[HTML][HTML] A survey on few-shot class-incremental learning
Large deep learning models are impressive, but they struggle when real-time data is not
available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …
available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …
Deep learning for retail product recognition: Challenges and techniques
Taking time to identify expected products and waiting for the checkout in a retail store are
common scenes we all encounter in our daily lives. The realization of automatic product …
common scenes we all encounter in our daily lives. The realization of automatic product …
Fine-grained image analysis with deep learning: A survey
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer
vision and pattern recognition, and underpins a diverse set of real-world applications. The …
vision and pattern recognition, and underpins a diverse set of real-world applications. The …
Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition
Our work focuses on tackling the challenging but natural visual recognition task of long-
tailed data distribution (ie, a few classes occupy most of the data, while most classes have …
tailed data distribution (ie, a few classes occupy most of the data, while most classes have …
Multi-label image recognition with graph convolutional networks
The task of multi-label image recognition is to predict a set of object labels that present in an
image. As objects normally co-occur in an image, it is desirable to model the label …
image. As objects normally co-occur in an image, it is desirable to model the label …
Google landmarks dataset v2-a large-scale benchmark for instance-level recognition and retrieval
While image retrieval and instance recognition techniques are progressing rapidly, there is a
need for challenging datasets to accurately measure their performance--while posing novel …
need for challenging datasets to accurately measure their performance--while posing novel …
Dual attention suppression attack: Generate adversarial camouflage in physical world
Deep learning models are vulnerable to adversarial examples. As a more threatening type
for practical deep learning systems, physical adversarial examples have received extensive …
for practical deep learning systems, physical adversarial examples have received extensive …
Bias-based universal adversarial patch attack for automatic check-out
Adversarial examples are inputs with imperceptible perturbations that easily misleading
deep neural networks (DNNs). Recently, adversarial patch, with noise confined to a small …
deep neural networks (DNNs). Recently, adversarial patch, with noise confined to a small …
Product1m: Towards weakly supervised instance-level product retrieval via cross-modal pretraining
Nowadays, customer's demands for E-commerce are more diversified, which introduces
more complications to the product retrieval industry. Previous methods are either subject to …
more complications to the product retrieval industry. Previous methods are either subject to …
MobileNet-CA-YOLO: An improved YOLOv7 based on the MobileNetV3 and attention mechanism for Rice pests and diseases detection
L Jia, T Wang, Y Chen, Y Zang, X Li, H Shi, L Gao - Agriculture, 2023 - mdpi.com
The efficient identification of rice pests and diseases is crucial for preventing crop damage.
To address the limitations of traditional manual detection methods and machine learning …
To address the limitations of traditional manual detection methods and machine learning …