# Simplified Concrete Dropout -- Improving the Generation of Attribution Masks for Fine-grained Classification

arXiv: https://arxiv.org/abs/2307.14825 · HTML: https://mlsanity.com/paper/2307.14825/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 27 Jul 2023.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](https://mlsanity.com/paper/1806.06193/) (2018)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [TransFG: A Transformer Architecture for Fine-grained Recognition](https://mlsanity.com/paper/2103.07976/) (2021)
- [Controlling the false discovery rate via knockoffs](https://mlsanity.com/paper/1404.5609/) (2014)
- [See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification](https://mlsanity.com/paper/1901.09891/) (2019)
- [The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition](https://mlsanity.com/paper/1511.06789/) (2015)
- [Visual Recognition of Great Ape Behaviours in the Wild](https://mlsanity.com/paper/2011.10759/) (2020)
- [Classification-Specific Parts for Improving Fine-Grained Visual Categorization](https://mlsanity.com/paper/1909.07075/) (2019)
- [Great Ape Detection in Challenging Jungle Camera Trap Footage via Attention-Based Spatial and Temporal Feature Blending](https://mlsanity.com/paper/1908.11240/) (2019)
- [Automated Visual Fin Identification of Individual Great White Sharks](https://mlsanity.com/paper/1609.06323/) (2016)
- [Fine-grained Recognition Datasets for Biodiversity Analysis](https://mlsanity.com/paper/1507.00913/) (2015)
- [Counterfactual Generation with Knockoffs](https://mlsanity.com/paper/2102.00951/) (2021)

## Built on by (most cited first, 2 of 2)

- [Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients](https://mlsanity.com/paper/2503.05424/) (2025)
- [Saccadic Vision for Fine-Grained Visual Classification](https://mlsanity.com/paper/2509.15688/) (2025)

## Abstract (arXiv)

Fine-grained classification is a particular case of a classification problem, aiming to classify objects that share the visual appearance and can only be distinguished by subtle differences. Fine-grained classification models are often deployed to determine animal species or individuals in automated animal monitoring systems. Precise visual explanations of the model's decision are crucial to analyze systematic errors. Attention- or gradient-based methods are commonly used to identify regions in the image that contribute the most to the classification decision. These methods deliver either too coarse or too noisy explanations, unsuitable for identifying subtle visual differences reliably. However, perturbation-based methods can precisely identify pixels causally responsible for the classification result. Fill-in of the dropout (FIDO) algorithm is one of those methods. It utilizes the concrete dropout (CD) to sample a set of attribution masks and updates the sampling parameters based on the output of the classification model. A known problem of the algorithm is a high variance in the gradient estimates, which the authors have mitigated until now by mini-batch updates of the sampling parameters. This paper presents a solution to circumvent these computational instabilities by simplifying the CD sampling and reducing reliance on large mini-batch sizes. First, it allows estimating the parameters with smaller mini-batch sizes without losing the quality of the estimates but with a reduced computational effort. Furthermore, our solution produces finer and more coherent attribution masks. Finally, we use the resulting attribution masks to improve the classification performance of a trained model without additional fine-tuning of the model.