# Spatial-Aware Token for Weakly Supervised Object Localization arXiv: https://arxiv.org/abs/2303.10438 ยท HTML: https://mlsanity.com/paper/2303.10438/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Builds on 36 of its 54 references that are in the map. - First posted on arXiv 18 Mar 2023. ## Builds on (most cited first, 30 of 36) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014) - [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020) - [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019) - [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015) - [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013) - [Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization](https://mlsanity.com/paper/1704.04232/) (2017) - [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018) - [Conformer: Local Features Coupling Global Representations for Visual Recognition](https://mlsanity.com/paper/2105.03889/) (2021) - [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) - [Evaluating Weakly Supervised Object Localization Methods Right](https://mlsanity.com/paper/2001.07437/) (2020) - [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021) - [Deep Model Reassembly](https://mlsanity.com/paper/2210.17409/) (2022) - [Self-produced Guidance for Weakly-supervised Object Localization](https://mlsanity.com/paper/1807.08902/) (2018) - [Inter-Image Communication for Weakly Supervised Localization](https://mlsanity.com/paper/2008.05096/) (2020) - [Rethinking the Route Towards Weakly Supervised Object Localization](https://mlsanity.com/paper/2002.11359/) (2020) - [Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.04523/) (2021) - [One-Shot Object Affordance Detection in the Wild](https://mlsanity.com/paper/2108.03658/) (2021) - [Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding](https://mlsanity.com/paper/1908.10568/) (2019) - [Geometry Constrained Weakly Supervised Object Localization](https://mlsanity.com/paper/2007.09727/) (2020) - [Shallow Feature Matters for Weakly Supervised Object Localization](https://mlsanity.com/paper/2108.00873/) (2021) - [Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2110.05741/) (2021) - [Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization](https://mlsanity.com/paper/2204.00220/) (2022) - [Combinational Class Activation Maps for Weakly Supervised Object Localization](https://mlsanity.com/paper/1910.05518/) (2019) - [LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.05291/) (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) - [Learning to Discretely Compose Reasoning Module Networks for Video Captioning](https://mlsanity.com/paper/2007.09049/) (2020) ## Built on by (most cited first, 7 of 7) - [Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues](https://mlsanity.com/paper/2402.00281/) (2024) - [A Realistic Protocol for Evaluation of Weakly Supervised Object Localization](https://mlsanity.com/paper/2404.10034/) (2024) - [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) - [Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization](https://mlsanity.com/paper/2505.04905/) (2025) - [Selective Prediction Forgetting for Adaptation of Weakly Supervised Localization of Histology Images](https://mlsanity.com/paper/2603.12468/) (2026) - [Learning from Synthetic Data via Provenance-Based Input Gradient Guidance](https://mlsanity.com/paper/2604.02946/) (2026) ## Abstract (arXiv) Weakly supervised object localization (WSOL) is a challenging task aiming to localize objects with only image-level supervision. Recent works apply visual transformer to WSOL and achieve significant success by exploiting the long-range feature dependency in self-attention mechanism. However, existing transformer-based methods synthesize the classification feature maps as the localization map, which leads to optimization conflicts between classification and localization tasks. To address this problem, we propose to learn a task-specific spatial-aware token (SAT) to condition localization in a weakly supervised manner. Specifically, a spatial token is first introduced in the input space to aggregate representations for localization task. Then a spatial aware attention module is constructed, which allows spatial token to generate foreground probabilities of different patches by querying and to extract localization knowledge from the classification task. Besides, for the problem of sparse and unbalanced pixel-level supervision obtained from the image-level label, two spatial constraints, including batch area loss and normalization loss, are designed to compensate and enhance this supervision. Experiments show that the proposed SAT achieves state-of-the-art performance on both CUB-200 and ImageNet, with 98.45% and 73.13% GT-known Loc, respectively. Even under the extreme setting of using only 1 image per class from ImageNet for training, SAT already exceeds the SOTA method by 2.1% GT-known Loc. Code and models are available at https://github.com/wpy1999/SAT.