It is official now: BCN.ai is born. Long life to #BCNai !

Our upcoming #ICML2019 paper "Unsupervised Label Noise Modeling and Loss Correction" is now on arXiv arxiv.org/abs/1904.11238. New SoTA in CIFAR10/100 under high-levels of noise using Beta mixtures to model & correct losses. Code: git.io/fjsvE Prof. Noel O'Connor (he/him) Kevin McGuinness

If you are attending #ICML2019 and are interested in learning in the presence of label noise, come see our poster on "Unsupervised Label Noise Modeling and Loss Correction" arxiv.org/abs/1904.11238 this evening from 6:30pm. Prof. Noel O'Connor (he/him) Eric Arazo Insight Research Ireland Centre

We are happy to present our paper "Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning" at #IJCNN202 at #WCCI2020 WCCI20. Come along (or e-mail us) if you want to know about some of the challenges of SSL (this evening from 8pm). Code: git.io/fjQsC

🔊New paper out! "Unsupervised Contrastive Learning of Sound Event Representations". Work done with Diego Ortego We learn audio representations by contrasting differently augmented views of sound events. paper: arxiv.org/abs/2011.07616 code (soon): github.com/edufonseca/ucl… (1/5)

Interested in training DNNs with noisy labels? Check out our new work on Multi-Objective Interpolation Training to deal with synthetic and web noise. Eric Arazo Paul Albert Prof. Noel O'Connor (he/him) Kevin McGuinness Insight Research Ireland Centre Paper: arxiv.org/abs/2012.04462 Code: git.io/JI40X

Happy to announce that our paper "Towards Robust Learning with Different Label Noise Distributions" has been accepted as an oral presentation at icpr2020milan. Eric Arazo Prof. Noel O'Connor (he/him) Kevin McGuinness Insight Research Ireland Centre Paper: arxiv.org/abs/1912.08741 Code: git.io/JJ0PV

Insight researcher Diego Ortego will be presenting "Towards Robust Learning with Different Label Noise Distributions" Jan. 12th, T1.2 at icpr2020milan Eric Arazo Prof. Noel O'Connor (he/him) Kevin McGuinness Insight Research Ireland Centre #ICPR2020 #AI Paper: arxiv.org/abs/1912.08741 git.io/JJ0PV

Diego Ortego "Objective Interpolation Training for Robustness to Label Noise" accepted #CVPR2021 Synthetic & real-world noise in image classification Eric Arazo Paul Albert Prof. Noel O'Connor (he/him) Kevin McGuinness Dublin City University: lnkd.in/eabGH_y Code: git.io/JI40X #DeepLearning

Excited to present Thursday our #BMVC21 paper on training CNNs under budget constraints. Check it out in the oral session 8 or poster session 4! Great teamwork Diego Ortego Prof. Noel O'Connor (he/him) Kevin McGuinness Insight Research Ireland Centre BMVC:bmvc2021-virtualconference.com/conference/pap… arXiV:arxiv.org/abs/2110.14283

I presented my work on using drones to predict herbage quality at the #AgricultureVision workshop #CVPR2026. A research collab in the VistaMilk Research Ireland Centre SFI centre between Teagasc and Insight Research Ireland Centre funded by @scienceirel. Great to attend in person again ! Paper: shorturl.at/cqzUZGreat

Very glad to announce that our label noise paper was accepted #ECCV2022. We observe a linear separation between OOD and ID samples in web crawled datasets using unsupervised contrastive learning arxiv.org/abs/2207.01573. Team: Eric Arazo Kevin McGuinness Prof. Noel O'Connor (he/him) Insight Research Ireland Centre

Our paper: "Is your noise correction noisy? PLS: Robustness to label noise with two stage detection" was accepted at #WACV2023 ! We detect incorrect true label guesses using our pseudo-loss to combat label noise in image classification datasets arxiv.org/abs/2210.04578

Super delicious diagram. And cool interactive tool too: evogeneao.com/explore/tree-o…