ADVANCED INTERACTION SEARCH
Abstract-
Detecting defects on the wine bottle surface is a challenging task due to these factors: (1) tiny defects on the surface, (2) visually similar defects with design patterns on bottles, (3) reflective (metallic) bottle surface, (4) real-time requirement. In this paper, we propose an efficient and light-weight detector for the defects. To this end, we adopt EfficientNet- B3 [1] as the backbone of the detector and YOLO [2] as the detection head. In addition, we use channel pruning approach [3] to obtain a more compact model. In the experiments, we obtain a score of 0.77 on the validation dataset, similar performance comparing to the two-stage methods[23]. The parameters of our detector are only 5. 8M , which are about one tenth of the YOLOs [2]. The proposed detector achieves a good balance between speed and accuracy.
(highlighting by VitiSynth)
Link to paper-
https://ieeexplore.ieee.org/abstract/document/9305489
https://doi.org/10.1109/ICARCV50220.2020.9305489
Partially indexed reference.
Published: | 2020 |
Publication: | ICARCV 2020 |
Issue: | 2020 2020 |
Author: | Lin M 2020 |
Recommendation: NOT SET |
Date: 19th April 2020
Vine Synth:Growth stage:VS 4 Flowering:VS 4c Bud development:VS 4c.2 Differentiation of main axis of anlage into inflorescence rachis primordium or tendril primordium
The development of inflorescence primordia (IP) is clearly described i...Read more
Date: 16th February 2020
Admin Synth:Guides:Data standards:Colour codes
I think it would be very useful if we have standard colour codes for e...Read more
Date: 29th October 2015
Reference:Journal:Weed Technology:2015:Online October 2015:Devkota P 2015:Influence of Spray Solution Temperature and Holding Duration on Weed Control with Premixed Glyphosate and Dicamba Formulation
Pesticides in general are chemical products, therefore the quality of ...Read more
List of sponsors.. Read more