# MASK-CNN-Transformer For Real-Time Multi-Label Weather Recognition

arXiv: https://arxiv.org/abs/2304.14857 · HTML: https://mlsanity.com/paper/2304.14857/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 49 references that are in the map.
- First posted on arXiv 28 Apr 2023.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition](https://mlsanity.com/paper/1908.07325/) (2019)
- [Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition](https://mlsanity.com/paper/2009.09450/) (2020)
- [Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data](https://mlsanity.com/paper/2301.09152/) (2023)
- [Neural Message Passing for Multi-Label Classification](https://mlsanity.com/paper/1904.08049/) (2019)
- [A CNN-RNN Architecture for Multi-Label Weather Recognition](https://mlsanity.com/paper/1904.10709/) (2019)
- [TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression](https://mlsanity.com/paper/2304.14131/) (2023)

## Built on by (most cited first, 8 of 8)

- [Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook](https://mlsanity.com/paper/2310.10196/) (2023)
- [Deep Learning for Multi-Label Learning: A Comprehensive Survey](https://mlsanity.com/paper/2401.16549/) (2024)
- [Federated Distillation for Medical Image Classification: Towards Trustworthy Computer-Aided Diagnosis](https://mlsanity.com/paper/2407.02261/) (2024)
- [AoSRNet: All-in-One Scene Recovery Networks via Multi-knowledge Integration](https://mlsanity.com/paper/2402.03738/) (2024)
- [ClearVision: Leveraging CycleGAN and SigLIP-2 for Robust All-Weather Classification in Traffic Camera Imagery](https://mlsanity.com/paper/2504.19684/) (2025)
- [FMDConv: Fast Multi-Attention Dynamic Convolution via Speed-Accuracy Trade-off](https://mlsanity.com/paper/2503.17530/) (2025)
- [Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising](https://mlsanity.com/paper/2510.05589/) (2025)
- [Optimizing Multi-Agent Weather Captioning via Text Gradient Descent: A Training-Free Approach with Consensus-Aware Gradient Fusion](https://mlsanity.com/paper/2603.21673/) (2026)

## Abstract (arXiv)

Weather recognition is an essential support for many practical life applications, including traffic safety, environment, and meteorology. However, many existing related works cannot comprehensively describe weather conditions due to their complex co-occurrence dependencies. This paper proposes a novel multi-label weather recognition model considering these dependencies. The proposed model called MASK-Convolutional Neural Network-Transformer (MASK-CT) is based on the Transformer, the convolutional process, and the MASK mechanism. The model employs multiple convolutional layers to extract features from weather images and a Transformer encoder to calculate the probability of each weather condition based on the extracted features. To improve the generalization ability of MASK-CT, a MASK mechanism is used during the training phase. The effect of the MASK mechanism is explored and discussed. The Mask mechanism randomly withholds some information from one-pair training instances (one image and its corresponding label). There are two types of MASK methods. Specifically, MASK-I is designed and deployed on the image before feeding it into the weather feature extractor and MASK-II is applied to the image label. The Transformer encoder is then utilized on the randomly masked image features and labels. The experimental results from various real-world weather recognition datasets demonstrate that the proposed MASK-CT model outperforms state-of-the-art methods. Furthermore, the high-speed dynamic real-time weather recognition capability of the MASK-CT is evaluated.