Global-Mapping-Consistency-Constrained Visual-Semantic Embedding for Interpreting Autonomous Perception Models
From the perspective of artificial intelligence evaluation, the need to discover and explain the potential shortness of the evaluated intelligent algorithms/systems as well as the need to evaluate the intelligence level of such testees are of equal importance. In this paper, we propose a possible so...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10570287/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590307919659008 |
|---|---|
| author | Chi Zhang Meng Yuan Xiaoning Ma Ping Wei Yuanqi Su Li Li Yuehu Liu |
| author_facet | Chi Zhang Meng Yuan Xiaoning Ma Ping Wei Yuanqi Su Li Li Yuehu Liu |
| author_sort | Chi Zhang |
| collection | DOAJ |
| description | From the perspective of artificial intelligence evaluation, the need to discover and explain the potential shortness of the evaluated intelligent algorithms/systems as well as the need to evaluate the intelligence level of such testees are of equal importance. In this paper, we propose a possible solution to these challenges: Explainable Evaluation for visual intelligence. Specifically, we focus on the problem setting where the internal mechanisms of AI algorithms are sophisticated, heterogeneous or unreachable. In this case, a latent attribute dictionary learning method with constrained by mapping consistency is proposed to explain the performance variation patterns of visual perception intelligence under different test samples. By jointly iteratively solving the learning of latent concept representation for test samples and the regression of latent concept-generalization performance, the mapping relationship between deep representation, semantic attribute annotation, and generalization performance of test samples is established to predict the degree of influence of semantic attributes on visual perception generalization performance. The optimal solution of proposed method could be reached via an alternating optimization process. Through quantitative experiments, we find that global mapping consistency constraints can make the learned latent concept representation strictly consistent with deep representation, thereby improving the accuracy of semantic attribute-perception performance correlation calculation. |
| format | Article |
| id | doaj-art-148ea933199a41a9970d4e1bb09f28f0 |
| institution | Kabale University |
| issn | 2687-7813 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj-art-148ea933199a41a9970d4e1bb09f28f02025-01-24T00:02:39ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132024-01-01539340810.1109/OJITS.2024.341855210570287Global-Mapping-Consistency-Constrained Visual-Semantic Embedding for Interpreting Autonomous Perception ModelsChi Zhang0https://orcid.org/0000-0001-9604-2800Meng Yuan1https://orcid.org/0009-0004-7348-033XXiaoning Ma2https://orcid.org/0009-0000-1238-4206Ping Wei3https://orcid.org/0000-0002-8535-9527Yuanqi Su4Li Li5https://orcid.org/0000-0002-9428-1960Yuehu Liu6National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, ChinaNational Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, ChinaSchool of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, ChinaNational Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, ChinaSchool of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, ChinaDepartment of Automation, BNRist, Tsinghua University, Beijing, ChinaNational Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, ChinaFrom the perspective of artificial intelligence evaluation, the need to discover and explain the potential shortness of the evaluated intelligent algorithms/systems as well as the need to evaluate the intelligence level of such testees are of equal importance. In this paper, we propose a possible solution to these challenges: Explainable Evaluation for visual intelligence. Specifically, we focus on the problem setting where the internal mechanisms of AI algorithms are sophisticated, heterogeneous or unreachable. In this case, a latent attribute dictionary learning method with constrained by mapping consistency is proposed to explain the performance variation patterns of visual perception intelligence under different test samples. By jointly iteratively solving the learning of latent concept representation for test samples and the regression of latent concept-generalization performance, the mapping relationship between deep representation, semantic attribute annotation, and generalization performance of test samples is established to predict the degree of influence of semantic attributes on visual perception generalization performance. The optimal solution of proposed method could be reached via an alternating optimization process. Through quantitative experiments, we find that global mapping consistency constraints can make the learned latent concept representation strictly consistent with deep representation, thereby improving the accuracy of semantic attribute-perception performance correlation calculation.https://ieeexplore.ieee.org/document/10570287/Explainable AI evaluationdictionary learninglatent knowledge representation |
| spellingShingle | Chi Zhang Meng Yuan Xiaoning Ma Ping Wei Yuanqi Su Li Li Yuehu Liu Global-Mapping-Consistency-Constrained Visual-Semantic Embedding for Interpreting Autonomous Perception Models IEEE Open Journal of Intelligent Transportation Systems Explainable AI evaluation dictionary learning latent knowledge representation |
| title | Global-Mapping-Consistency-Constrained Visual-Semantic Embedding for Interpreting Autonomous Perception Models |
| title_full | Global-Mapping-Consistency-Constrained Visual-Semantic Embedding for Interpreting Autonomous Perception Models |
| title_fullStr | Global-Mapping-Consistency-Constrained Visual-Semantic Embedding for Interpreting Autonomous Perception Models |
| title_full_unstemmed | Global-Mapping-Consistency-Constrained Visual-Semantic Embedding for Interpreting Autonomous Perception Models |
| title_short | Global-Mapping-Consistency-Constrained Visual-Semantic Embedding for Interpreting Autonomous Perception Models |
| title_sort | global mapping consistency constrained visual semantic embedding for interpreting autonomous perception models |
| topic | Explainable AI evaluation dictionary learning latent knowledge representation |
| url | https://ieeexplore.ieee.org/document/10570287/ |
| work_keys_str_mv | AT chizhang globalmappingconsistencyconstrainedvisualsemanticembeddingforinterpretingautonomousperceptionmodels AT mengyuan globalmappingconsistencyconstrainedvisualsemanticembeddingforinterpretingautonomousperceptionmodels AT xiaoningma globalmappingconsistencyconstrainedvisualsemanticembeddingforinterpretingautonomousperceptionmodels AT pingwei globalmappingconsistencyconstrainedvisualsemanticembeddingforinterpretingautonomousperceptionmodels AT yuanqisu globalmappingconsistencyconstrainedvisualsemanticembeddingforinterpretingautonomousperceptionmodels AT lili globalmappingconsistencyconstrainedvisualsemanticembeddingforinterpretingautonomousperceptionmodels AT yuehuliu globalmappingconsistencyconstrainedvisualsemanticembeddingforinterpretingautonomousperceptionmodels |