English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

An effective framework for learning 3D representations for perception tasksis distilling rich self-supervised image features via contrastive learning.However, image-to point representation learning for autonomous driving datasetsfaces two main challenges: 1) the abundance of self-similarity, which resultsin the contrastive losses pushing away semantically similar point and imageregions and thus disturbing the local semantic structure of the learnedrepresentations, and 2) severe class imbalance as pretraining gets dominated byover-represented classes. We propose to alleviate the self-similarity problemthrough a novel semantically tolerant image-to-point contrastive loss thattakes into consideration the semantic distance between positive and negativeimage regions to minimize contrasting semantically similar point and imageregions. Additionally, we address class imbalance by designing a class-agnosticbalanced loss that approximates the degree of class imbalance through anaggregate sample-to-samples semantic similarity measure. We demonstrate thatour semantically-tolerant contrastive loss with class balancing improvesstate-of-the art 2D-to-3D representation learning in all evaluation settings on3D semantic segmentation. Our method consistently outperforms state-of-the-art2D-to-3D representation learning frameworks across a wide range of 2Dself-supervised pretrained models.

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss