# Occlusion Robustness of CLIP for Military Vehicle Classification

arXiv: https://arxiv.org/abs/2508.20760 · HTML: https://mlsanity.com/paper/2508.20760/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models](https://mlsanity.com/paper/2402.12336/) (2024)
- [An Inverse Scaling Law for CLIP Training](https://mlsanity.com/paper/2305.07017/) (2023)

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

- [Comparative Study of Out-of-the-Box Technology for Automatic Target Detection and Recognition](https://mlsanity.com/paper/2608.17917/) (2026)
- [Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions](https://mlsanity.com/paper/2609.11126/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) like CLIP enable zero-shot classification by aligning images and text in a shared embedding space, offering advantages for defense applications with scarce labeled data. However, CLIP's robustness in challenging military environments, with partial occlusion and degraded signal-to-noise ratio (SNR), remains underexplored. We investigate CLIP variants' robustness to occlusion using a custom dataset of 18 military vehicle classes and evaluate using Normalized Area Under the Curve (NAUC) across occlusion percentages. Four key insights emerge: (1) Transformer-based CLIP models consistently outperform CNNs, (2) fine-grained, dispersed occlusions degrade performance more than larger contiguous occlusions, (3) despite improved accuracy, performance of linear-probed models sharply drops at around 35% occlusion, (4) by finetuning the model's backbone, this performance drop occurs at more than 60% occlusion. These results underscore the importance of occlusion-specific augmentations during training and the need for further exploration into patch-level sensitivity and architectural resilience for real-world deployment of CLIP.