How to Recycle: General Vision-Language Model without Task Tuning for Predicting Object Recyclability
15. prosince 2023
Řečníci
Eliot Park
Speaker · 0 followers
Shreya Johri
Speaker · 0 followers
Pranav Rajpurkar
Speaker · 0 followers
O prezentaci
Waste segregation and recycling place a crucial role in fostering environmental sustainability. However, discerning the whether a material is recyclable or not poses a formidable challenge, primarily because of inadequate recycling guidelines to accommodate a diverse spectrum of objects and their varying conditions. We investigated the role of vision-language models in addressing this challenge. We curated a dataset consisting >1000 images across 11 disposal categories for optimal discarding and assessed the applicability of general vision-language models for recyclability classification. Our results show that Contrastive Language-Image Pre- training (CLIP) model, which is pretrained to understand the relationship between images and text, demonstrated remarkable performance in the zero-shot recycla- bility classification task, with an accuracy of 89Waste segregation and recycling place a crucial role in fostering environmental sustainability. However, discerning the whether a material is recyclable or not poses a formidable challenge, primarily because of inadequate recycling guidelines to accommodate a diverse spectrum of objects and their varying conditions. We investigated the role of vision-language models in addressing this challenge. We curated a dataset consisting >1000 images across 11 disposal categories for optimal discarding…
Organizátor
NeurIPS 2023
Account · 645 followers
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Domain Constraints Improve Risk Prediction When Outcome Data is Missing
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Max-Sliced Mutual Information
Watch later
Dor Tsur, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
One-Step Diffusion Distillation via Deep Equilibrium Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Deep Generative Models for Molecular Structure Prediction
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Lossy Compression and the Granularity of Causal Representation
Watch later
David Kinney, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
RELIC: Reproducibility and Extension on LIC metric in quantifying bias in captioning models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%