# Now You See Me: Robust approach to Partial Occlusions

arXiv: https://arxiv.org/abs/2304.11779 · HTML: https://mlsanity.com/paper/2304.11779/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 24 Apr 2023.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [A Large-Scale Car Dataset for Fine-Grained Categorization and Verification](https://mlsanity.com/paper/1506.08959/) (2015)
- [Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1807.08407/) (2018)
- [A survey of face recognition techniques under occlusion](https://mlsanity.com/paper/2006.11366/) (2020)
- [Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion](https://mlsanity.com/paper/2006.15538/) (2020)
- [Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models](https://mlsanity.com/paper/1905.04598/) (2019)
- [Grid Loss: Detecting Occluded Faces](https://mlsanity.com/paper/1609.00129/) (2016)
- [Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP](https://mlsanity.com/paper/2111.01322/) (2021)
- [Faceness-Net: Face Detection through Deep Facial Part Responses](https://mlsanity.com/paper/1701.08393/) (2017)
- [Detecting Semantic Parts on Partially Occluded Objects](https://mlsanity.com/paper/1707.07819/) (2017)
- [Unsupervised Pre-training for Biomedical Question Answering](https://mlsanity.com/paper/2009.12952/) (2020)
- [SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection](https://mlsanity.com/paper/1807.00959/) (2018)
- [What is Holding Back Convnets for Detection?](https://mlsanity.com/paper/1508.02844/) (2015)

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

- [Robustness of SAM: Segment Anything Under Corruptions and Beyond](https://mlsanity.com/paper/2306.07713/) (2023)
- [Hierarchical and Multimodal Data for Daily Activity Understanding](https://mlsanity.com/paper/2504.17696/) (2025)

## Abstract (arXiv)

Occlusions of objects is one of the indispensable problems in Computer vision. While Convolutional Neural Net-works (CNNs) provide various state of the art approaches for regular image classification, they however, prove to be not as effective for the classification of images with partial occlusions. Partial occlusion is scenario where an object is occluded partially by some other object/space. This problem when solved,holds tremendous potential to facilitate various scenarios. We in particular are interested in autonomous driving scenario and its implications in the same. Autonomous vehicle research is one of the hot topics of this decade, there are ample situations of partial occlusions of a driving sign or a person or other objects at different angles. Considering its prime importance in situations which can be further extended to video analytics of traffic data to handle crimes, anticipate income levels of various groups etc.,this holds the potential to be exploited in many ways. In this paper, we introduce our own synthetically created dataset by utilising Stanford Car Dataset and adding occlusions of various sizes and nature to it. On this created dataset, we conducted a comprehensive analysis using various state of the art CNN models such as VGG-19, ResNet 50/101, GoogleNet, DenseNet 121. We further in depth study the effect of varying occlusion proportions and nature on the performance of these models by fine tuning and training these from scratch on dataset and how is it likely to perform when trained in different scenarios, i.e., performance when training with occluded images and unoccluded images, which model is more robust to partial occlusions and soon.