figshare
Browse
thorat-ccn18-poster.pdf (10.38 MB)

The function of cue-driven feature-based feedback in object recognition

Download (10.38 MB)
Version 5 2018-08-31, 13:54
Version 4 2018-08-30, 08:46
Version 3 2018-08-27, 14:40
Version 2 2018-08-27, 14:34
Version 1 2018-08-27, 11:36
journal contribution
posted on 2018-08-31, 13:54 authored by Sushrut ThoratSushrut Thorat, Marius V. Peelen, Marcel A.J. van Gerven

Visual object recognition is not a trivial task, especially when the objects are degraded or surrounded by clutter or presented briefly. External cues (such as verbal cues or visual context) can boost recognition performance in such conditions. In this work, we build an artificial neural network to model the interaction between the object pro- cessing stream (OPS) and the cue. We study the effects of varying neural and representational capacities of the OPS on the performance boost provided by cue-driven feature- based feedback in the OPS. We observe that the feed- back provides performance boosts only if the category- specific features about the objects cannot be fully rep- resented in the OPS. This representational limit is more dependent on task demands than neural capacity. We also observe that the feedback scheme trained to max- imise recognition performance boost is not the same as tuning-based feedback, and actually performs better than tuning-based feedback.

History

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC