Feature Correlation Residual Network for Fine-Grained Image Recognition
نویسندگان
چکیده
منابع مشابه
PatchIt: Self-Supervised Network Weight Initialization for Fine-grained Recognition
ConvNet training is highly sensitive to initialization of the weights. A widespread approach is to initialize the network with weights trained for a different task, an auxiliary task. The ImageNet-based ILSVRC classification task is a very popular choice for this, as it has shown to produce powerful feature representations applicable to a wide variety of tasks. However, this creates a significa...
متن کاملFine-Grained Entity Recognition
Entity Recognition (ER) is a key component of relation extraction systems and many other natural-language processing applications. Unfortunately, most ER systems are restricted to produce labels from to a small set of entity classes, e.g., person, organization, location or miscellaneous. In order to intelligently understand text and extract a wide range of information, it is useful to more prec...
متن کاملFine-grained Recognition Datasets for Biodiversity Analysis
In the following paper, we present and discuss challenging applications for fine-grained visual classification (FGVC): biodiversity and species analysis. We not only give details about two challenging new datasets suitable for computer vision research with up to 675 highly similar classes, but also present first results with localized features using convolutional neural networks (CNN). We concl...
متن کاملBilinear CNNs for Fine-grained Visual Recognition
We present a simple and effective architecture for fine-grained visual recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs belong to the class of orderless texture representations but unlike prior w...
متن کاملFine-Grained and Layered Object Recognition
This paper presents a novel research on promoting the performance and enriching the functionalities of object recognition. Instead of simply ̄tting various data to a few prede ̄ned semantic object categories, we propose to generate proper results for di®erent object instances based on their actual visual appearances. The results can be ̄ne-grained and layered categorization along with absolute or ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2020
ISSN: 2169-3536
DOI: 10.1109/access.2020.3040857