You Only Learn One Representation: Unified Network for Multiple Tasks

By Chien-Yao Wang, I-Hau Yeh, Hongpeng Liao. Journal of information science and engineering, 2021

596 citations recorded by the source corpus.

People ``understand'' the world via vision, hearing, tactile, and also the past experience. Human experience can be learned through normal learning (we call it explicit knowledge), or subconsciously (we call it implicit knowledge). These experiences learned through normal learning or subconsciously will be encoded and stored in the brain. Using these abundant experience as a huge database, human beings can effectively process data, even they were unseen beforehand. In this paper, we propose a unified network to encode implicit knowledge and explicit knowledge together, just like the human brain can learn knowledge from normal learning as well as subconsciousness learning. The unified network can generate a unified representation to simultaneously serve various tasks. We can perform kernel space alignment, prediction refinement, and multi-task learning in a convolutional neural network. The results demonstrate that when implicit knowledge is introduced into the neural network, it benefits the performance of all tasks. We further analyze the implicit representation learnt from the proposed unified network, and it shows great capability on catching the physical meaning of different tasks. The source code of this work is at : https://github.com/WongKinYiu/yolor.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0b14b26cf6c3dd161e272707b1b0236bc8152155

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors (2022, methodology): “As for methods such as YOLOX [20] and YOLOR [79], they focus on improving the inference speed of various GPUs.”
Designing Network Design Strategies Through Gradient Path Analysis (2022, methodology): “As for baseline architecture we chose residual-based YOLOv3-SPP [23], and for baseline decoder we chose a combination of YOLOR [34] and YOLO-v5 (r6.”
YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception (2025, unknown): “YOLOR [26] fused explicit and implicit features for richer representations and stronger generalization.”
A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond (2023, unknown): “YOLOv7 [94] was published in ArXiv in July 2022 by the same authors of YOLOv4 and YOLOR.”