VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization

Hou, Saihui; Feng, Yushan; Wang, Zhong Lin

doi:10.1109/iccv.2017.66

Cited by 111 publications

(70 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the vehicle datasets used in experiments have two-level hierarchical labels, we use our RNN-HA with t = 2 for the vehicle re-identification problem. Beyond that, the proposed RNN-HA model can also deal with the hierarchical fine-grained recognition problem, e.g., [9], which reveals the generalization usage of our model.…”

Section: Crucial Modules In Rnn-hamentioning

confidence: 87%

Coarse-to-Fine: A RNN-Based Hierarchical Attention Model for Vehicle Re-identification

Wei¹,

Zhang

Liu

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Xiu-Shen Wei 1[0000−0002−8200−1845] , Chen-Lin Zhang 2[0000−0002−3168−1852] , Lingqiao Liu 3[0000−0003−3584−795X] , Chunhua Shen 3[0000−0002−8648−8718] , and Jianxin Wu 2[0000−0002−2085−7568]Abstract Vehicle re-identification is an important problem and becomes desirable with the rapid expansion of applications in video surveillance and intelligent transportation. By recalling the identification process of human vision, we are aware that there exists a native hierarchical dependency when humans identify different vehicles. Specifically, humans always firstly determine one vehicle's coarse-grained category, i.e., the car model/type. Then, under the branch of the predicted car model/type, they are going to identify specific vehicles by relying on subtle visual cues, e.g., customized paintings and windshield stickers, at the fine-grained level. Inspired by the coarse-to-fine hierarchical process, we propose an end-to-end RNN-based Hierarchical Attention (RNN-HA) classification model for vehicle re-identification. RNN-HA consists of three mutually coupled modules: the first module generates image representations for vehicle images, the second hierarchical module models the aforementioned hierarchical dependent relationship, and the last attention module focuses on capturing the subtle visual information distinguishing specific vehicles from each other. By conducting comprehensive experiments on two vehicle re-identification benchmark datasets VeRi and VehicleID, we demonstrate that the proposed model achieves superior performance over state-of-theart methods. Coarse-to-fineModel level Vehicle level Query … … … … Figure 1: Illustration of coarse-to-fine hierarchical information as a latent but crucial cue for vehicle re-identification. (Best viewed in color and zoomed in.) has diverse applications in video surveillance [30], intelligent transportation [37]and urban computing [40]. Moreover, vehicle re-identification has recently drawn increasing attentions in the computer vision community [19,20,23]. Compared with the classic person re-identification problem, vehicle re-identification could be more challenging as different specific vehicles can only be distinguished by slight and subtle differences, such as some customized paintings, windshield stickers, favorite decorations, etc. Nevertheless, there still conceals some latent but crucial information for handling this problem. As shown in Fig. 1, when humans identify different vehicles, they always follow a coarse-to-fine identification process. Specifically, we tend to firstly determine this specific vehicle belongs to which car model/type. The first step can eliminate many distractors, i.e., vehicles with similar subtle visual appearances but belonging to the other different car models/types. In the following, within the candidate vehicle set of the same car model/type, humans will carefully distinguish different vehicles from each other by using these subtle visual cues. Apparently, there is a hierarchical dependency in this coarse-to-fine process, which is yet neg...

show abstract

Section: Crucial Modules In Rnn-hamentioning

confidence: 87%

Coarse-to-Fine: A RNN-Based Hierarchical Attention Model for Vehicle Re-identification

Wei¹,

Zhang

Liu

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…We construct a new large-scale butter y (Butter y-200) dataset with four-level categories and organize the 200 bird species of the Caltech-UCSD Birds (CUB) dataset also with four-level categories. We evaluate our proposed framework, the baseline methods and the existing competitors on these two and the VegFru [14] datasets. In this section, we rst introduce these three datasets.…”

Section: Datasetsmentioning

confidence: 99%

“…To our knowledge, these two datasets are the rst that involves in four-level categories in FGIR and they may bene t research on multi-granularity image recognition. 3) We conduct experiments on the two and the VegFru [14] datasets, and demonstrate the e ectiveness of our proposed HSE framework over the baseline and existing state-of-the-art methods. Moreover, we also conduct ablative studies to carefully evaluate and analyze the contribution of each component of the proposed framework.…”

Section: Introductionmentioning

confidence: 99%

“…VegFru [14] is a newly released large-scale dataset for ne-grained vegetables and fruits recognition. It covers two-level categories of 25 upper-level categories and 292 subordinate classes.…”

Section: Vegfru Dataset Introductionmentioning

confidence: 99%

“…The dataset contains 160,731 images in total, including a training set of 29,200 images, a validation set of 14,600 images, and a test set of 116,931 images. Similarly, we follow this standard train/val/test splits as [14] to evaluate our HSE framework and the existing methods for fair comparison.…”

Section: Vegfru Dataset Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding

Chen

Gao

et al. 2018

Proceedings of the 26th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Object categories inherently form a hierarchy with di erent levels of concept abstraction, especially for ne-grained categories. For example, birds (Aves) can be categorized according to a four-level hierarchy of order, family, genus, and species. This hierarchy encodes rich correlations among various categories across di erent levels, which can e ectively regularize the semantic space and thus make prediction less ambiguous. However, previous studies of negrained image recognition primarily focus on categories of one certain level and usually overlook this correlation information. In this work, we investigate simultaneously predicting categories of di erent levels in the hierarchy and integrating this structured correlation information into the deep neural network by developing a novel Hierarchical Semantic Embedding (HSE) framework. Specically, the HSE framework sequentially predicts the category score vector of each level in the hierarchy, from highest to lowest. At each level, it incorporates the predicted score vector of the higher level as prior knowledge to learn ner-grained feature representation. During training, the predicted score vector of the higher level is also employed to regularize label prediction by using it as soft targets of corresponding sub-categories. To evaluate the proposed framework, we organize the 200 bird species of the Caltech-UCSD birds dataset with the four-level category hierarchy and construct a large-scale butter y dataset that also covers four level categories. Extensive experiments on these two and the newly-released VegFru datasets demonstrate the superiority of our HSE framework over the baseline methods and existing competitors.

show abstract

Towards practical robotic chef: Review of relevant work and future challenges

Sochacki,

Zhang,

Abdulali

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

Robotic chefs are a promising technology that can improve the availability of quality food by reducing the time required for cooking, therefore decreasing food's overall cost. This paper clarifies and structures design and benchmarking rules in this new area of research, and provides a comprehensive review of technologies suitable for the construction of cooking robots. The diner is an ultimate judge of the cooking outcome, therefore we put focus on explaining human food preferences and perception of taste and ways to use them for control. Mechanical design of robotic chefs at a practically low cost remains the challenge, but some recently published gripper designs as well as whole robotic systems show the use of cheap materials or off‐the‐shelf components. Moreover, technologies like taste sensing, machine learning, and computer vision are making their way into robotic cooking enabling smart sensing and therefore improving controllability and autonomy. Furthermore, objective assessment of taste and food palatability is a challenge even for trained humans, therefore the paper provides a list of procedures for benchmarking the robot's tasting and cooking abilities. The paper is written from the point of view of a researcher or engineer building a practical robotic system, therefore there is a strong priority for solutions and technologies that are proven, robust and self‐contained enough to be a part of a larger system.

show abstract

VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization

Cited by 111 publications

References 22 publications

Coarse-to-Fine: A RNN-Based Hierarchical Attention Model for Vehicle Re-identification

Coarse-to-Fine: A RNN-Based Hierarchical Attention Model for Vehicle Re-identification

Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding

Towards practical robotic chef: Review of relevant work and future challenges

Contact Info

Product

Resources

About