# Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches

arXiv: https://arxiv.org/abs/1610.06756 · HTML: https://mlsanity.com/paper/1610.06756/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2016.

## Built on by (most cited first, 5 of 5)

- [A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?](https://mlsanity.com/paper/2112.00639/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Custom Object Detection via Multi-Camera Self-Supervised Learning](https://mlsanity.com/paper/2102.03442/) (2021)
- [Modeling Generalized Specialist Approach To Train Quality Resilient Snapshot Ensemble](https://mlsanity.com/paper/2206.05853/) (2022)
- [SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks](https://mlsanity.com/paper/2505.15628/) (2025)

## Abstract (arXiv)

In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to image transformations encountered during wild image capture?; (2) how can we predict CNN sensitivity?; and (3) can we increase the robustness of CNNs with respect to image degradations? To answer the first question, we provide an extensive empirical sensitivity analysis of commonly used CNN architectures (AlexNet, VGG19, GoogleNet) across various types of image degradations. This allows for predicting CNN performance for new domains comprised by images of lower quality or captured from a different viewpoint. We also show how the sensitivity of CNN outputs can be predicted for single images. Furthermore, we demonstrate that input layer dropout or pre-filtering during test time only reduces CNN sensitivity for high levels of degradation. Experiments for fine-grained recognition tasks reveal that VGG19 is more robust to severe image degradations than AlexNet and GoogleNet. However, small intensity noise can lead to dramatic changes in CNN performance even for VGG19.