Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ning, Chao, Gan, Wanshui, Xuan, Weihao, Yokoya, Naoto
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2503.07637
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915199668191232
author Ning, Chao
Gan, Wanshui
Xuan, Weihao
Yokoya, Naoto
author_facet Ning, Chao
Gan, Wanshui
Xuan, Weihao
Yokoya, Naoto
contents Pre-trained encoders are widely employed in dense prediction tasks for their capability to effectively extract visual features from images. The decoder subsequently processes these features to generate pixel-level predictions. However, due to structural differences and variations in input data, only encoders benefit from pre-learned representations from vision benchmarks such as image classification and self-supervised learning, while decoders are typically trained from scratch. In this paper, we introduce $\times$Net, which facilitates a "pre-trained encoder $\times$ pre-trained decoder" collaboration through three innovative designs. $\times$Net enables the direct utilization of pre-trained models within the decoder, integrating pre-learned representations into the decoding process to enhance performance in dense prediction tasks. By simply coupling the pre-trained encoder and pre-trained decoder, $\times$Net distinguishes itself as a highly promising approach. Remarkably, it achieves this without relying on decoding-specific structures or task-specific algorithms. Despite its streamlined design, $\times$Net outperforms advanced methods in tasks such as monocular depth estimation and semantic segmentation, achieving state-of-the-art performance particularly in monocular depth estimation. and semantic segmentation, achieving state-of-the-art results, especially in monocular depth estimation. embedding algorithms. Despite its streamlined design, $\times$Net outperforms advanced methods in tasks such as monocular depth estimation and semantic segmentation, achieving state-of-the-art performance particularly in monocular depth estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07637
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Is Pre-training Applicable to the Decoder for Dense Prediction?
Ning, Chao
Gan, Wanshui
Xuan, Weihao
Yokoya, Naoto
Machine Learning
Pre-trained encoders are widely employed in dense prediction tasks for their capability to effectively extract visual features from images. The decoder subsequently processes these features to generate pixel-level predictions. However, due to structural differences and variations in input data, only encoders benefit from pre-learned representations from vision benchmarks such as image classification and self-supervised learning, while decoders are typically trained from scratch. In this paper, we introduce $\times$Net, which facilitates a "pre-trained encoder $\times$ pre-trained decoder" collaboration through three innovative designs. $\times$Net enables the direct utilization of pre-trained models within the decoder, integrating pre-learned representations into the decoding process to enhance performance in dense prediction tasks. By simply coupling the pre-trained encoder and pre-trained decoder, $\times$Net distinguishes itself as a highly promising approach. Remarkably, it achieves this without relying on decoding-specific structures or task-specific algorithms. Despite its streamlined design, $\times$Net outperforms advanced methods in tasks such as monocular depth estimation and semantic segmentation, achieving state-of-the-art performance particularly in monocular depth estimation. and semantic segmentation, achieving state-of-the-art results, especially in monocular depth estimation. embedding algorithms. Despite its streamlined design, $\times$Net outperforms advanced methods in tasks such as monocular depth estimation and semantic segmentation, achieving state-of-the-art performance particularly in monocular depth estimation.
title Is Pre-training Applicable to the Decoder for Dense Prediction?
topic Machine Learning
url https://arxiv.org/abs/2503.07637