AlignedReID++: Dynamically matching local information for person re-identification

Luo, Hao; Jiang, Wei; Zhang, Xuan; Fan, Xing; Qian, Jin; Zhang, Chi

doi:10.1016/j.patcog.2019.05.028

Cited by 200 publications

(76 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The contribution of the existing methods mainly vary depending on the problematic part they propose to solve. For example, [18] focus on addressing misalignment in person bounding boxes. In [2] multi-scale feature learning is adapted to include information about the small details at representation level.…”

Section: Deep Learning For Person Re-identificationmentioning

confidence: 99%

End-to-end training of CNN ensembles for person re-identification

Serbetci

Akgül

2020

Pattern Recognition

View full text Add to dashboard Cite

We propose an end-to-end ensemble method for person re-identification (ReID) to address the problem of overfitting in discriminative models. These models are known to converge easily, but they are biased to the training data in general and may produce a high model variance, which is known as overfitting. The ReID task is more prone to this problem due to the large discrepancy between training and test distributions. To address this problem, our proposed ensemble learning framework produces several diverse and accurate base learners in a single DenseNet. Since most of the costly dense blocks are shared, our method is computationally efficient, which makes it favorable compared to the conventional ensemble models. Experiments on several benchmark datasets demonstrate that our method achieves state-of-the-art results. Noticeable performance improvements, especially on relatively small datasets, indicate that the proposed method deals with the overfitting problem effectively.

show abstract

Section: Deep Learning For Person Re-identificationmentioning

confidence: 99%

End-to-end training of CNN ensembles for person re-identification

Serbetci

Akgül

2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…The performance of our proposed person Re-ID method is compared with the state-of-the-art methods on both Market-1501 and DukeMTMC-reID datasets. The employed comparison methods include AlignedReID [45], IDE (ID-discriminative embedding) [39], SVDNet (singular vector decomposition net) [46], TriNet (triplet net) [30], Pyramid [47], AWTL (adaptive weighted triplet loss) [48], ABD-Net (Attentive but Diverse Net) [49], DSA-reID (Densely Semantically Aligned reID) [50], the baseline method in [51], and the baseline method together with triplet loss [51].…”

Section: A Person Re-id Performancementioning

confidence: 99%

Person Re-Identification Using Additive Distance Constraint With Similar Labels Loss

Lei

Tang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Despite the promising progress made in recent years, person re-identification (Re-ID) remains a challenging task due to the intra-class variations. Most of the current studies used the traditional Softmax loss for solutions, but its discriminative capability encounters a bottleneck. Therefore, how to improve person Re-ID performance is still a challenging task. To address this problem, we proposed a novel loss function, namely additive distance constraint with similar labels loss (ADCSLL). Specifically, we reformulated the Softmax loss by adding a distance constraint to the ground truth label, based on which similar labels were introduced to enhance the learned features to be much more stable and centralized. Experimental evaluations were conducted on two popular datasets (Market-1501 and DukeMTMC-reID) to examine the effectiveness of our proposed method. The results showed that our proposed ADCSLL was more discriminative than most of the other compared state-of-the-art methods. The rank-1 accuracy and the mAP on Market-1501 were 95.0% and 87.0%, respectively. The numbers were 88.6% and 77.2% on DukeMTMC-reID, respectively.

show abstract

“…For instance, GoogleNet can provide the base knowledge for a multilevel triplet deep learning model to compute multilevel features efficiently for person re-identification tasks [13]. Similarly, models which use global features can benefit from the transferred knowledge for mapping local features to person reidentification tasks [14]. While fine-tuning works well on new tasks, it suffers forgetting problem on old tasks due to the absence of updating the weights for the original datasets.…”

Section: Related Workmentioning

confidence: 99%

Continuous Learning without Forgetting for Person Re-Identification

Sugianto

Tjondronegoro

Sorwar

et al. 2019

2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

Deep learning-based person re-identification faces a scalability challenge when the target domain requires continuous learning. Service environments, such as airports, need to recognize new visitors and add new cameras over time. Training-at-once is not enough to make the model robust to new tasks and domain variations. A well-known approach is fine-tuning, which suffers forgetting problem on old tasks when learning new tasks. Joint-training can alleviate the problem but requires old datasets, which is unobtainable in some cases. Recently, Learning without forgetting (LwF) shows its ability to mitigate the problem without old datasets. This paper extends the benefit of LwF from image classification to person re-identification with further challenges. Comprehensive experiments are based on Market1501 and DukeMTMC4ReID to evaluate and benchmark LwF to other approaches. The results confirm that LwF outperforms fine-tuning in preserving old knowledge and joint-training in faster training.

show abstract

AlignedReID++: Dynamically matching local information for person re-identification

Cited by 200 publications

References 9 publications

End-to-end training of CNN ensembles for person re-identification

End-to-end training of CNN ensembles for person re-identification

Person Re-Identification Using Additive Distance Constraint With Similar Labels Loss

Continuous Learning without Forgetting for Person Re-Identification

Contact Info

Product

Resources

About