# CLICv2: Image Complexity Representation via Content Invariance Contrastive Learning

arXiv: https://arxiv.org/abs/2503.06641 · HTML: https://mlsanity.com/paper/2503.06641/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Efficient Algorithms for t-distributed Stochastic Neighborhood Embedding](https://mlsanity.com/paper/1712.09005/) (2017)
- [Semantic Segmentation using Vision Transformers: A survey](https://mlsanity.com/paper/2305.03273/) (2023)
- [Masked Frequency Modeling for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2206.07706/) (2022)
- [Criticality Metrics for Automated Driving: A Review and Suitability Analysis of the State of the Art](https://mlsanity.com/paper/2108.02403/) (2021)
- [Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning](https://mlsanity.com/paper/2104.11056/) (2021)
- [ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection](https://mlsanity.com/paper/2305.16713/) (2023)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [DeepMIM: Deep Supervision for Masked Image Modeling](https://mlsanity.com/paper/2303.08817/) (2023)
- [Patch-wise Contrastive Style Learning for Instagram Filter Removal](https://mlsanity.com/paper/2204.07486/) (2022)
- [Patch-wise Graph Contrastive Learning for Image Translation](https://mlsanity.com/paper/2312.08223/) (2023)
- [CLIC: Contrastive Learning Framework for Unsupervised Image Complexity Representation](https://mlsanity.com/paper/2411.12792/) (2024)

## Built on by (most cited first, 4 of 4)

- [Image Complexity-Aware Adaptive Retrieval for Efficient Vision-Language Models](https://mlsanity.com/paper/2512.15372/) (2025)
- [Describe-to-Score: A text-guided framework for image complexity assessment](https://mlsanity.com/paper/2509.16609/) (2025)
- [DReX: Pure Vision Fusion of Self-Supervised and Convolutional Representations for Image Complexity Prediction](https://mlsanity.com/paper/2511.16991/) (2025)
- [The Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning](https://mlsanity.com/paper/2606.04280/) (2026)

## Abstract (arXiv)

Unsupervised image complexity representation often suffers from bias in positive sample selection and sensitivity to image content. We propose CLICv2, a contrastive learning framework that enforces content invariance for complexity representation. Unlike CLIC, which generates positive samples via cropping-introducing positive pairs bias-our shifted patchify method applies randomized directional shifts to image patches before contrastive learning. Patches at corresponding positions serve as positive pairs, ensuring content-invariant learning. Additionally, we propose patch-wise contrastive loss, which enhances local complexity representation while mitigating content interference. In order to further suppress the interference of image content, we introduce Masked Image Modeling as an auxiliary task, but we set its modeling objective as the entropy of masked patches, which recovers the entropy of the overall image by using the information of the unmasked patches, and then obtains the global complexity perception ability. Extensive experiments on IC9600 demonstrate that CLICv2 significantly outperforms existing unsupervised methods in PCC and SRCC, achieving content-invariant complexity representation without introducing positive pairs bias.