Adding hierarchy-encouraging losses to hyperbolic text-image-point cloud contrastive training yields hierarchical 3D point cloud embeddings with small downstream gains.
Embedding Geometries of Contrastive Language-Image Pre-Training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Since the publication of CLIP, the approach of using InfoNCE loss for contrastive pre-training has become widely popular for bridging two or more modalities. Despite its wide adoption, CLIP's original design choices of L2 normalization and cosine similarity logit have rarely been revisited. We have systematically experimented with alternative geometries and softmax logits for language-image pre-training and identified that variants with intuitive Euclidean geometry, Euclidean CLIP (EuCLIP), match or exceed the performance of CLIP and support hierarchical relationships at least as well as more complicated hyperbolic alternative.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding
Adding hierarchy-encouraging losses to hyperbolic text-image-point cloud contrastive training yields hierarchical 3D point cloud embeddings with small downstream gains.