English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Although modern object detection and classification models achieve highaccuracy, these are typically constrained in advance on a fixed train set andare therefore not flexible to deal with novel, unseen object categories.Moreover, these models most often operate on a single frame, which may yieldincorrect classifications in case of ambiguous viewpoints. In this paper, wepropose an active inference agent that actively gathers evidence for objectclassifications, and can learn novel object categories over time. Drawinginspiration from the human brain, we build object-centric generative modelscomposed of two information streams, a what- and a where-stream. Thewhat-stream predicts whether the observed object belongs to a specificcategory, while the where-stream is responsible for representing the object inits internal 3D reference frame. We show that our agent (i) is able to learnrepresentations for many object categories in an unsupervised way, (ii)achieves state-of-the-art classification accuracies, actively resolvingambiguity when required and (iii) identifies novel object categories.Furthermore, we validate our system in an end-to-end fashion where the agent isable to search for an object at a given pose from a pixel-based rendering. Webelieve that this is a first step towards building modular, intelligent systemsthat can be used for a wide range of tasks involving three dimensional objects.

Disentangling What and Where for 3D Object-Centric Representations Through Active Inference