3D Object Representations for Fine-Grained Categorization

Krause, Jonathan; Stark, Michael; Deng, Jia; Li, Feifei

doi:10.1109/iccvw.2013.77

Cited by 2,358 publications

(1,587 citation statements)

References 32 publications

Supporting

Mentioning

1,560

Contrasting

Unclassified

Order By: Relevance

“…We propose a more general 3D modeling approach for fine-grained classification based on the Active Shape Model (ASM) formulation, which is more flexible and effective than using a large set of classifiers [14] (…”

Section: Related Workmentioning

confidence: 99%

“…However, a rough ellipsoid might not be suitable for other categories (e.g., car). The most related work to ours is [14], which lifts 2D-based features into 3D space to better associate features across different viewpoints. However, they use a massive bank of classifiers (i.e., example-based) to match 3D models to 2D images, which is time consuming and not applicable to different object shapes.…”

Section: Related Workmentioning

confidence: 99%

“…Additionally, the predicted class label provides a better class-specific shape prior, which improves model fitting by alleviating the local minima problem for non-linear objective functions. Instead of using a rough 3D ellipsoid [8] or a massive bank of classifiers [14], we adopt a more general and flexible 3D modeling approach, which is based on a highly detailed and deformable 3D model constructed by Principal Components Analysis (PCA) on a set of 3D CAD models.…”

Section: A) Input Image (B) Part Locations (C) Regression Model (Dmentioning

confidence: 99%

“…Recently, researchers [8,14] have used 3D models for fine-grained classification. While these methods have shown some success in tackling viewpoint variations within the objects, their non-deformable 3D model representations limit the ability of these approaches to adjust to different shapes of objects.…”

Section: Introductionmentioning

confidence: 99%

“…Fine-grained recognition methods have been proposed to address different types of super-ordinate categories (e.g., birds [10,5,6,8], dogs [18] or cars [23,14]), and many of these methods focus on finding distinctive 2D parts for distinguishing different classes [6,27,5,2] or seeking better pose-invariant feature representations [29]. Recently, researchers [8,14] have used 3D models for fine-grained classification.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Jointly Optimizing 3D Model Fitting and Fine-Grained Classification

Lin

Morariu

Hsu

et al. 2014

Computer Vision – ECCV 2014

100

View full text Add to dashboard Cite

Abstract. 3D object modeling and fine-grained classification are often treated as separate tasks. We propose to optimize 3D model fitting and fine-grained classification jointly. Detailed 3D object representations encode more information (e.g., precise part locations and viewpoint) than traditional 2D-based approaches, and can therefore improve fine-grained classification performance. Meanwhile, the predicted class label can also improve 3D model fitting accuracy, e.g., by providing more detailed classspecific shape models. We evaluate our method on a new fine-grained 3D car dataset (FG3DCar), demonstrating our method outperforms several state-of-the-art approaches. Furthermore, we also conduct a series of analyses to explore the dependence between fine-grained classification performance and 3D models.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: A) Input Image (B) Part Locations (C) Regression Model (Dmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Jointly Optimizing 3D Model Fitting and Fine-Grained Classification

Lin

Morariu

Hsu

et al. 2014

Computer Vision – ECCV 2014

100

View full text Add to dashboard Cite

show abstract

Multilayer feature descriptors fusion CNN models for fine‐grained visual recognition

Hou

Luo

Zhao

et al. 2019

Computer Animation & Virtual

View full text Add to dashboard Cite

Fine‐grained image classification is a challenging topic in the field of computer vision. General models based on first‐order local features cannot achieve acceptable performance because the features are not so efficient in capturing fine‐grained difference. A bilinear convolutional neural network (CNN) model exhibits that a second‐order statistical feature is more efficient in capturing fine‐grained difference than a first‐order local feature. However, this framework only considers the extraction of a second‐order feature descriptor, using a single convolutional layer. The potential effective classification features of other convolutional layers are ignored, resulting in loss of recognition accuracy. In this paper, a multilayer feature descriptors fusion CNN model is proposed. It fully considers the second‐order feature descriptors and the first‐order local feature descriptor generated by different layers. Experimental verification was carried out on fine‐grained classification benchmark data sets, CUB‐200‐2011, Stanford Cars, and FGVC‐aircraft. Compared with the bilinear CNN model, the proposed method has improved accuracy by 0.8%, 1.1%, and 5.5%. Compared with the compact bilinear pooling model, there is an accuracy increase of 0.64%, 1.63%, and 1.45%, respectively. In addition, the proposed model effectively uses multiple 1×1 convolution kernels to reduce dimension. The experimental results show that the multilayer low‐dimensional second‐order feature descriptors fusion model has comparable recognition accuracy of the original model.

show abstract

Semantic interaction learning for fine‐grained vehicle recognition

Zhang

Lei

Yang

et al. 2021

Computer Animation & Virtual

View full text Add to dashboard Cite

Fine‐grained vehicle recognition is a challenging problem due to high inter‐class confusion among vehicle models under the influence of pose and viewpoint. To effectively describe the discriminative characteristics, many approaches try to learn detailed information from an individual image. Inspired by Siamese network that addresses the case where two inputs are relatively similar, the semantic interaction learning network (SIL‐Net) is designed to discover semantic differences between two fine‐grained categories via pairwise comparison. Specifically, SIL‐Net first collecting contrastive information by learning the mutual feature of input image pair, and then compare it with individual features to generate corresponding semantic features. These features learn semantic differences from contextual comparison, this gives SIL‐Net the ability to distinguish between two confusing images via pairwise interaction. After training, SIL‐Net can adaptively learn feature priorities under the supervision of the margin ranking loss and converge quickly. SIL‐Net performs well on two public vehicle benchmarks (Stanford Cars and CompCars), showing the suitability of SIL‐Net to fine‐grained vehicle recognition.

show abstract

3D Object Representations for Fine-Grained Categorization

Cited by 2,358 publications

References 32 publications

Jointly Optimizing 3D Model Fitting and Fine-Grained Classification

Jointly Optimizing 3D Model Fitting and Fine-Grained Classification

Multilayer feature descriptors fusion CNN models for fine‐grained visual recognition

Semantic interaction learning for fine‐grained vehicle recognition

Contact Info

Product

Resources

About