Events Calendar

03 Dec
Cathedral
Event Type

Lectures, Symposia, Etc., Virtual

Topic

Research, Technology

Target Audience

Undergraduate Students, Staff, Faculty, Graduate Students

Website

https://pitt.co1.qualtrics.com/jfe/fo...

Department
Intelligent Systems Program
Hashtag

#isp

Subscribe
Google Calendar iCal Outlook

ISP AI Forum: Improving Object Recognition with Explicit Shape Representations

This is a past event.

Speaker: Harsh Sinha, ISP PhD candidate

Title: Improving Object Recognition with Explicit Shape Representations

Abstract: Convolutional Neural Networks (CNNs) have emerged as the most powerful techniques for object recognition. The success of CNNs is often attributed to the simple and generic formulation of CNNs which holds the potential to learn from vast amounts of data. The impressive success of CNNs shadows the fact, that CNNs are prone to failure in various ways. CNNs belong to a class of learning algorithms which implicitly assume that, it is possible to predict well on distributions, by training on a particular data distribution. This naive assumption of generalization has failed in various real-world scenarios. This talk addresses the emerging challenges due to distribution-shift in training and test data, by seeking to extract an invariant across several dataset distributions, in hope that such invariances also hold in all novel test scenarios.

Recent studies have shown that CNNs fail to generalize to unseen domains, due to their strong inductive bias towards global image texture. Motivated by findings in cognitive psychology, the talk will investigate if explicit shape-bias can serve as an invariant to alleviate vulnerabilities in CNNs, leading to better object recognition. We advocate that inclusion of a simple shape structure can make the network robust against unseen image manipulations. As the project progresses, newer algorithms may emerge, creating the need for a flexible neural architecture that is able to rapidly integrate newer variances in data distribution and even unseen classes.

RSVP: https://pitt.co1.qualtrics.com/jfe/form/SV_79DkEFNGTq1myjk

Friday, December 3 at 1:00 p.m. to 1:30 p.m.

Virtual Event

ISP AI Forum: Improving Object Recognition with Explicit Shape Representations

Speaker: Harsh Sinha, ISP PhD candidate

Title: Improving Object Recognition with Explicit Shape Representations

Abstract: Convolutional Neural Networks (CNNs) have emerged as the most powerful techniques for object recognition. The success of CNNs is often attributed to the simple and generic formulation of CNNs which holds the potential to learn from vast amounts of data. The impressive success of CNNs shadows the fact, that CNNs are prone to failure in various ways. CNNs belong to a class of learning algorithms which implicitly assume that, it is possible to predict well on distributions, by training on a particular data distribution. This naive assumption of generalization has failed in various real-world scenarios. This talk addresses the emerging challenges due to distribution-shift in training and test data, by seeking to extract an invariant across several dataset distributions, in hope that such invariances also hold in all novel test scenarios.

Recent studies have shown that CNNs fail to generalize to unseen domains, due to their strong inductive bias towards global image texture. Motivated by findings in cognitive psychology, the talk will investigate if explicit shape-bias can serve as an invariant to alleviate vulnerabilities in CNNs, leading to better object recognition. We advocate that inclusion of a simple shape structure can make the network robust against unseen image manipulations. As the project progresses, newer algorithms may emerge, creating the need for a flexible neural architecture that is able to rapidly integrate newer variances in data distribution and even unseen classes.

RSVP: https://pitt.co1.qualtrics.com/jfe/form/SV_79DkEFNGTq1myjk

Friday, December 3 at 1:00 p.m. to 1:30 p.m.

Virtual Event

Hashtag

#isp

Powered by the Localist Community Events Calendar ©