Fast Fine-Grained Image Classification via Weakly Supervised Discriminative Localization

He, Xiangteng; Zhao, Junjie

doi:10.1109/tcsvt.2018.2834480

Cited by 68 publications

(26 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He et al [22] proposed the weakly supervised discriminative localization approach for fast fine-grained image classification. They first applied multi-level attention to guide the discriminative localization learning to localize multiple discriminative regions simultaneously for each image, which only uses image-level subcategory label to avoid using labor-consuming annotations.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based Object Detection Improvement for Fine-Grained Birds

Yang

Song

2021

IEEE Access

View full text Add to dashboard Cite

When the object detection algorithm is applied to the bird protection project, there are many problems like large model parameters, high similarity between bird species and single sample scene. In order to further improve the detection accuracy and stability of the object detection model, a multi-object detection algorithm for fine-grained birds is proposed. Firstly, the algorithm introduces Depthwise separable convolution into the feature extraction layer of YOLOv3 algorithm. The convolution process is divided into two parts: deep convolution and point-by-point convolution. The separation between intra-channel convolution and inter-channel convolution is realized. On the basis of high detection accuracy, the number of algorithm model parameters and calculation amount are greatly reduced. Finally, Focal loss was added to the loss function to solve the serious imbalance of positive and negative samples. By reducing the weight of the large number of simple background classes, the algorithm was more focused on detecting foreground classes. The experimental results show that, in the bird data set, the average precision mean (mAP) index of this algorithm is 2.71% higher than YOLOv3 algorithm, the number of parameters is 79.88% lower than YOLOv3 basic model, and the number of frames per second (FPS) is 19.98% higher than YOLOv3 algorithm. This algorithm not only greatly reduces the number of model parameters and computation, but also improves the detection speed and mAP.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based Object Detection Improvement for Fine-Grained Birds

Yang

Song

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Many other efficient classification methods [ 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 ] have also been proposed. Zhang et al [ 57 ] proposed mapping images into subsemantic space instead of only using visual representations.…”

Section: Related Workmentioning

confidence: 99%

“…Zhang et al [ 57 ] proposed mapping images into subsemantic space instead of only using visual representations. Weak location information was also used [ 60 ] to improve classification performance. Part and pose information were used [ 62 , 63 ].…”

Section: Related Workmentioning

confidence: 99%

Exploring Misclassification Information for Fine-Grained Image Classification

Wang

Zhou

et al. 2021

Sensors

View full text Add to dashboard Cite

Fine-grained image classification is a hot topic that has been widely studied recently. Many fine-grained image classification methods ignore misclassification information, which is important to improve classification accuracy. To make use of misclassification information, in this paper, we propose a novel fine-grained image classification method by exploring the misclassification information (FGMI) of prelearned models. For each class, we harvest the confusion information from several prelearned fine-grained image classification models. For one particular class, we select a number of classes which are likely to be misclassified with this class. The images of selected classes are then used to train classifiers. In this way, we can reduce the influence of irrelevant images to some extent. We use the misclassification information for all the classes by training a number of confusion classifiers. The outputs of these trained classifiers are combined to represent images and produce classifications. To evaluate the effectiveness of the proposed FGMI method, we conduct fine-grained classification experiments on several public image datasets. Experimental results prove the usefulness of the proposed method.

show abstract

“…Results are compared with four typical weakly supervised localization algorithms, that is, WSDL [35], MEAN [36], Unsupervised Object Discovery [37], and SCDA [21]. The accuracy of localization is shown in Table 2.…”

Section: Weakly Supervised Localizationmentioning

confidence: 99%

Bilinear CNN Model for Fine-Grained Classification Based on Subcategory-Similarity Measurement

et al. 2019

View full text Add to dashboard Cite

One of the challenges in fine-grained classification is that subcategories with significant similarity are hard to be distinguished due to the equal treatment of all subcategories in existing algorithms. In order to solve this problem, a fine-grained image classification method by combining a bilinear convolutional neural network (B-CNN) and the measurement of subcategory similarities is proposed. Firstly, an improved weakly supervised localization method is designed to obtain the bounding box of the main object, which allows the model to eliminate the influence of background noise and obtain more accurate features. Then, sample features in the training set are computed by B-CNN so that the fuzzing similarity matrix for measuring interclass similarities can be obtained. To further improve classification accuracy, the loss function is designed by weighting triplet loss and softmax loss. Extensive experiments implemented on two benchmarks datasets, Stanford Cars-196 and Caltech-UCSD Birds-200-2011 (CUB-200-2011), show that the newly proposed method outperforms in accuracy several state-of-the-art weakly supervised classification models.

show abstract

Fast Fine-Grained Image Classification via Weakly Supervised Discriminative Localization

Cited by 68 publications

References 55 publications

Deep Learning-Based Object Detection Improvement for Fine-Grained Birds

Deep Learning-Based Object Detection Improvement for Fine-Grained Birds

Exploring Misclassification Information for Fine-Grained Image Classification

Bilinear CNN Model for Fine-Grained Classification Based on Subcategory-Similarity Measurement

Contact Info

Product

Resources

About