# Positive-Unlabeled Compression on the Cloud

arXiv: https://arxiv.org/abs/1909.09757 · HTML: https://mlsanity.com/paper/1909.09757/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2019.

## Built on by (most cited first, 27 of 27)

- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Source-Free Domain Adaptation via Distribution Estimation](https://mlsanity.com/paper/2204.11257/) (2022)
- [Multiscale Positive-Unlabeled Detection of AI-Generated Texts](https://mlsanity.com/paper/2305.18149/) (2023)
- [Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation](https://mlsanity.com/paper/2107.01378/) (2021)
- [GhostNetV2: Enhance Cheap Operation with Long-Range Attention](https://mlsanity.com/paper/2211.12905/) (2022)
- [Manifold Regularized Dynamic Network Pruning](https://mlsanity.com/paper/2103.05861/) (2021)
- [Learning Frequency Domain Approximation for Binary Neural Networks](https://mlsanity.com/paper/2103.00841/) (2021)
- [Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data](https://mlsanity.com/paper/2110.15094/) (2021)
- [Boosting Light-Weight Depth Estimation Via Knowledge Distillation](https://mlsanity.com/paper/2105.06143/) (2021)
- [GhostNets on Heterogeneous Devices via Cheap Operations](https://mlsanity.com/paper/2201.03297/) (2022)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator](https://mlsanity.com/paper/2102.07358/) (2021)
- [Distribution Shift Matters for Knowledge Distillation with Webly Collected Images](https://mlsanity.com/paper/2307.11469/) (2023)
- [Dense Depth Distillation with Out-of-Distribution Simulated Images](https://mlsanity.com/paper/2208.12464/) (2022)
- [Efficient and Effective Model Extraction](https://mlsanity.com/paper/2409.14122/) (2024)
- [Unsupervised Search for Ethnic Minorities' Medical Segmentation Training Set](https://mlsanity.com/paper/2501.02442/) (2025)
- [Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling](https://mlsanity.com/paper/2210.12575/) (2022)
- [Redistribution of Weights and Activations for AdderNet Quantization](https://mlsanity.com/paper/2212.10200/) (2022)
- [BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons](https://mlsanity.com/paper/2212.14158/) (2022)
- [Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning](https://mlsanity.com/paper/2302.06271/) (2023)
- [Anti-Compression Contrastive Facial Forgery Detection](https://mlsanity.com/paper/2302.06183/) (2023)
- [Training Quantized Deep Neural Networks via Cooperative Coevolution](https://mlsanity.com/paper/2112.14834/) (2021)
- [Bipartite Mode Matching for Vision Training Set Search from a Hierarchical Data Server](https://mlsanity.com/paper/2601.09531/) (2026)
- [Distillation from heterogeneous unlabeled collections](https://mlsanity.com/paper/2201.06507/) (2022)
- [Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection](https://mlsanity.com/paper/2302.10437/) (2023)
- [Navigating Efficiency in MobileViT through Gaussian Process on Global Architecture Factors](https://mlsanity.com/paper/2406.04820/) (2024)
- [Seeing the Whole Picture: Distribution-Guided Data-Free Distillation for Semantic Segmentation](https://mlsanity.com/paper/2512.13175/) (2025)

## Abstract (arXiv)

Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providing compression and acceleration service of deep learning models on the cloud is therefore of significance and is attractive for end users. However, existing network compression and acceleration approaches usually fine-tuning the svelte model by requesting the entire original training data (eg ImageNet), which could be more cumbersome than the network itself and cannot be easily uploaded to the cloud. In this paper, we present a novel positive-unlabeled (PU) setting for addressing this problem. In practice, only a small portion of the original training set is required as positive examples and more useful training examples can be obtained from the massive unlabeled data on the cloud through a PU classifier with an attention based multi-scale feature extractor. We further introduce a robust knowledge distillation (RKD) scheme to deal with the class imbalance problem of these newly augmented training examples. The superiority of the proposed method is verified through experiments conducted on the benchmark models and datasets. We can use only 8% of uniformly selected data from the ImageNet to obtain an efficient model with comparable performance to the baseline ResNet-34.