The functional role of cue-driven feature-based feedback in object recognition
This work addresses the problem of understanding feedback mechanisms in visual recognition for neuroscience and AI, but it is incremental as it builds on existing models.
The study investigated how cue-driven feedback improves object recognition in degraded conditions using a neural network model, finding that feedback boosts performance only when the object processing stream cannot fully represent category-specific features, with task demands being more critical than neural capacity.
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 processing 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 feedback provides performance boosts only if the category-specific features about the objects cannot be fully represented in the OPS. This representational limit is more dependent on task demands than neural capacity. We also observe that the feedback scheme trained to maximise recognition performance boost is not the same as tuning-based feedback, and actually performs better than tuning-based feedback.