Papers › X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation

X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation

24 Oct 2021arXiv:2110.12516archive 2025-07-28

Hong Cai, Janarbek Matai, Shubhankar Borse, Yizhe Zhang, Amin Ansari, Fatih Porikli

In this paper, we propose a novel method, X-Distill, to improve the self-supervised training of monocular depth via cross-task knowledge distillation from semantic segmentation to depth estimation. More specifically, during training, we utilize a pretrained semantic segmentation teacher network and transfer its semantic knowledge to the depth network. In order to enable such knowledge distillation across two different visual tasks, we introduce a small, trainable network that translates the predicted depth map to a semantic segmentation map, which can then be supervised by the teacher network. In this way, this small network enables the backpropagation from the semantic segmentation teacher's supervision to the depth network during training. In addition, since the commonly used object classes in semantic segmentation are not directly transferable to depth, we study the visual and geometric characteristics of the objects and design a new way of grouping them that can be shared by both tasks. It is noteworthy that our approach only modifies the training process and does not incur additional computation during inference. We extensively evaluate the efficacy of our proposed approach on the standard KITTI benchmark and compare it with the latest state of the art. We further test the generalizability of our approach on Make3D. Overall, the results show that our approach significantly improves the depth estimation accuracy and outperforms the state of the art.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Depth EstimationKnowledge DistillationMonocular Depth EstimationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split unsupervised X-Distill (M+1024x320) Delta < 1.25 0.895 #32 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised X-Distill (M+1024x320) Delta < 1.25^2 0.965 #32 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised X-Distill (M+1024x320) Delta < 1.25^3 0.983 #32 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised X-Distill (M+1024x320) RMSE 4.439 #32 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised X-Distill (M+1024x320) RMSE log 0.180 #32 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised X-Distill (M+1024x320) Sq Rel 0.698 #32 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised X-Distill (M+1024x320) absolute relative error 0.102 #32 of 55 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

Knowledge DistillationTest

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