"NYCerebro is a CLIP-powered search engine for NYC traffic cameras. It uses AI to find camera views matching your text descriptions."
nycerebro.vercel.app
#solidstatelife #ai #contrastivelearning
nycerebro.vercel.app
#solidstatelife #ai #contrastivelearning
NYCerebro
Search NYC traffic cameras using CLIP
nycerebro.vercel.app
January 30, 2025 at 3:00 AM
"NYCerebro is a CLIP-powered search engine for NYC traffic cameras. It uses AI to find camera views matching your text descriptions."
nycerebro.vercel.app
#solidstatelife #ai #contrastivelearning
nycerebro.vercel.app
#solidstatelife #ai #contrastivelearning
Interested in training hyperspectral image analysis models with reduced annotated data?
Salma explores this question in her recent paper.
doi.org/10.1007/s104...
#hyperspectral #HSI #AI #ML #ContrastiveLearning
#sqIRL #IDLab #UAntwerp #imec
Salma explores this question in her recent paper.
doi.org/10.1007/s104...
#hyperspectral #HSI #AI #ML #ContrastiveLearning
#sqIRL #IDLab #UAntwerp #imec
Enhancing hyperspectral image prediction with contrastive learning in low-label regimes - Applied Intelligence
Labelled data scarcity remains a longstanding challenge in hyperspectral image analysis, primarily due to high spectral dimensionality and the laborious nature of manual annotation. Self-supervised co...
doi.org
February 21, 2026 at 10:41 AM
Interested in training hyperspectral image analysis models with reduced annotated data?
Salma explores this question in her recent paper.
doi.org/10.1007/s104...
#hyperspectral #HSI #AI #ML #ContrastiveLearning
#sqIRL #IDLab #UAntwerp #imec
Salma explores this question in her recent paper.
doi.org/10.1007/s104...
#hyperspectral #HSI #AI #ML #ContrastiveLearning
#sqIRL #IDLab #UAntwerp #imec
An extensive evaluation of single-cell RNA-Seq contrastivelearning generative networks for intrinsic cell-typesdistribution estimation #SingleCell 🧪🧬🖥️
https://www.biorxiv.org/content/10.1101/2025.09.15.675691v1
https://www.biorxiv.org/content/10.1101/2025.09.15.675691v1
September 18, 2025 at 4:00 PM
An extensive evaluation of single-cell RNA-Seq contrastivelearning generative networks for intrinsic cell-typesdistribution estimation #SingleCell 🧪🧬🖥️
https://www.biorxiv.org/content/10.1101/2025.09.15.675691v1
https://www.biorxiv.org/content/10.1101/2025.09.15.675691v1
👉 Let’s talk multimodal learning — come by or check out the paper!
Joint work with an amazing team: @benoit-dufumier.bsky.social, D. Tuia & J-P. Thiran
#ICLR2025 #MultimodalLearning #SelfSupervisedLearning #ContrastiveLearning
Joint work with an amazing team: @benoit-dufumier.bsky.social, D. Tuia & J-P. Thiran
#ICLR2025 #MultimodalLearning #SelfSupervisedLearning #ContrastiveLearning
April 24, 2025 at 4:02 PM
👉 Let’s talk multimodal learning — come by or check out the paper!
Joint work with an amazing team: @benoit-dufumier.bsky.social, D. Tuia & J-P. Thiran
#ICLR2025 #MultimodalLearning #SelfSupervisedLearning #ContrastiveLearning
Joint work with an amazing team: @benoit-dufumier.bsky.social, D. Tuia & J-P. Thiran
#ICLR2025 #MultimodalLearning #SelfSupervisedLearning #ContrastiveLearning
A new semantic retrieval contrastive learning approach claims to boost recommendation accuracy, according to the latest article. Read more: https://getnews.me/semantic-retrieval-contrastive-learning-boosts-recommendations/ #semanticretrieval #contrastivelearning #recommendations
October 8, 2025 at 5:23 PM
A new semantic retrieval contrastive learning approach claims to boost recommendation accuracy, according to the latest article. Read more: https://getnews.me/semantic-retrieval-contrastive-learning-boosts-recommendations/ #semanticretrieval #contrastivelearning #recommendations
A new task-level contrastive method boosts few-shot learning accuracy on the MetaDataset benchmark without adding parameters or extra computation. Read more: https://getnews.me/task-level-contrastiveness-boosts-cross-domain-few-shot-learning/ #fewshotlearning #contrastivelearning #metadataset
October 7, 2025 at 3:43 PM
A new task-level contrastive method boosts few-shot learning accuracy on the MetaDataset benchmark without adding parameters or extra computation. Read more: https://getnews.me/task-level-contrastiveness-boosts-cross-domain-few-shot-learning/ #fewshotlearning #contrastivelearning #metadataset
SRA‑CL mixes large language models with contrastive learning to produce richer embeddings, improving recommendations. Tests on four benchmark datasets show gains. https://getnews.me/semantic-retrieval-contrastive-learning-sra-cl-improves-recommendations/ #semanticretrieval #contrastivelearning
October 1, 2025 at 11:57 AM
SRA‑CL mixes large language models with contrastive learning to produce richer embeddings, improving recommendations. Tests on four benchmark datasets show gains. https://getnews.me/semantic-retrieval-contrastive-learning-sra-cl-improves-recommendations/ #semanticretrieval #contrastivelearning
GenView++ improves MoCo v2 on ImageNet linear classification by +2.5% and raises zero‑shot accuracy by +12.31% over CLIP across ten benchmarks overall. Read more: https://getnews.me/genview-enhances-contrastive-learning-with-adaptive-views/ #genview #contrastivelearning
September 30, 2025 at 2:04 PM
GenView++ improves MoCo v2 on ImageNet linear classification by +2.5% and raises zero‑shot accuracy by +12.31% over CLIP across ten benchmarks overall. Read more: https://getnews.me/genview-enhances-contrastive-learning-with-adaptive-views/ #genview #contrastivelearning
Semivariogram‑based spatial regularization improves GeoCLIP accuracy on the OSV5M street‑view dataset, helping it separate visually similar but distant locations. Read more: https://getnews.me/spatially-regularized-contrastive-learning-improves-geo-localization/ #geolocalization #contrastivelearning
September 29, 2025 at 6:36 AM
Semivariogram‑based spatial regularization improves GeoCLIP accuracy on the OSV5M street‑view dataset, helping it separate visually similar but distant locations. Read more: https://getnews.me/spatially-regularized-contrastive-learning-improves-geo-localization/ #geolocalization #contrastivelearning
Diffusion‑Augmented Contrastive Learning (DACL) achieved an AUROC of 0.7815 on the PhysioNet 2017 ECG benchmark, showing robust biosignal encoding. Read more: https://getnews.me/diffusion-augmented-contrastive-learning-robust-biosignal-encoding/ #biosignals #diffusion #contrastivelearning
September 26, 2025 at 7:23 PM
Diffusion‑Augmented Contrastive Learning (DACL) achieved an AUROC of 0.7815 on the PhysioNet 2017 ECG benchmark, showing robust biosignal encoding. Read more: https://getnews.me/diffusion-augmented-contrastive-learning-robust-biosignal-encoding/ #biosignals #diffusion #contrastivelearning
CoUn uses contrastive learning on retained data to push forgotten samples away in latent space, boosting machine‑unlearning effectiveness without full retraining. Read more: https://getnews.me/contrastive-learning-boosts-machine-unlearning-effectiveness/ #machineunlearning #contrastivelearning #ai
September 24, 2025 at 5:50 AM
CoUn uses contrastive learning on retained data to push forgotten samples away in latent space, boosting machine‑unlearning effectiveness without full retraining. Read more: https://getnews.me/contrastive-learning-boosts-machine-unlearning-effectiveness/ #machineunlearning #contrastivelearning #ai
A contrastive learning model retrieves instrument timbres from isolated or mixed audio, reaching 81.7% top‑1 and 95.7% top‑5 accuracy on three‑instrument queries. Read more: https://getnews.me/contrastive-learning-boosts-instrument-and-synthesizer-retrieval/ #contrastivelearning #timbre
September 18, 2025 at 5:59 PM
A contrastive learning model retrieves instrument timbres from isolated or mixed audio, reaching 81.7% top‑1 and 95.7% top‑5 accuracy on three‑instrument queries. Read more: https://getnews.me/contrastive-learning-boosts-instrument-and-synthesizer-retrieval/ #contrastivelearning #timbre
An extensive evaluation of single-cell RNA-Seq contrastivelearning generative networks for intrinsic cell-typesdistribution estimation https://www.biorxiv.org/content/10.1101/2025.09.15.675691v1
September 18, 2025 at 7:47 AM
An extensive evaluation of single-cell RNA-Seq contrastivelearning generative networks for intrinsic cell-typesdistribution estimation https://www.biorxiv.org/content/10.1101/2025.09.15.675691v1
🆕 SimCLR vs CLIP: Why Contrastive Learning Failed in Prod
#DeepLearning #AI #contrastivelearning #SimCLR
https://tildalice.io/simclr-vs-clip-contrastive-learning-production-tradeoffs/
#DeepLearning #AI #contrastivelearning #SimCLR
https://tildalice.io/simclr-vs-clip-contrastive-learning-production-tradeoffs/
March 8, 2026 at 6:05 PM
🆕 SimCLR vs CLIP: Why Contrastive Learning Failed in Prod
#DeepLearning #AI #contrastivelearning #SimCLR
https://tildalice.io/simclr-vs-clip-contrastive-learning-production-tradeoffs/
#DeepLearning #AI #contrastivelearning #SimCLR
https://tildalice.io/simclr-vs-clip-contrastive-learning-production-tradeoffs/
An extensive evaluation of single-cell RNA-Seq contrastivelearning generative networks for intrinsic cell-typesdistribution estimation https://www.biorxiv.org/content/10.1101/2025.09.15.675691v1
September 18, 2025 at 7:47 AM
An extensive evaluation of single-cell RNA-Seq contrastivelearning generative networks for intrinsic cell-typesdistribution estimation https://www.biorxiv.org/content/10.1101/2025.09.15.675691v1