paper-with-me

Papers

Where to Look Next: Unsupervised Active Visual Exploration on 360° Input

2019-09-23 · Soroush Seifi, Tinne Tuytelaars

We address the problem of active visual exploration of large 360{\deg} inputs. In our setting an active agent with a limited camera bandwidth explores its 360{\deg} environment by changing its viewing direction at limited discrete time steps. As such, it observes the world as a sequence of narrow field-of-view 'glimpses', deciding for itself where to look next. Our proposed method exceeds previous works' performance by a significant margin without the need for deep reinforcement learning or training separate networks as sidekicks. A key component of our system are the spatial memory maps that make the system aware of the glimpses' orientations (locations in the 360{\deg} image). Further, we stress the advantages of retina-like glimpses when the agent's sensor bandwidth and time-steps are limited. Finally, we use our trained model to do classification of the whole scene using only the information observed in the glimpses.

📄 PDF Abstract BibTeX arXiv:1909.10304

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle

2019-09-16 · IJCNLP 2019 11 · Peter West, Ari Holtzman, Jan Buys, Yejin Choi

The principle of the Information Bottleneck (Tishby et al. 1999) is to produce a summary of information X optimized to predict some other relevant information Y. In this paper, we propose a novel approach to unsupervised…

Abstractive Text SummarizationExtractive SummarizationLanguage ModelingLanguage Modelling+4

Learning to predict where to look in interactive environments using deep recurrent q-learning

2016-12-17 · Sajad Mousavi, Michael Schukat, Enda Howley, Ali Borji 외

Bottom-Up (BU) saliency models do not perform well in complex interactive environments where humans are actively engaged in tasks (e.g., sandwich making and playing the video games). In this paper, we leverage Reinforcem…

Atari GamesQ-Learningreinforcement-learningReinforcement Learning+1

Picking groups instead of samples: A close look at Static Pool-based Meta-Active Learning

2019-11-01 · Ignasi Mas, Josep Ramon Morros, Veronica Vilaplana

Active Learning techniques are used to tackle learning problems where obtaining training labels is costly. In this work we use Meta-Active Learning to learn to select a subset of samples from a pool of unsupervised input…

Active Learning

Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models

2026-04-09 · Marcel Gröpl, Jaewoo Jung, Seungryong Kim, Marc Pollefeys 외 arxiv

Despite rapid progress, pretrained vision-language models still struggle when answers depend on tiny visual details or on combining clues spread across multiple regions, as in documents and compositional queries. We addr…

Ecological Sampling of Gaze Shifts

2013-04-16 · IEEE Transactions on Cybernetics 2013 4 · Giuseppe Boccignone, Mario Ferraro

Visual attention guides our gaze to relevant parts of the viewed scene, yet the moment-to-moment relocation of gaze can be different among observers even though the same locations are taken into account. Surprisingly, th…

Gaze EstimationGaze Prediction