A survey on self-supervised learning: Algorithms, applications, and future trends

J Gui, T Chen, J Zhang, Q Cao, Z Sun… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Nesf: Neural semantic fields for generalizable semantic segmentation of 3d scenes

S Vora, N Radwan, K Greff, H Meyer, K Genova… - arxiv preprint arxiv …, 2021 - arxiv.org
We present NeSF, a method for producing 3D semantic fields from posed RGB images
alone. In place of classical 3D representations, our method builds on recent work in implicit …

Cross-modal center loss for 3D cross-modal retrieval

L **g, E Vahdani, J Tan, Y Tian - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Cross-modal retrieval aims to learn discriminative and modal-invariant features for data from
different modalities. Unlike the existing methods which usually learn from the features …

Point cloud pre-training with natural 3d structures

R Yamada, H Kataoka, N Chiba… - Proceedings of the …, 2022 - openaccess.thecvf.com
The construction of 3D point cloud datasets requires a great deal of human effort. Therefore,
constructing a largescale 3D point clouds dataset is difficult. In order to remedy this issue …