When Regression Meets Manifold Learning For Object Recognition And Pose Estimation

Abstract

In this work, we propose a method for object recognition and pose estimation from depth images using convolutional neural networks. Previous methods addressing this problem rely on manifold learning to learn low dimensional viewpoint descriptors and employ them in a nearest neighbor search on an estimated descriptor space. In comparison we create an efficient multi-task learning framework combining manifold descriptor learning and pose regression. By combining the strengths of manifold learning using triplet loss and pose regression, we could either estimate the pose directly reducing the complexity compared to NN search, or use learned descriptor for the NN descriptor matching. By in depth experimental evaluation of the novel loss function we observed that the view descriptors learned by the network are much more discriminative resulting in almost 30% increase regarding relative pose accuracy compared to related works. On the other hand, regarding directly regressed poses we obtained

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keybui2018when

Related papers

• 3D Object Instance Recognition And Pose Estimation Using Triplet Loss With Dynamic Margin (2019)11.76
• Multiview-consistent Semi-supervised Learning For 3D Human Pose Estimation (2019)13.05
• End-to-end Learning Of Keypoint Detector And Descriptor For Pose Invariant 3D Matching (2018)12.40
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Cross-modal Manifold Learning For Cross-modal Retrieval (2016)0.00
• View-invariant, Occlusion-robust Probabilistic Embedding For Human Pose (2020)8.82
• An Application Of Manifold Learning In Global Shape Descriptors (2019)5.84
• For Manifold Learning, Deep Neural Networks Can Be Locality Sensitive Hash Functions (2021)0.00