Deep Relative Distance Learning: Tell the Difference between Similar Vehicles

By Hongye Liu, Yonghong Tian, Yaowei Wang, Lu Pang, Tiejun Huang. 2016

738 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Recent advances in convolutional neural networks (2015, methodology): “Triplet loss and its variants have been widely used in various tasks, including re-identification [71], verification [70], and image retrieval [72].”
DeepStore: In-Storage Acceleration for Intelligent Queries (2019, background): “We believe these identified intelligent query applications show the generality of emerging intelligent query systems [23, 30, 43, 46, 51, 57, 69, 83, 84, 102].”
CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification (2019, methodology): “There have also been some works on providing datasets for vehicle-based ReID [29, 27, 55].”
TransReID: Transformer-based Object Re-Identification (2021, methodology): “We evaluate our proposed method on four person ReID datasets, Market-1501 [45], DukeMTMC-reID [29], MSMT17 [38], Occluded-Duke [26], and two vehicle ReID datasets, VeRi-776 [21] and VehicleID [20].”
Perceptual Generative Adversarial Networks for Small Object Detection (2017, methodology): “For traffic sign detection, we use the pretrained VGGCNN-M-1024 model [3] as adopted in [24] to initialize our network.”
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-”
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID (2020, neutral): “We conduct experiments with the real-world VeRi776, VehicleID and the synthetic VehicleX datasets.”
FastReID: A Pytorch Toolbox for General Instance Re-identification (2020, neutral): “Methods Small Medium Large R-1 R-5 R-1 R-5 R-1 R-5 DRDL [57] 48.”
Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-Temporal Path Proposals (2017, background): “Vehicle recognition is an active research field in computer vision, which includes applications such as vehicle classification [42, 35, 26], vehicle detection [31], and vehicle segmentation [30].”
The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification (2020, methodology): “Through extensive experimentation in section 4, we show the effectiveness of our approach on multiple challenging vehicle re-id benchmarks [43, 22, 9, 27, 24], obtaining state-of-the-art results.”
Learning an Evolutionary Embedding via Massive Knowledge Distillation (2020, methodology): “Second, we compare the proposed EEL with other well-known deep embedding learning methods such as Con-trastive (Sun et al. 2014), N-pair (Sohn 2016), Triplet (Schroff et al. 2015), Center loss (Wen et al. 2016), LM-softmax (Liu et al. 2016) and A-softmax (Liu et al. 2017), respectively, in Table 3.”
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review (2017, neutral): “In addition to the successes discussed in section 3.3, some of the other successful applications that incorporated CNNs for their image classification component prior to the resurgence of neural networks in 2006 include medical image segmentation (Ning et al., 2005); facial recognition, detection, a”
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].”
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels (2022, methodology): “We evaluate our method on four person re-identification datasets, including MSMT17 (Wei et al. 2018), Market-1501 (Zheng et al. 2015), DukeMTMC-reID (Ristani et al. 2016), Occluded-Duke (Miao et al. 2019), and two vehicle ReID datasets, VeRi-776 (Liu et al. 2016b) and VehicleID (Liu et al. 2016a).”
VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild (2019, methodology): “Comparison among the samples of VehicleID [9], VeRI776 [10] and VERI-Wild datasets.”
Large-Scale Metric Learning: A Voyage From Shallow to Deep (2018, result): “This is in line with other deep metric learning models [21], [24].”
Hard-Aware Deeply Cascaded Embedding (2016, methodology): “• VehicleID dataset [17] is a large-scale vehicle dataset that contains 221,763 images of 26,267 vehicles, where the training set contains 110,178 images of 13,134 vehicles and the testing set contains 111,585 images of 13,133 vehicles.”
Triplet-Center Loss for Multi-view 3D Object Retrieval (2018, background): “Several variants of triplet loss have also been proposed, such as [19, 23, 37].”
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification (2021, methodology): “We conducted the experiments on two widely used vehicle datasets including Veri-776 [30] and VehicleID [29].”