Introduces SmellNet-V synthetic visuo-olfactory dataset and See & Sniff self-supervised framework that learns aligned representations and produces smell saliency maps.
Machine learning for scent: Learning generalizable perceptual representations of small molecules
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Predicting the relationship between a molecule's structure and its odor remains a difficult, decades-old task. This problem, termed quantitative structure-odor relationship (QSOR) modeling, is an important challenge in chemistry, impacting human nutrition, manufacture of synthetic fragrance, the environment, and sensory neuroscience. We propose the use of graph neural networks for QSOR, and show they significantly out-perform prior methods on a novel data set labeled by olfactory experts. Additional analysis shows that the learned embeddings from graph neural networks capture a meaningful odor space representation of the underlying relationship between structure and odor, as demonstrated by strong performance on two challenging transfer learning tasks. Machine learning has already had a large impact on the senses of sight and sound. Based on these early results with graph neural networks for molecular properties, we hope machine learning can eventually do for olfaction what it has already done for vision and hearing.
representative citing papers
SCENT uses VLM-generated scene descriptions as a semantic bridge to align electronic-nose signals with visual and textual embeddings, improving cross-modal smell retrieval and enabling object-context odor disentanglement.
NOSE aligns molecular, receptor, and linguistic modalities in a shared embedding space via tri-modal orthogonal contrastive learning and weak positive samples, achieving SOTA performance and zero-shot generalization on olfactory tasks.
SmellNet supplies 828k gas-sensor time series across 50 substances plus 43 mixtures; ScentFormer reaches 63.3% top-1 accuracy on classification and 50.2% top-1@0.1 on mixture prediction.
SCENT uses multi-modal contrastive learning to align EI-MS spectra with chemical structure embeddings, achieving odor descriptor prediction performance comparable to structure-based models without requiring molecular structure at test time.
citing papers explorer
-
See & Sniff: Learning Visuo-Olfactory Representations
Introduces SmellNet-V synthetic visuo-olfactory dataset and See & Sniff self-supervised framework that learns aligned representations and produces smell saliency maps.
-
What Images Cannot Say: Language-Guided Olfactory Representation Learning
SCENT uses VLM-generated scene descriptions as a semantic bridge to align electronic-nose signals with visual and textual embeddings, improving cross-modal smell retrieval and enabling object-context odor disentanglement.
-
NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning
NOSE aligns molecular, receptor, and linguistic modalities in a shared embedding space via tri-modal orthogonal contrastive learning and weak positive samples, achieving SOTA performance and zero-shot generalization on olfactory tasks.
-
SmellNet: A Large-scale Dataset for Real-world Smell Recognition
SmellNet supplies 828k gas-sensor time series across 50 substances plus 43 mixtures; ScentFormer reaches 63.3% top-1 accuracy on classification and 50.2% top-1@0.1 on mixture prediction.
-
SCENT: Aligning Mass Spectra with Molecular Structure for Olfactory Perception
SCENT uses multi-modal contrastive learning to align EI-MS spectra with chemical structure embeddings, achieving odor descriptor prediction performance comparable to structure-based models without requiring molecular structure at test time.