Triplet-Center Loss for Multi-view 3D Object Retrieval

By Xinwei He, Yang Zhou, Zhichao Zhou, Song Bai, Xiang Bai. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

373 citations recorded by the source corpus.

Most existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with deep metric learning for 3D object retrieval is more or less neglected. In the paper, we study variants of deep metric learning losses for 3D object retrieval, which did not receive enough attention from this area. First, two kinds of representative losses, triplet loss and center loss, are introduced which could learn more discriminative features than traditional classification loss. Then, we propose a novel loss named triplet-center loss, which can further enhance the discriminative power of the features. The proposed triplet-center loss learns a center for each class and requires that the distances between samples and centers from the same class are closer than those from different classes. Extensive experimental results on two popular 3D object retrieval benchmarks and two widely-adopted sketch-based 3D shape retrieval benchmarks consistently demonstrate the effectiveness of our proposed loss, and significant improvements have been achieved compared with the state-of-the-arts.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/abb6e069538588bd1214bf2744e41181d164f41b

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations (2020, methodology): “In the computer vision (CV) literature, deep metric learning (DML) has been used to great effect for learning visual representations [24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34].”
View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions (2018, result): “The compared results include LFD, SHD, Fisher vector, 3D ShapeNets (Wu et al. 2015), GeoIm-age (Sinha, Bai, and Ramani 2016), Pano (Shi et al. 2015), MVCNN (Su et al. 2015), GIFT (Bai et al. 2017), RAMA (Sﬁkas, Theoharis, and Pratikakis 2017) and Trip (He et al. 2018).”
Towards 3D VR-Sketch to 3D Shape Retrieval (2020, methodology): “Multi-view representation We choose View N-Gram Network (NGVNN) [12] as a baseline for a multi-view based shape retrieval, since it was shown to outperform all the alternative existing solutions [17][13][7][30] on the 3D-shape based retrieval task on ModelNet40.”
Classification-Based Anomaly Detection for General Data (2020, methodology): “Similarly to He et al. (2018), to stabilize training, we added a softmax + cross entropy loss, as well as L 2 norm regularization for the extracted features f ( x ) .”
Transductive Zero-Shot Learning for 3D Point Cloud Classification (2019, methodology): “Learning with a Triplet Loss: Triplet losses have been widely used in computer vision [44, 32, 12, 16, 11].”
Clustering-Oriented Representation Learning with Attractive-Repulsive Loss (2018, methodology): “…et al. 2018; Hsu, Lv, and Kira 2018), and triplet-based methods (Norouzi, Fleet, and Salakhutdinov 2012; Schroff, Kalenichenko, and Philbin 2015; He et al. 2018); all of these require sophisticated methods for sampling training data, necessitating more hyperparameters and architectural…”
DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (2019, neutral): “Points PointNet [10] 1k 70.”
Bi-Directional Center-Constrained Top-Ranking for Visible Thermal Person Re-Identification (2020, background): “The basic idea is to replace the comparison of anchor to samples by anchor to centers [55].”
PF-Net: Point Fractal Network for 3D Point Cloud Completion (2020, background): “However, multi-view and voxel-based representation[18, 7, 34, 11, 13, 37] leads to unnecessarily voluminous and limits the output resolution of voxels.”
Deep Metric Learning: A Survey (2019, background): “The authors in [48] attempted to find a more robust and discriminative feature that was embedded with a novel loss function that combined triplet loss and center loss for 3D image retrieval task.”
Deep Anomaly Detection for Generalized Face Anti-Spoofing (2019, background): “Recent work [17] demonstrates that the triplet loss, acting as a regularizer of the softmax function, achieves more discriminative and robust embeddings.”