Generative Partial Visual-Tactile Fused Object Clustering
Preprint
Abstract
Visual-tactile fused sensing for object clustering has achieved significant progresses recently, since the involvement of tactile modality can effectively improve clustering performance. However, the missing data (i.e., partial data) issues always happen due to occlusion and noises during the data collecting process. This issue is not well solved by most existing partial multi-view clustering methods for the heterogeneous modality challenge. Naively employing these methods would inevitably induce a negative effect and further hurt the performance. To solve the mentioned challenges, we propose a Generative Partial Visual-Tactile Fused (i.e., GPVTF) framework for object clustering. More specifically, we first do partial visual and tactile features extraction from the partial visual and tactile data, respectively, and encode the extracted features in modality-specific feature subspaces. A conditional cross-modal clustering generative adversarial network is then developed to synthesize one modality conditioning on the other modality, which can compensate missing samples and align the visual and tactile modalities naturally by adversarial learning. To the end, two pseudo-label based KL-divergence losses are employed to update the corresponding modality-specific encoders. Extensive comparative experiments on three public visual-tactile datasets prove the effectiveness of our method.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Multi-Scale Fusion Subspace Clustering Using Similarity Constraint2020
- What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation2020
- Dynamic auto-weighted multi-view co-clusteringPattern Recognition, 2020
- Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation2019
- Generative Multi-View Human Action Recognition2019
- Adversarial Fine-Grained Composition Learning for Unseen Attribute-Object Recognition2019
- Connecting Touch and Vision via Cross-Modal Prediction2019
- Incomplete Multi-view Clustering via Graph Regularized Matrix Factorization2019
- Connecting Look and Feel: Associating the Visual and Tactile Properties of Physical Materials2017
- Clustering on Multiple Incomplete Datasets via Collective Kernel Learning2013