Explainable Deep Classification Models for Domain Generalization

no code implementations • 13 Mar 2020 • Andrea Zunino, Sarah Adel Bargal, Riccardo Volpi, Mehrnoosh Sameki, Jianming Zhang, Stan Sclaroff, Vittorio Murino, Kate Saenko

Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision.

Classification Domain Generalization +1

BUOCA: Budget-Optimized Crowd Worker Allocation

no code implementations • 11 Jan 2019 • Mehrnoosh Sameki, Sha Lai, Kate K. Mays, Lei Guo, Prakash Ishwar, Margrit Betke

We next train a machine learning system (BUOCA-ML) that predicts an optimal number of crowd workers needed to maximize the accuracy of the labeling.

Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)

no code implementations • 30 Apr 2017 • Danna Gurari, Kun He, Bo Xiong, Jianming Zhang, Mehrnoosh Sameki, Suyog Dutt Jain, Stan Sclaroff, Margrit Betke, Kristen Grauman

We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems.

Object Semantic Segmentation +1

Dynamic Allocation of Crowd Contributions for Sentiment Analysis during the 2016 U.S. Presidential Election

no code implementations • 31 Aug 2016 • Mehrnoosh Sameki, Mattia Gentil, Kate K. Mays, Lei Guo, Margrit Betke

We explore two dynamic-allocation methods: (1) The number of workers queried to label a tweet is computed offline based on the predicted difficulty of discerning the sentiment of a particular tweet.

Sentiment Analysis

Salient Object Subitizing

no code implementations • CVPR 2015 • Jianming Zhang, Shugao Ma, Mehrnoosh Sameki, Stan Sclaroff, Margrit Betke, Zhe Lin, Xiaohui Shen, Brian Price, Radomir Mech

We study the problem of Salient Object Subitizing, i. e. predicting the existence and the number of salient objects in an image using holistic cues.

Image Retrieval Object +4