# Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels

arXiv: https://arxiv.org/abs/2010.08644 · HTML: https://mlsanity.com/paper/2010.08644/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2112.01515/) (2021)
- [Visual Explanations from Spiking Neural Networks using Interspike Intervals](https://mlsanity.com/paper/2103.14441/) (2021)
- [Poly-CAM: High resolution class activation map for convolutional neural networks](https://mlsanity.com/paper/2204.13359/) (2022)
- [Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism](https://mlsanity.com/paper/2209.11189/) (2022)
- [Expected Grad-CAM: Towards gradient faithfulness](https://mlsanity.com/paper/2406.01274/) (2024)
- [Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach](https://mlsanity.com/paper/2411.14946/) (2024)
- [Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry](https://mlsanity.com/paper/2402.11670/) (2024)
- [BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models](https://mlsanity.com/paper/2210.17130/) (2022)
- [Text-Driven Weakly Supervised OCT Lesion Segmentation with Structural Guidance](https://mlsanity.com/paper/2411.12615/) (2024)
- [Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks](https://mlsanity.com/paper/2510.25134/) (2025)

## Abstract (arXiv)

Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activation mapping (CAM) and Grad-CAM, use only the deepest, lowest resolution convolutional layer, missing all information in intermediate layers. We propose Zoom-CAM: going beyond the last lowest resolution layer by integrating the importance maps over all activations in intermediate layers. Zoom-CAM captures fine-grained small-scale objects for various discriminative class instances, which are commonly missed by the baseline visualization methods. We focus on generating pixel-level pseudo-labels from class labels. The quality of our pseudo-labels evaluated on the ImageNet localization task exhibits more than 2.8% improvement on top-1 error. For weakly supervised semantic segmentation our generated pseudo-labels improve a state of the art model by 1.1%.