Sid
@sidgairo18.bsky.social
🏔️📍🇩🇪
🇪🇺 PhD student at the Max Planck Institute for Informatics, and Institute of Science & Technology - Austria.
💻🏃🏻♂️🚴🏻🏋🏻🏊⛷️🎸🎹📚
Webpage: https://sidgairo18.github.io/
🇪🇺 PhD student at the Max Planck Institute for Informatics, and Institute of Science & Technology - Austria.
💻🏃🏻♂️🚴🏻🏋🏻🏊⛷️🎸🎹📚
Webpage: https://sidgairo18.github.io/
Heading to #ICCV2025? Don’t miss #CV4DC — Oct 19, Honolulu 🌺 An in-person workshop spotlighting research for/with developing regions.
See exciting keynote talks from leading researches!
See accepted papers & posters here: cv4dc.github.io/2025/
#AI4Good
See exciting keynote talks from leading researches!
See accepted papers & posters here: cv4dc.github.io/2025/
#AI4Good
October 9, 2025 at 8:58 PM
Heading to #ICCV2025? Don’t miss #CV4DC — Oct 19, Honolulu 🌺 An in-person workshop spotlighting research for/with developing regions.
See exciting keynote talks from leading researches!
See accepted papers & posters here: cv4dc.github.io/2025/
#AI4Good
See exciting keynote talks from leading researches!
See accepted papers & posters here: cv4dc.github.io/2025/
#AI4Good
⏳Still need to wait for your last experiment results?
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
July 24, 2025 at 6:20 AM
⏳Still need to wait for your last experiment results?
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
📣 Proceeding track's results are out.
🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th.
⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th.
⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
July 12, 2025 at 9:11 AM
📣 Proceeding track's results are out.
🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th.
⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th.
⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
Porto, Portugal 🇵🇹 June-July 2025
One of the prettiest and liveliest cities I’ve traveled to ✨ 🚤
One of the prettiest and liveliest cities I’ve traveled to ✨ 🚤
July 2, 2025 at 8:20 AM
Porto, Portugal 🇵🇹 June-July 2025
One of the prettiest and liveliest cities I’ve traveled to ✨ 🚤
One of the prettiest and liveliest cities I’ve traveled to ✨ 🚤
Easy to catch on smaller datasets / experiments (eg CIFAR100). 🚨
June 23, 2025 at 4:27 PM
Easy to catch on smaller datasets / experiments (eg CIFAR100). 🚨
🚨More tiny experiments that seem benign: linear probing on frozen features (but again not explicitly making BatchNorm params to .eval) can have big implications.
Best test accuracy: 71.20% at Epoch 10, for Learning Rate = 0.01 Makes a hell of a lot of difference! Almost 10% 🚨
Best test accuracy: 71.20% at Epoch 10, for Learning Rate = 0.01 Makes a hell of a lot of difference! Almost 10% 🚨
June 23, 2025 at 4:27 PM
🚨More tiny experiments that seem benign: linear probing on frozen features (but again not explicitly making BatchNorm params to .eval) can have big implications.
Best test accuracy: 71.20% at Epoch 10, for Learning Rate = 0.01 Makes a hell of a lot of difference! Almost 10% 🚨
Best test accuracy: 71.20% at Epoch 10, for Learning Rate = 0.01 Makes a hell of a lot of difference! Almost 10% 🚨
Seemingly innocuous error that I see students making time and again: model.eval() or param.eval() for models with norm layers (like batch-norm) is critical. Especially when freezing ❄️ certain layers and training rest.
June 23, 2025 at 2:32 PM
Seemingly innocuous error that I see students making time and again: model.eval() or param.eval() for models with norm layers (like batch-norm) is critical. Especially when freezing ❄️ certain layers and training rest.
Had my older MTB catching dust in the bike room, took 2 hours to replace both tyres and tubes with brand new ones, new brakes, and chain cleaned + greased. 💥
Pretty relaxing and a nice rejuvinating break from research✨
P.S.: Once you are used to driving road bikes, MTBs seem too slow 🤪
Pretty relaxing and a nice rejuvinating break from research✨
P.S.: Once you are used to driving road bikes, MTBs seem too slow 🤪
May 15, 2025 at 9:00 PM
Had my older MTB catching dust in the bike room, took 2 hours to replace both tyres and tubes with brand new ones, new brakes, and chain cleaned + greased. 💥
Pretty relaxing and a nice rejuvinating break from research✨
P.S.: Once you are used to driving road bikes, MTBs seem too slow 🤪
Pretty relaxing and a nice rejuvinating break from research✨
P.S.: Once you are used to driving road bikes, MTBs seem too slow 🤪
Had a great time presenting our work at ICLR 2025 in Singapore 🇸🇬.
Lot of great interactions, meeting amazing people and a very well organised conference 🌟.
It was great to catch up with old colleagues and meet new folks.
For more detail see: arxiv.org/abs/2503.00641
Lot of great interactions, meeting amazing people and a very well organised conference 🌟.
It was great to catch up with old colleagues and meet new folks.
For more detail see: arxiv.org/abs/2503.00641
May 4, 2025 at 9:22 AM
Had a great time presenting our work at ICLR 2025 in Singapore 🇸🇬.
Lot of great interactions, meeting amazing people and a very well organised conference 🌟.
It was great to catch up with old colleagues and meet new folks.
For more detail see: arxiv.org/abs/2503.00641
Lot of great interactions, meeting amazing people and a very well organised conference 🌟.
It was great to catch up with old colleagues and meet new folks.
For more detail see: arxiv.org/abs/2503.00641
🚀 I will be @iclr_conf in Singapore next week presenting our recent work.
We answer how exactly does "What you explain depend on how you train". 🤓
We will be @ Hall 3 + Hall 2B #492 (26th April, 3PM - 5:30 PM)
Please reach out via dm if interestd in a chat or ☕️
#ICLR2025
We answer how exactly does "What you explain depend on how you train". 🤓
We will be @ Hall 3 + Hall 2B #492 (26th April, 3PM - 5:30 PM)
Please reach out via dm if interestd in a chat or ☕️
#ICLR2025
April 16, 2025 at 10:28 AM
🚀 I will be @iclr_conf in Singapore next week presenting our recent work.
We answer how exactly does "What you explain depend on how you train". 🤓
We will be @ Hall 3 + Hall 2B #492 (26th April, 3PM - 5:30 PM)
Please reach out via dm if interestd in a chat or ☕️
#ICLR2025
We answer how exactly does "What you explain depend on how you train". 🤓
We will be @ Hall 3 + Hall 2B #492 (26th April, 3PM - 5:30 PM)
Please reach out via dm if interestd in a chat or ☕️
#ICLR2025
🧑🚒Weekend hack: built a tiny U-Net based diffusion model for image generation (more so for understanding how the heck these things work).
Currently works on MNIST and CIFAR-10. Slowly, will scale the architecture, and training for more complex data.
github.com/sidgairo18/s...
Currently works on MNIST and CIFAR-10. Slowly, will scale the architecture, and training for more complex data.
github.com/sidgairo18/s...
March 30, 2025 at 3:04 PM
🧑🚒Weekend hack: built a tiny U-Net based diffusion model for image generation (more so for understanding how the heck these things work).
Currently works on MNIST and CIFAR-10. Slowly, will scale the architecture, and training for more complex data.
github.com/sidgairo18/s...
Currently works on MNIST and CIFAR-10. Slowly, will scale the architecture, and training for more complex data.
github.com/sidgairo18/s...
The bridge(s) of Saar ✨
March 18, 2025 at 7:34 PM
The bridge(s) of Saar ✨
🚀SmartKC++: Improving Performance of Smartphone-Based Corneal Topographers @ WACV'25
A follow-up to the original SmartKC with improved & robust image processing 💥
With V Ganatra, M Jain, N Kwatra, Dr. K Murali, & others at MSRI + Sankara.
#healthcare #hci #vision
A follow-up to the original SmartKC with improved & robust image processing 💥
With V Ganatra, M Jain, N Kwatra, Dr. K Murali, & others at MSRI + Sankara.
#healthcare #hci #vision
March 18, 2025 at 8:40 AM
🚀SmartKC++: Improving Performance of Smartphone-Based Corneal Topographers @ WACV'25
A follow-up to the original SmartKC with improved & robust image processing 💥
With V Ganatra, M Jain, N Kwatra, Dr. K Murali, & others at MSRI + Sankara.
#healthcare #hci #vision
A follow-up to the original SmartKC with improved & robust image processing 💥
With V Ganatra, M Jain, N Kwatra, Dr. K Murali, & others at MSRI + Sankara.
#healthcare #hci #vision
Saarbrücken riverside 🚴♂️
March 16, 2025 at 6:03 PM
Saarbrücken riverside 🚴♂️
🚀Intriguing Applications and Overlooked Pitfalls of XAI in Visual Models
The slides for a talk I had given at the Group of Machine Learning Research (GMUM) Workshop, Jagiellonian University in October, 2024 are now up. ✨
Slides: sidgairo18.github.io/misc_resourc...
#XAI #ML #CV #research
The slides for a talk I had given at the Group of Machine Learning Research (GMUM) Workshop, Jagiellonian University in October, 2024 are now up. ✨
Slides: sidgairo18.github.io/misc_resourc...
#XAI #ML #CV #research
March 5, 2025 at 9:16 AM
🚀Intriguing Applications and Overlooked Pitfalls of XAI in Visual Models
The slides for a talk I had given at the Group of Machine Learning Research (GMUM) Workshop, Jagiellonian University in October, 2024 are now up. ✨
Slides: sidgairo18.github.io/misc_resourc...
#XAI #ML #CV #research
The slides for a talk I had given at the Group of Machine Learning Research (GMUM) Workshop, Jagiellonian University in October, 2024 are now up. ✨
Slides: sidgairo18.github.io/misc_resourc...
#XAI #ML #CV #research
🚀 As promised, the arXiv manuscript and code, for our ICLR 2025 work - How To Probe: Simple Yet Effective Techniques for Improving Post-Hoc Explanations are now out!
arXiv 📜: arxiv.org/abs/2503.00641
Code 💻: github.com/sidgairo18/h...
#ICLR2025 #arxiv
arXiv 📜: arxiv.org/abs/2503.00641
Code 💻: github.com/sidgairo18/h...
#ICLR2025 #arxiv
March 4, 2025 at 8:53 AM
🚀 As promised, the arXiv manuscript and code, for our ICLR 2025 work - How To Probe: Simple Yet Effective Techniques for Improving Post-Hoc Explanations are now out!
arXiv 📜: arxiv.org/abs/2503.00641
Code 💻: github.com/sidgairo18/h...
#ICLR2025 #arxiv
arXiv 📜: arxiv.org/abs/2503.00641
Code 💻: github.com/sidgairo18/h...
#ICLR2025 #arxiv
Revisiting this 7 years later. 💯- Mark Manson
February 23, 2025 at 1:07 AM
Revisiting this 7 years later. 💯- Mark Manson
Aiming to be more consistent with outdoor running 🏃🏻♂️ and cycling 🚴🏻. I have been weight training consistently for the past 2 years; but a consistent cardio training routine has been lacking.
VO2 Max is currently at 50. Will be tracking and updating here as I make progress.
VO2 Max is currently at 50. Will be tracking and updating here as I make progress.
February 22, 2025 at 11:11 PM
Aiming to be more consistent with outdoor running 🏃🏻♂️ and cycling 🚴🏻. I have been weight training consistently for the past 2 years; but a consistent cardio training routine has been lacking.
VO2 Max is currently at 50. Will be tracking and updating here as I make progress.
VO2 Max is currently at 50. Will be tracking and updating here as I make progress.
New artwork at home 🖼️ ✨ @ Dehradun ❤️
February 21, 2025 at 4:30 PM
New artwork at home 🖼️ ✨ @ Dehradun ❤️
Auf wiedersehen Wien (Vienna) 🇦🇹 👋🏼.
Had a great 6 months at IST-Austria visiting Prof. @locatelf.bsky.social
at the CLAI Group (ista.ac.at/en/research/...).
Now back to Saarbrücken 🇩🇪
Had a great 6 months at IST-Austria visiting Prof. @locatelf.bsky.social
at the CLAI Group (ista.ac.at/en/research/...).
Now back to Saarbrücken 🇩🇪
February 10, 2025 at 5:40 PM
Auf wiedersehen Wien (Vienna) 🇦🇹 👋🏼.
Had a great 6 months at IST-Austria visiting Prof. @locatelf.bsky.social
at the CLAI Group (ista.ac.at/en/research/...).
Now back to Saarbrücken 🇩🇪
Had a great 6 months at IST-Austria visiting Prof. @locatelf.bsky.social
at the CLAI Group (ista.ac.at/en/research/...).
Now back to Saarbrücken 🇩🇪
