# Reconstruction Task Finds Universal Winning Tickets

Source: [Reconstruction Task Finds Universal Winning Tickets](<https://www.sota2.com/research/paper/68fa6be01e209131cea30cc8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:59:05.045Z

Authors: Ruichen Li, Binghui Li, Qi Qian, Liwei Wang

Published: 2022-02-23T13:04:32.000Z

## Abstract

Pruning well-trained neural networks is effective to achieve a promising accuracy-efficiency trade-off in computer vision regimes. However, most of existing pruning algorithms only focus on the classification task defined on the source domain. Different from the strong transferability of the original model, a pruned network is hard to transfer to complicated downstream tasks such as object detection arXiv:arch-ive/2012.04643. In this paper, we show that the image-level pretrain task is not capable of pruning models for diverse downstream tasks. To mitigate this problem, we introduce image reconstruction, a pixel-level task, into the traditional pruning framework. Concretely, an autoencoder is trained based on the original model, and then the pruning process is optimized with both autoencoder and classification losses. The empirical study on benchmark downstream tasks shows that the proposed method can outperform state-of-the-art results explicitly.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2202.11484>)

[PDF](<https://arxiv.org/pdf/2202.11484.pdf>)
