paper-with-me

Papers

Staying in Shape: Learning Invariant Shape Representations using Contrastive Learning

2021-07-08 · Jeffrey Gu, Serena Yeung

Creating representations of shapes that are invari-ant to isometric or almost-isometric transforma-tions has long been an area of interest in shape anal-ysis, since enforcing invariance allows the learningof more effective and robust shape representations.Most existing invariant shape representations arehandcrafted, and previous work on learning shaperepresentations do not focus on producing invariantrepresentations. To solve the problem of learningunsupervised invariant shape representations, weuse contrastive learning, which produces discrimi-native representations through learning invarianceto user-specified data augmentations. To producerepresentations that are specifically isometry andalmost-isometry invariant, we propose new dataaugmentations that randomly sample these transfor-mations. We show experimentally that our methodoutperforms previous unsupervised learning ap-proaches in both effectiveness and robustness.

📄 PDF Abstract BibTeX arXiv:2107.03552

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

Contrastive Viewpoint-aware Shape Learning for Long-term Person Re-Identification

2024-01-04 · IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 1 · Vuong D. Nguyen, Khadija Khaldi, Dung Nguyen, Pranav Mantini 외

Traditional approaches for Person Re-identification (Re-ID) rely heavily on modeling the appearance of persons. This measure is unreliable over longer durations due to the possibility for changes in clothing or biometric…

Cloth-Changing Person Re-IdentificationContrastive LearningGraph AttentionPerson Re-Identification

MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation

2022-08-18 · Gopal Sharma, Kangxue Yin, Subhransu Maji, Evangelos Kalogerakis 외

We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. This is inspired by the observation that view-based surface representations are more effective at modeling h…

Contrastive LearningSegmentation

TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval

2022-01-19 · Yue Ruan, Han-Hung Lee, Yiming Zhang, Ke Zhang 외

Text-to-shape retrieval is an increasingly relevant problem with the growth of 3D shape data. Recent work on contrastive losses for learning joint embeddings over multimodal data has been successful at tasks such as retr…

Contrastive LearningMulti-Task LearningRepresentation LearningRetrieval

Latent feature disentanglement for 3D meshes

2019-06-07 · Jake Levinson, Avneesh Sud, Ameesh Makadia

Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional V…

Disentanglement

Generative-Contrastive Learning for Self-Supervised Latent Representations of 3D Shapes from Multi-Modal Euclidean Input

2023-01-11 · Chengzhi Wu, Julius Pfrommer, Mingyuan Zhou, Jürgen Beyerer

We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes. The architecture uses two encoder branches for voxel grids and multi-view images from the …

Contrastive LearningDecoder