A large-scale car dataset for fine-grained categorization and verification

By Linjie Yang, Ping Luo, Chen Change Loy, Xiaoou Tang. 2015

874 citations recorded by the source corpus.

This paper aims to highlight vision related tasks centered around “car”, which has been largely neglected by vision community in comparison to other objects. We show that there are still many interesting car-related problems and applications, which are not yet well explored and researched. To facilitate future car-related research, in this paper we present our on-going effort in collecting a large-scale dataset, “CompCars”, that covers not only different car views, but also their different internal and external parts, and rich attributes. Importantly, the dataset is constructed with a cross-modality nature, containing a surveillance-nature set and a web-nature set. We further demonstrate a few important applications exploiting the dataset, namely car model classification, car model verification, and attribute prediction. We also discuss specific challenges of the car-related problems and other potential applications that worth further investigations. The latest dataset can be downloaded at http://mmlab.ie.cuhk.edu.hk/ datasets/comp_cars/index.html.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Recent advances in convolutional neural networks (2015, background): “There are already some finegrained image datasets (such as Flower [98], Birds [99], [100], Dogs [101], Cars [102] and Shoes [103]).”
Improvements to Context Based Self-Supervised Learning (2017, methodology): “For validation, we use a combination of CUB birds [45] (a fine-grained bird species dataset) and CompCars [46] (a fine-grained car model dataset).”
The iNaturalist Challenge 2017 Dataset (2017, background): “The vision community has released many fine-grained datasets covering several domains such as birds [42, 40, 2, 38, 16], dogs [14, 28, 22], airplanes [23, 39], flowers [26], leaves [18], trees [41] and cars [17, 20, 46, 6].”
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning (2018, background): “Examples include recognizing natural categories such as species of birds [58, 54], dogs [28] and plants [39, 59]; or man-made categories such as car make & model [32, 63].”
Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition (2016, background): “Others have explored directions such as utilizing hierarchical label structures [57], combining visual and textual information [54, 2, 16], 3D-assisted recognition [26, 31, 37], introducing humans in the loop [40, 4, 7], and collecting larger amount of data [45, 47, 25, 17].”
Attribute-Aware Attention Model for Fine-grained Representation Learning (2018, methodology): “We conduct experiments on two benchmark fine-grained classification dataset, namely, CUB-200-2011 [37] and CompCars [44].”
Adaptation Across Extreme Variations using Unlabeled Domain Bridges (2019, methodology): “For the recognition task, we use the Comprehensive Cars (CompCars) [55] dataset to recognize car models in the surveillance domain at night time using labeled images from the web domain.”
Lifelong Generative Modelling Using Dynamic Expansion Graph Model (2021, background): “…Chen, and Hsu 2014), 3D-Chair (Aubry et al. 2014), Ommiglot (Lake, Salakhutdinov, and Tenenbaum 2015), ImageNet* (Krizhevsky, Sutskever, and Hinton 2012), Car (Yang et al. 2015), Zappos (Yu and Grauman 2017), CUB (Wah et al. 2010) (detailed dataset setting is provided in Appendix-L.1 from SM1).”
HoloGAN: Unsupervised Learning of 3D Representations From Natural Images (2019, methodology): “Data We train HoloGAN using a variety of datasets: Basel Face [42], CelebA [35], Cats [63], Chairs [7], Cars [58], and LSUN bedroom [59].”
PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance (2018, methodology): “Furthermore, existing datasets, such as CompCars [2] and VehicleID [16], only provide the appearance labels such as types and models, ne-”
Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding (2018, background): “More recently, there also released some datasets that involved categories of multiple levels, like CompCars [45], Boxcars [36], Cars-333 [44] with three-level car categories of make, model, and year, and VegFru [14] with 25 upper-level categories and 292 subordinate classes of vegetables and fruits.”
Diversified Visual Attention Networks for Fine-Grained Object Classification (2016, background): “, various species of birds [1], dogs [2], [3] and different classes of cars [4], [5].”
A High Resolution Optical Satellite Image Dataset for Ship Recognition and Some New Baselines (2017, background): “In fact, sub-class recognition is not uncommon in natural image domain (Yang et al., 2015).”
Vision-based vehicle detection and counting system using deep learning in highway scenes (2019, methodology): “The Comprehensive Cars Dataset [34] is similar to the Stanford Car Dataset but contains many pictures.”
Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification (2017, methodology): “Datasets used for training the proposed model, including (a) VeRi-776 [9], (b) VehicleID [8], (c) BoxCars21k [17],and (d) CompCars [23].”
The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification (2020, methodology): “With recent breakthroughs due to deep learning, we can easily learn discriminative embeddings for vehicles by feeding images from large-scale vehicle datasets, such as VehicleID, VeRi, VERI-Wild, Vehicle-1M, PKU VD1&VD2 [43], CompCars [44], and CityFlow [40], to train a DCNN that is later used as th”
Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification (2018, background): “recognize subordinate categories of some base categories, such as different models of cars [7, 8], species of birds [9], variants of aircraft [10], kinds of foods [11], etc.”