Papers › Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D...

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

16 Dec 2022arXiv:2212.08320archive 2025-07-28

Runpei Dong, Zekun Qi, Linfeng Zhang, Junbo Zhang, Jianjian Sun, Zheng Ge, Li Yi, Kaisheng Ma

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Modal Teachers (ACT). The pretrained Transformers are transferred as cross-modal 3D teachers using discrete variational autoencoding self-supervision, during which the Transformers are frozen with prompt tuning for better knowledge inheritance. The latent features encoded by the 3D teachers are used as the target of masked point modeling, wherein the dark knowledge is distilled to the 3D Transformer students as foundational geometry understanding. Our ACT pretrained 3D learner achieves state-of-the-art generalization capacity across various downstream benchmarks, e.g., 88.21% overall accuracy on ScanObjectNN. Codes have been released at https://github.com/RunpeiDong/ACT.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

runpeidong/act officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ShapeLLM: Universal 3D Object Understanding for Embodied Interaction (arXiv:2402.17766; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
asterisci/point-gcc mentioned on GitHubpytorchMITSyntology: not harvested report
qizekun/ReCon mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ShapeLLM: Universal 3D Object Understanding for Embodied Interaction (arXiv:2402.17766; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
qizekun/vpp mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation (arXiv:2307.16605; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 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

3D Point Cloud ClassificationFew-Shot 3D Point Cloud ClassificationKnowledge DistillationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ScanObjectNN ACT Overall Accuracy 89.17 #29 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN ACT (no voting) OBJ-BG (OA) 93.29 #39 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN ACT (no voting) OBJ-ONLY (OA) 91.91 #39 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN ACT (no voting) Overall Accuracy 88.21 #39 of 77 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) ACT Overall Accuracy 93.3 #9 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) ACT Standard Deviation 4.0 #9 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) ACT Overall Accuracy 95.6 #11 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) ACT Standard Deviation 2.8 #11 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) ACT Overall Accuracy 96.8 #14 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) ACT Standard Deviation 2.3 #14 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) ACT Overall Accuracy 98.0 #13 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) ACT Standard Deviation 1.4 #13 of 30 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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