com/paper/2305.18712/) (2023) - [Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2209.09209/) (2022) - [Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation](https://mlsanity.com/paper/2107.12972/) (2021) - [Better Practices for Domain Adaptation](https://mlsanity.com/paper/2309.03879/) (2023) ## Built on by (most cited first, 5 of 5) - [BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change](https://mlsanity.com/paper/2505.19328/) (2025) - [Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions](https://mlsanity.com/paper/2604.11730/) (2026) - [TeD-Loc: Text Distillation for Weakly Supervised Object Localization](https://mlsanity.com/paper/2501.12632/) (2025) - [PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization](https://mlsanity.com/paper/2503.24135/) (2025) - [Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution](https://mlsanity.com/paper/2605.05283/) (2026) ## Abstract (arXiv) Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only global class-level labels. The absence of bounding box (bbox) supervision during training raises challenges in the literature for hyper-parameter tuning, model selection, and evaluation. WSOL methods rely on a validation set with bbox annotations for model selection, and a test set with bbox annotations for threshold estimation for producing bboxes from localization maps. This approach, however, is not aligned with the WSOL setting as these annotations are typically unavailable in real-world scenarios. Our initial empirical analysis shows a significant decline in LOC performance when model selection and threshold estimation rely solely on class labels and the image itself, respectively, compared to using manual bbox annotations. This highlights the importance of incorporating bbox labels for optimal model performance. In this paper,a new WSOL evaluation protocol is proposed that provides LOC information without the need for manual bbox annotations. In particular, we generated noisy pseudo-boxes from a pretrained off-the-shelf region proposal method such as Selective Search, CLIP, and RPN for model selection. These bboxes are also employed to estimate the threshold from LOC maps, circumventing the need for test-set bbox annotations. Our experiments with several WSOL methods on challenging natural and medical image datasets show that using the proposed pseudo-bboxes for validation facilitates the model selection and threshold estimation, with LOC performance comparable to models selected using GT bboxes on the validation set and threshold estimation on the test set. It also outperforms models selected using class-level labels, and then dynamically thresholded with only LOC maps.