# A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection

Source: [A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection](<https://www.sota2.com/research/paper/68fa68f01e209131cea1f1f2>)

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

Data updated: 2025-10-25T22:49:52.437Z

Authors: Jianbo Liu, Sijie Ren, Yuanjie Zheng, Xiaogang Wang, Hongsheng Li

Published: 2020-12-18T10:51:49.000Z

## Abstract

Both high-level and high-resolution feature representations are of great importance in various visual understanding tasks. To acquire high-resolution feature maps with high-level semantic information, one common strategy is to adopt dilated convolutions in the backbone networks to extract high-resolution feature maps, such as the dilatedFCN-based methods for semantic segmentation. However, due to many convolution operations are conducted on the high-resolution feature maps, such methods have large computational complexity and memory consumption. In this paper, we propose one novel holistically-guided decoder which is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding is achieved via novel holistic codeword generation and codeword assembly operations, which take advantages of both the high-level and low-level features from the encoder features. With the proposed holistically-guided decoder, we implement the EfficientFCN architecture for semantic segmentation and HGD-FPN for object detection and instance segmentation. The EfficientFCN achieves comparable or even better performance than state-of-the-art methods with only 1/3 of their computational costs for semantic segmentation on PASCAL Context, PASCAL VOC, ADE20K datasets. Meanwhile, the proposed HGD-FPN achieves $\>2\\%$ higher mean Average Precision (mAP) when integrated into several object detection frameworks with ResNet-50 encoding backbones.

## 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/2012.10162>)

[PDF](<https://arxiv.org/pdf/2012.10162.pdf>)