-
- Shimon Ullman
- Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot 7610001, Israel;
-
- Liav Assif
- Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot 7610001, Israel;
-
- Ethan Fetaya
- Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot 7610001, Israel;
-
- Daniel Harari
- Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot 7610001, Israel;
説明
<jats:title>Significance</jats:title> <jats:p>Discovering the visual features and representations used by the brain to recognize objects is a central problem in the study of vision. Recent successes in computational models of visual recognition naturally raise the question: Do computer systems and the human brain use similar or different computations? We show by combining a novel method (minimal images) and simulations that the human recognition system uses features and learning processes, which are critical for recognition, but are not used by current models. The study uses a “phase transition” phenomenon in minimal images, in which minor changes to the image have a drastic effect on its recognition. The results show fundamental limitations of current approaches and suggest directions to produce more realistic and better-performing models.</jats:p>
収録刊行物
-
- Proceedings of the National Academy of Sciences
-
Proceedings of the National Academy of Sciences 113 (10), 2744-2749, 2016-02-16
Proceedings of the National Academy of Sciences
