Papers › You Only Learn One Representation: Unified Network for Multiple Tasks

You Only Learn One Representation: Unified Network for Multiple Tasks

10 May 2021arXiv:2105.04206archive 2025-07-28

Chien-Yao Wang, I-Hau Yeh, Hong-Yuan Mark Liao

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.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

WongKinYiu/yolor officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
DataXujing/YOLOR- mentioned on GitHubpytorchSyntology: not harvested report
SnailDev/github-hot-hub mentioned on GitHubpytorchMITSyntology: not harvested report
alexeyab/yolor mentioned on GitHubpytorchSyntology: not harvested report
lonnyzhang423/github-hot-hub mentioned on GitHubpytorchMITSyntology: not harvested report
rjlallana/YOLO mentioned on GitHubpytorchSyntology: not harvested report
totoadel/Minst mentioned on GitHubpytorchSyntology: not harvested report
yasarniyazoglu/YOLOR-----Object-Detection-in-Custom-Data-with-YoloR mentioned on GitHubpytorchSyntology: not harvested report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Task LearningObject DetectionReal-Time Object DetectionTraffic Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival YOLOR-D6 (1280, single-scale, 31 fps) AP50 73.5 #213 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-D6 (1280, single-scale, 31 fps) AP75 60.6 #213 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-D6 (1280, single-scale, 31 fps) APL 68.7 #213 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-D6 (1280, single-scale, 31 fps) APM 60.1 #213 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-D6 (1280, single-scale, 31 fps) APS 40.4 #213 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-P6 (1280, single-scale, 72 fps) AP50 70.6 #215 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-P6 (1280, single-scale, 72 fps) AP75 57.4 #215 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-P6 (1280, single-scale, 72 fps) APL 65.2 #215 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-P6 (1280, single-scale, 72 fps) APM 57.3 #215 of 220 Archive leaderboard report
Object Detection COCO minival YOLOR-P6 (1280, single-scale, 72 fps) APS 37.4 #215 of 220 Archive leaderboard report
Object Detection COCO test-dev YOLOR-D6 (1280, single-scale, 30 fps) AP50 73.3 #49 of 225 Archive leaderboard report
Object Detection COCO test-dev YOLOR-D6 (1280, single-scale, 30 fps) AP75 60.6 #49 of 225 Archive leaderboard report
Object Detection COCO test-dev YOLOR-D6 (1280, single-scale, 30 fps) box mAP 55.4 #49 of 225 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-D6 FPS (V100, b=1) 30 #13 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-D6 box AP 55.4 #13 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-E6 FPS (V100, b=1) 37 #19 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-E6 box AP 54.8 #19 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-W6 FPS (V100, b=1) 47 #25 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-W6 box AP 54.1 #25 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-P6D FPS (V100, b=1) 49 #34 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-P6D box AP 53 #34 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-P6 FPS (V100, b=1) 49 #41 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOR-P6 box AP 52.6 #41 of 82 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

(2+1)D Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections