Feature Learning for Image Classification Via Multiobjective Genetic Programming

By Ling Shao, Li Liu, Xuelong Li. IEEE Transactions on Neural Networks and Learning Systems, 2014

297 citations recorded by the source corpus.

Feature extraction is the first and most critical step in image classification. Most existing image classification methods use hand-crafted features, which are not adaptive for different image domains. In this paper, we develop an evolutionary learning methodology to automatically generate domain-adaptive global feature descriptors for image classification using multiobjective genetic programming (MOGP). In our architecture, a set of primitive 2-D operators are randomly combined to construct feature descriptors through the MOGP evolving and then evaluated by two objective fitness criteria, i.e., the classification error and the tree complexity. After the entire evolution procedure finishes, the best-so-far solution selected by the MOGP is regarded as the (near-)optimal feature descriptor obtained. To evaluate its performance, the proposed approach is systematically tested on the Caltech-101, the MIT urban and nature scene, the CMU PIE, and Jochen Triesch Static Hand Posture II data sets, respectively. Experimental results verify that our method significantly outperforms many state-of-the-art hand-designed features and two feature learning techniques in terms of classification accuracy.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/8185be0689442db83813b49e215bf30870017459

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ming Zong
2. Qi Wang
3. Yuan Yuan
4. Jianzhe Lin
5. Ling Shao
6. Shichao Zhang
7. Xuelong Li
8. Xiaofeng Zhu

In Computational Theory and Mathematics

1. Yuan Yuan
2. Qi Wang
3. Jianzhe Lin
4. Ling Shao
5. Shichao Zhang
6. Jiaming Mai
7. Qingsong Zhu
8. Xuelong Li

Citations in the corpus

• A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior (2015, background): “Therefore, improving the technique of image haze removal will benefit many image understanding and computer vision applications such as aerial imagery [1], image classification [2]–[5], image/video retrieval [6]–[8], remote sensing [9]–[11] and video analysis and recognition [12]–[14].”
• Convolutional Neural Networks Based Fire Detection in Surveillance Videos (2018, background): “hand-written digits classification, it has shown promising 163 results for combating different problems including action 164 recognition [20], [21], pose estimation, image classifica165 tion [22]–[26], visual saliency detection, object tracking, 166 image segmentation, scene labeling, object localiz”
• Efficient kNN Classification With Different Numbers of Nearest Neighbors (2018, background): “Equation (3) has been proved to result in sparse W [2], [56] and is also called the least absolute shrinkage and selection operator [9], [53].”
• Cross-Modality Submodular Dictionary Learning for Information Retrieval (2014, background): “While classical approaches [34], [39], [41], [20], [40] , which only utilize a unimodal representation, e.”
• Block-Row Sparse Multiview Multilabel Learning for Image Classification (2016, background): “Literature has shown that conducting image classification with multiview learning can further improve the classification performance [6], [8], [23]–[25].”
• Weakly supervised target detection in remote sensing images based on transferred deep features and negative bootstrapping (2015, unknown): “To address the shortcomings of handcrafted features, some high-level image representations (Shao et al. 2014b; Zhang et al. 2014) and domain-adaptive learning methods (Shao et al. 2014a; Zhu and Shao 2014) have been proposed.”
• Local structure preserving discriminative projections for RGB-D sensor-based scene classification (2015, background): “Feature representation is a hot topic in image classification [37,41,46,55,64].”
• Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking (2016, methodology): “Fortunately, inspired by the success of natural computation [41], the clone selection algorithm [42], [43] is utilized to solve this problem.”