基于跨領(lǐng)域卷積稀疏自動(dòng)編碼器的抽象圖像情緒性分類
doi: 10.11999/JEIT160241 cstr: 32379.14.JEIT160241
-
1.
(西北工業(yè)大學(xué)電子信息學(xué)院 西安 710072) ②(鄭州輕工業(yè)學(xué)院計(jì)算機(jī)與通信工程學(xué)院 鄭州 450002)
陜西省科技統(tǒng)籌創(chuàng)新工程重點(diǎn)實(shí)驗(yàn)室項(xiàng)目(2013 SZS15-K02)
Affective Abstract Image Classification Based on Convolutional Sparse Autoencoders across Different Domains
-
1.
(School of Electronics and Information, Northwestern Polytechnical University, Xi&rsquo
The Science and Technology Innovation Engineering Program for Shaanxi Key Laboratories (2013SZS15-K02)
-
摘要: 為了將無監(jiān)督特征學(xué)習(xí)應(yīng)用于小樣本量的圖像情緒語義分析,該文采用一種基于卷積稀疏自動(dòng)編碼器進(jìn)行自學(xué)習(xí)的領(lǐng)域適應(yīng)方法對(duì)少量有標(biāo)記抽象圖像進(jìn)行情緒性分類。并且提出了一種采用平均梯度準(zhǔn)則對(duì)自動(dòng)編碼器所學(xué)權(quán)重進(jìn)行排序的方法,用于對(duì)基于不同領(lǐng)域的特征學(xué)習(xí)結(jié)果進(jìn)行直觀比較。首先在源領(lǐng)域中的大量無標(biāo)記圖像上隨機(jī)采集圖像子塊并利用稀疏自動(dòng)編碼器學(xué)習(xí)局部特征,然后將對(duì)應(yīng)不同特征的權(quán)重矩陣按照每個(gè)矩陣在3個(gè)色彩通道上的平均梯度中的最小值進(jìn)行排序。最后采用包含池化層的卷積神經(jīng)網(wǎng)絡(luò)提取目標(biāo)領(lǐng)域有標(biāo)記圖像樣本的全局特征響應(yīng),并送入邏輯回歸模型進(jìn)行情緒性分類。實(shí)驗(yàn)結(jié)果表明基于自學(xué)習(xí)的領(lǐng)域適應(yīng)可以為無監(jiān)督特征學(xué)習(xí)在有限樣本目標(biāo)領(lǐng)域上的應(yīng)用提供訓(xùn)練數(shù)據(jù),而且采用稀疏自動(dòng)編碼器的跨領(lǐng)域特征學(xué)習(xí)能在有限數(shù)量抽象圖像情緒語義分析中獲得比底層視覺特征更優(yōu)秀的辨識(shí)效果。
-
關(guān)鍵詞:
- 圖像分類 /
- 圖像情緒 /
- 自學(xué)習(xí) /
- 卷積自動(dòng)編碼器 /
- 領(lǐng)域適應(yīng)
Abstract: To apply unsupervised feature learning to emotional semantic analysis for images in small sample size situations, convolutional sparse autoencoder based self-taught learning for domain adaption is adopted for affective classification of a small amount of labeled abstract images. To visually compare the results of feature learning on different domains, an average gradient criterion based method is further proposed for the sorting of weights learned by sparse autoencoders. Image patches are first randomly collected from a large number of unlabeled images in the source domain and local features are learned using a sparse autoencoder. Then the weight matrices corresponding to different features are sorted according to the minimal average gradient of each matrix in three color channels. Global feature activations of labeled images in the target domain are finally obtained by a convolutional neural network including a pooling layer and sent into a logistic regression model for affective classification. Experimental results show that self-taught learning based domain adaption can provide training data for the application of unsupervised feature learning in target domains with limited samples. Sparse autoencoder based feature learning across different domains can produce better identification effect than low-level visual features in emotional semantic analysis of a limited number of abstract images.-
Key words:
- Image classification /
- Image affect /
- Self-taught learning /
- Convolutional autoencoder /
- Domain adaption
-
BORTH D, JI R, CHEN T, et al. Large-scale visual sentiment ontology and detectors using adjective noun pairs[C]. 21st ACM International Conference on Multimedia, Barcelona, Spain, 2013: 223-232. doi: 10.1145/2502081.2502282. 李祖賀, 樊養(yǎng)余. 基于視覺的情感分析研究綜述[J]. 計(jì)算機(jī)應(yīng)用研究, 2015, 32(12): 3521-3526. doi: 10.3969/j.issn.1001- 3695.2015.12.001. LI Zuhe and FAN Yangyu. Survey on visual sentiment analysis[J]. Application Research of Computers, 2015, 32(12): 3521-3526. doi: 10.3969/j.issn.1001-3695.2015.12.001. MACHAJDIK J and HANBURY A. Affective image classification using features inspired by psychology and art theory[C]. 18th ACM International Conference on Multimedia, Firenze, Italy, 2010: 83-92. doi: 10.1145/ 1873951.1873965. ZHANG H, G?NEN M, YANG Z, et al. Understanding emotional impact of images using Bayesian multiple kernel learning[J]. Neurocomputing, 2015, 165: 3-13. doi: 10.1016/ j.neucom.2014.10.093. ZHAO S, GAO Y, JIANG X, et al. Exploring principles-of-art features for image emotion recognition[C]. 22nd ACM International Conference on Multimedia, Orlando, FL, USA, 2014: 47-56. doi: 10.1145/2647868.2654930. ZHANG H, YANG Z, G?NEN M, et al. Affective abstract image classification and retrieval using multiple kernel learning[C]. 20th International Conference on Neural Information Processing, Daegu, South Korea, 2013: 166-175. doi: 10.1007/978-3-642-42051-1_22. ZHANG H, AUGILIUS E, HONKELA T, et al. Analyzing emotional semantics of abstract art using low-level image features[C]. 10th International Symposium on Intelligent Data Analysis, Porto, Portugal, 2011: 413-423. doi: 10.1007/ 978-3-642-24800-9_38. LECUN Y, BENGIO Y, and HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. doi: 10.1038/nature14539. 李寰宇, 畢篤彥, 查宇飛, 等. 一種易于初始化的類卷積神經(jīng)網(wǎng)絡(luò)視覺跟蹤算法[J]. 電子與信息學(xué)報(bào), 2016, 38(1): 1-7. doi: 10.11999/JEIT150600. LI Huanyu, BI Duyan, ZHA Yufei, et al. An easily initialized visual tracking algorithm based on similar structure for convolutional neural network[J]. Journal of Electronics Information Technology, 2016, 38(1): 1-7. doi: 10.11999/ JEIT150600. YOU Q, LUO J, JIN H, et al. Robust image sentiment analysis using progressively trained and domain transferred deep networks[C]. 29th AAAI Conference on Artificial Intelligence (AAAI), Austin, TX, USA, 2015: 381-388. 李祖賀, 樊養(yǎng)余, 王鳳琴. YUV空間中基于稀疏自動(dòng)編碼器的無監(jiān)督特征學(xué)習(xí)[J]. 電子與信息學(xué)報(bào), 2016, 38(1): 29-37. doi: 10.11999/JEIT150557. LI Zuhe, FAN Yangyu, and WANG Fengqin. Unsupervised feature learning with sparse autoencoders in YUV space[J]. Journal of Electronics Information Technology, 2016, 38(1): 29-37. doi: 10.11999/JEIT150557. ZHANG F, DU B, and ZHANG L. Saliency-guided unsupervised feature learning for scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(4): 2175-2184. doi: 10.1109/TGRS.2014.2357078. 楊興明, 吳克偉, 孫永宣, 等. 可遷移測(cè)度準(zhǔn)則下的協(xié)變量偏移修正多源集成方法[J]. 電子與信息學(xué)報(bào), 2015, 37(12): 2913-2920. doi: 10.11999/JEIT150323. YANG Xingming, WU Kewei, SUN Yongxuan, et al. Modified covariate-shift multi-source ensemble method in transferability metric[J]. Journal of Electronics Information Technology, 2015, 37(12): 2913-2920. doi: 10.11999/JEIT150323. 莊福振, 羅平, 何清, 等. 遷移學(xué)習(xí)研究進(jìn)展[J]. 軟件學(xué)報(bào), 2015, 26(1): 26-39. doi: 10.13328/j.cnki.jos.004631. ZHUANG Fuzhen, LUO Ping, HE Qing, et al. Survey on transfer learning research[J]. Journal of Software, 2015, 26(1): 26-39. doi: 10.13328/j.cnki.jos.004631. DENG J, ZHANG Z, EYBEN F, et al. Autoencoder-based unsupervised domain adaptation for speech emotion recognition[J]. IEEE Signal Processing Letters, 2014, 21(9): 1068-1072. doi: 10.1109/LSP.2014.2324759. YANG X, ZHANG T, and XU C. Cross-domain feature learning in multimedia [J]. IEEE Transactions on Multimedia, 2015, 17(1): 64-78. doi: 10.1109/TMM.2014.2375793. ZHOU J T, PAN S J, TSANG I W, et al. Hybrid heterogeneous transfer learning through deep learning[C]. 28th AAAI Conference on Artificial Intelligence (AAAI), Quebec City, QC, Canada, 2014: 2213-2219. KOUNO K, SHINNOU H, SASAKI M, et al. Unsupervised domain adaptation for word sense disambiguation using stacked denoising autoencoder[C]. 29th Pacific Asia Conference on Language, Information and Computation (PACLIC 29), Shanghai, China, 2015: 224-231. COATES A, LEE H, and NG A Y. An analysis of single-layer networks in unsupervised feature learning[C]. 14th International Conference on Artificial Intelligence and Statistics, Ft. Lauderdale, FL, USA, 2011: 215-223. WANG R, DU L, YU Z, et al. Infrared and visible images fusion using compressed sensing based on average gradient[C]. 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), San Jose, CA, USA, 2013: 1-4. doi: 10.1109/ICMEW.2013.6618257. L?NGKVIST M and LOUTFI A. Learning feature representations with a cost-relevant sparse autoencoder[J]. International Journal of Neural Systems, 2015, 25(1): 1-11. doi: 10.1142/S0129065714500348. LI Z, FAN Y, and LIU W. The effect of whitening transformation on pooling operations in convolutional autoencoders[J]. EURASIP Journal on Advances in Signal Processing, 2015, 2015(1): 1-11. doi: 10.1186/s13634-015- 0222-1. VEDALDI A and LENC K. MatConvNet: convolutional neural networks for matlab[C]. 23rd ACM International Conference on Multimedia, Brisbane, Australia, 2015: 689-692. doi: 10.1145/2733373.2807412. -
計(jì)量
- 文章訪問數(shù): 1561
- HTML全文瀏覽量: 218
- PDF下載量: 453
- 被引次數(shù): 0