Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition

• Published in: IEEE transactions on image processing Vol. 26; no. 4; pp. 2028 - 2041
• Main Authors: Wang, Zhe, Wang, Limin, Wang, Yali, Zhang, Bowen, Qiao, Yu
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Coding; Customization; Dictionaries; Feature extraction; Feature recognition; Image coding; Image recognition; Image representation; Neural networks; Object recognition; Patches (structures); PatchNet; Representations; scene recognition; semantic codebook; Semantics; Training; Visualization; VSAD

Traditional feature encoding scheme (e.g., Fisher vector) with local descriptors (e.g., SIFT) and recent convolutional neural networks (CNNs) are two classes of successful methods for image recognition. In this paper, we propose a hybrid representation, which leverages the discriminative capacity of...