Abstract | ||
---|---|---|
Here we study the low-resolution visual recognition problem. Conventional methods are usually trained on images with large ROIs (regions of interest), while the regions and insider images are often small and blur in real-world applications. Therefore, deep neural networks learned on high-resolution images cannot be directly used for recognizing low-resolution objects. To overcome this challenging problem, we propose to use the teacher-student learning paradigm for distilling useful feature information from a pre-trained deep model on high-resolution visual data. In practice, a distillation loss is used to seek the perceptual consistency of low-resolution images and high-resolution images. By simultaneously optimizing the recognition loss and distillation loss, we formulate a novel low-resolution recognition approach. Experiments conducted on benchmarks demonstrate that the proposed method is capable to learn well-performed models for recognizing low-resolution objects, which is superior to the state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/icassp.2019.8682926 | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Low-Resolution Recognition, Deep Convolutional Networks, Teacher-Student Paradigm | Data modeling,Pattern recognition,Computer science,Visualization,Feature extraction,Distillation,Visual recognition,Artificial intelligence,Perception,Image resolution,Deep neural networks | Conference |
ISSN | Citations | PageRank |
1520-6149 | 1 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mingjian Zhu | 1 | 15 | 0.89 |
Kai Han | 2 | 55 | 11.16 |
Chao Zhang | 3 | 939 | 103.66 |
Jinlong Lin | 4 | 22 | 6.11 |
Yunhe Wang | 5 | 113 | 22.76 |