Timezone: »
Existing methods for interactive image retrieval have demonstrated the merit of integrating user feedback, improving retrieval results. However, most current systems rely on restricted forms of user feedback, such as binary relevance responses, or feedback based on a fixed set of relative attributes, which limits their impact. In this paper, we introduce a new approach to interactive image search that enables users to provide feedback via natural language, allowing for more natural and effective interaction. We formulate the task of dialog-based interactive image retrieval as a reinforcement learning problem, and reward the dialog system for improving the rank of the target image during each dialog turn. To mitigate the cumbersome and costly process of collecting human-machine conversations as the dialog system learns, we train our system with a user simulator, which is itself trained to describe the differences between target and candidate images. The efficacy of our approach is demonstrated in a footwear retrieval application. Experiments on both simulated and real-world data show that 1) our proposed learning framework achieves better accuracy than other supervised and reinforcement learning baselines and 2) user feedback based on natural language rather than pre-specified attributes leads to more effective retrieval results, and a more natural and expressive communication interface.
Author Information
Xiaoxiao Guo (IBM Research)
Hui Wu (IBM Research)
Yu Cheng (Microsoft AI & Research)
Steven Rennie (Fusemachines)
Gerald Tesauro (IBM TJ Watson Research Center)
Rogerio Feris (IBM Research AI)
More from the Same Authors
-
2020 Poster: AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning »
Ximeng Sun · Rameswar Panda · Rogerio Feris · Kate Saenko -
2020 Poster: Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis »
Gang Wang · Songtao Lu · Georgios Giannakis · Gerald Tesauro · Jian Sun -
2019 Poster: Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries »
Fuwen Tan · Paola Cascante-Bonilla · Xiaoxiao Guo · Hui Wu · Song Feng · Vicente Ordonez -
2018 Poster: Learning Abstract Options »
Matthew Riemer · Miao Liu · Gerald Tesauro -
2018 Poster: Delta-encoder: an effective sample synthesis method for few-shot object recognition »
Eli Schwartz · Leonid Karlinsky · Joseph Shtok · Sivan Harary · Mattias Marder · Abhishek Kumar · Rogerio Feris · Raja Giryes · Alex Bronstein -
2018 Spotlight: Delta-encoder: an effective sample synthesis method for few-shot object recognition »
Eli Schwartz · Leonid Karlinsky · Joseph Shtok · Sivan Harary · Mattias Marder · Abhishek Kumar · Rogerio Feris · Raja Giryes · Alex Bronstein -
2018 Poster: Co-regularized Alignment for Unsupervised Domain Adaptation »
Abhishek Kumar · Prasanna Sattigeri · Kahini Wadhawan · Leonid Karlinsky · Rogerio Feris · Bill Freeman · Gregory Wornell -
2017 Workshop: Conversational AI - today's practice and tomorrow's potential »
Alborz Geramifard · Jason Williams · Larry Heck · Jim Glass · Antoine Bordes · Steve Young · Gerald Tesauro -
2017 Poster: Dilated Recurrent Neural Networks »
Shiyu Chang · Yang Zhang · Wei Han · Mo Yu · Xiaoxiao Guo · Wei Tan · Xiaodong Cui · Michael Witbrock · Mark Hasegawa-Johnson · Thomas Huang -
2007 Spotlight: Managing Power Consumption and Performance of Computing Systems Using Reinforcement Learning »
Gerald Tesauro · Rajarshi Das · Hoi Chan · Jeffrey O Kephart · David Levine · Freeman Rawson · Charles Lefurgy -
2007 Poster: Managing Power Consumption and Performance of Computing Systems Using Reinforcement Learning »
Gerald Tesauro · Rajarshi Das · Hoi Chan · Jeffrey O Kephart · David Levine · Freeman Rawson · Charles Lefurgy