Cooperative Learning with Visual Attributes
Learning paradigms involving varying levels of supervision have received a lot of interest within the computer vision and machine learning communities. The supervisory information is typically considered to come from a human supervisor -- a "teacher" figure. In this paper, we consider an alternate source of supervision -- a "peer" -- i.e. a different machine. We introduce cooperative learning, where two agents trying to learn the same visual concepts, but in potentially different environments using different sources of data (sensors), communicate their current knowledge of these concepts to each other. Given the distinct sources of data in both agents, the mode of communication between the two agents is not obvious. We propose the use of visual attributes -- semantic mid-level visual properties such as furry, wooden, etc.-- as the mode of communication between the agents. Our experiments in three domains -- objects, scenes, and animals -- demonstrate that our proposed cooperative learning approach improves the performance of both agents as compared to their performance if they were to learn in isolation. Our approach is particularly applicable in scenarios where privacy, security and/or bandwidth constraints restrict the amount and type of information the two agents can exchange.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues
In this work, we focus on leveraging facial cues beyond the lip region for robust Audio-Visual Speech Enhancement (AVSE). The facial region, encompassing the lip region, reflects additional speech-related attributes such…
Speech EnhancementEvolving Dyadic Strategies for a Cooperative Physical Task
Many cooperative physical tasks require that individuals play specialized roles (e.g., leader-follower). Humans are adept cooperators, negotiating these roles and transitions between roles innately. Yet how roles are del…
Dual Expert Distillation Network for Generalized Zero-Shot Learning
Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation. Existing studies resort to refining a uniform mapping function to align and correlate the samp…
AttributeGeneralized Zero-Shot LearningZero-Shot LearningLearning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
We introduce the first goal-driven training for visual question answering and dialog agents. Specifically, we pose a cooperative 'image guessing' game between two agents -- Qbot and Abot -- who communicate in natural lan…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+3A case study on context-bound referring expression generation
In recent years, Bayesian models of referring expression generation have gained prominence in order to produce situationally more adequate referring expressions. Basically, these models enable the integration of differen…
Referring ExpressionReferring expression generation