BEGIN:VCALENDAR
PRODID:-//AddEvent Inc//AddEvent.com v1.7//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20261101T010000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:Abstract: Vision Transformers (ViTs)\, with their ability to model long-range dependencies through self-attention mechanisms\, have become a standard architecture in computer vision. However\, the interpretability of these models remains a challenge. To address this\, we propose LeGrad\, an explainability method specifically designed for ViTs. LeGrad computes the gradient with respect to the attention maps of ViT layers\, considering the gradient itself as the explainability signal. We aggregate the signal over all layers\, combining the activations of the last as well as intermediate tokens to produce the merged explainability map. This makes LeGrad a conceptually simple and an easy-to-implement tool for enhancing the transparency of ViTs. We evaluate LeGrad in challenging segmentation\, perturbation\, and open-vocabulary settings\, showcasing its versatility compared to other SotA explainability methods demonstrating its superior spatial fidelity and robustness to perturbations. \n\nAbout the speaker: I'm a PhD student at Bonn University\, advised by Prof. Hilde Kuehne. I'm also participating in MIT-IBM Watson Sight and Sound Project.My primary research area is deep learning for multimodal models. Particularly\, I am interested in zero-shot adaptation of pretrained models for emerging behavior.Prior to this\, I finished my Master of Engineering in Applied Mathematics at ENSTA Paris in France and my Master of Science in Statistics and applied Probabilities at the National University of Singapore (NUS).\n\n------\n\nCreate your own Add to Calendar links with addevent.com/r/a \n
X-ALT-DESC;FMTTYPE=text/html:Abstract: Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To address this, we propose LeGrad, an explainability method specifically designed for ViTs. LeGrad computes the gradient with respect to the attention maps of ViT layers, considering the gradient itself as the explainability signal. We aggregate the signal over all layers, combining the activations of the last as well as intermediate tokens to produce the merged explainability map. This makes LeGrad a conceptually simple and an easy-to-implement tool for enhancing the transparency of ViTs. We evaluate LeGrad in challenging segmentation, perturbation, and open-vocabulary settings, showcasing its versatility compared to other SotA explainability methods demonstrating its superior spatial fidelity and robustness to perturbations. <br><br>About the speaker: I'm a PhD student at Bonn University, advised by Prof. Hilde Kuehne. I'm also participating in MIT-IBM Watson Sight and Sound Project.My primary research area is deep learning for multimodal models. Particularly, I am interested in zero-shot adaptation of pretrained models for emerging behavior.Prior to this, I finished my Master of Engineering in Applied Mathematics at ENSTA Paris in France and my Master of Science in Statistics and applied Probabilities at the National University of Singapore (NUS).<br /><br />------<br /><br />Create your own Add to Calendar links with addevent.com/r/a <br>
UID:2de5d371fb204d6c8502b96a2877cc62addeventcom
SUMMARY:[C4AI] Walid Bousselham - LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity (Geo Asia)
DTSTART;TZID=America/Los_Angeles:20240527T110000
DTEND;TZID=America/Los_Angeles:20240527T120000
DTSTAMP:20260816T093305Z
TRANSP:OPAQUE
STATUS:CONFIRMED
SEQUENCE:0
LOCATION:https://meet.google.com/yhv-tiir-ava
X-MICROSOFT-CDO-BUSYSTATUS:BUSY
BEGIN:VALARM
TRIGGER:-PT30M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
END:VEVENT
END:VCALENDAR