On The Classification-Distortion-Perception Tradeoff

Authors: Dong Liu, Haochen Zhang, Zhiwei Xiong

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We rigorously prove the existence of the CDP tradeoff, i.e. the distortion, perceptual difference, and classification error rate cannot be made all minimal simultaneously. We also provide both simulation and experimental results to showcase the CDP tradeoff.
Researcher Affiliation Academia Dong Liu, Haochen Zhang, Zhiwei Xiong University of Science and Technology of China, Hefei 230027, China dongeliu@ustc.edu.cn
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Our code and models are published at https://github.com/ Alan Zhang1995/CDP-Tradeoff.
Open Datasets Yes We use the MNIST handwritten digit recognition dataset [11] and the CIFAR-10 image recognition dataset [9].
Dataset Splits No The paper mentions training and testing data but does not explicitly provide details about a validation dataset split.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments are mentioned in the paper.
Software Dependencies No No specific software dependencies with version numbers are mentioned in the paper.
Experiment Setup Yes In order to showcase the CDP tradeoff, we train a restoration (denoising or SR) network with a combination of three loss functions that correspond to distortion, perceptual difference, and classification error rate. In short, the entire loss function is ℓrestoration = αℓMSE + βℓadv + γℓCE where α, β, γ are weights. ...with different combinations of (α, β, γ).