ترغب بنشر مسار تعليمي؟ اضغط هنا

Rethinking Classification Loss Designs for Person Re-identification with a Unified View

178   0   0.0 ( 0 )
 نشر من قبل Zhizheng Zhang
 تاريخ النشر 2020
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Person Re-identification (ReID) aims at matching a person of interest across images. In convolutional neural networks (CNNs) based approaches, loss design plays a role of metric learning which guides the feature learning process to pull closer features of the same identity and to push far apart features of different identities. In recent years, the combination of classification loss and triplet loss achieves superior performance and is predominant in ReID. In this paper, we rethink these loss functions within a generalized formulation and argue that triplet-based optimization can be viewed as a two-class subsampling classification, which performs classification over two sampled categories based on instance similarities. Furthermore, we present a case study which demonstrates that increasing the number of simultaneously considered instance classes significantly improves the ReID performance, since it is aligned better with the ReID test/inference process. With the multi-class subsampling classification incorporated, we provide a strong baseline which achieves the state-of-the-art performance on the benchmark person ReID datasets. Finally, we propose a new meta prototypical N-tuple loss for more efficient multi-class subsampling classification. We aim to inspire more new loss designs in the person ReID field.



قيم البحث

اقرأ أيضاً

Unsupervised person re-identification (re-ID) remains a challenging task. While extensive research has focused on the framework design or loss function, we show in this paper that sampling strategy plays an equally important role. We analyze the reas ons for differences in performance between various sampling strategies under the same framework and loss function. We suggest that deteriorated over-fitting is an important factor causing poor performance, and enhancing statistical stability can rectify this issue. Inspired by that, a simple yet effective approach is proposed, known as group sampling, which gathers groups of samples from the same class into a mini-batch. The model is thereby trained using normalized group samples, which helps to alleviate the effects associated with a single sample. Group sampling updates the pipeline of pseudo label generation by guaranteeing that samples are more efficiently divided into the correct classes. Group sampling regulates the representation learning process, which enhances statistical stability for feature representation in a progressive fashion. Qualitative and quantitative experiments on Market-1501, DukeMTMC-reID, and MSMT17 show that group sampling improves upon state-of-the-art methods by between 3.3%~6.1%. Code has been available at https://github.com/ucas-vg/GroupSampling.
Although great progress in supervised person re-identification (Re-ID) has been made recently, due to the viewpoint variation of a person, Re-ID remains a massive visual challenge. Most existing viewpoint-based person Re-ID methods project images fro m each viewpoint into separated and unrelated sub-feature spaces. They only model the identity-level distribution inside an individual viewpoint but ignore the underlying relationship between different viewpoints. To address this problem, we propose a novel approach, called textit{Viewpoint-Aware Loss with Angular Regularization }(textbf{VA-reID}). Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level. In addition, rather than modeling different viewpoints as hard labels used for conventional viewpoint classification, we introduce viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation. VALSR can effectively solve the ambiguity of the viewpoint cluster label assignment. Extensive experiments on the Market1501 and DukeMTMC-reID datasets demonstrated that our method outperforms the state-of-the-art supervised Re-ID methods.
Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss. The triplet loss used in video re-ID is usually based on so-called clip features, each aggregated from a few fram e features. In this paper, we propose to model the video clip as a set and instead study the distance between sets in the corresponding triplet loss. In contrast to the distance between clip representations, the distance between clip sets considers the pair-wise similarity of each element (i.e., frame representation) between two sets. This allows the network to directly optimize the feature representation at a frame level. Apart from the commonly-used set distance metrics (e.g., ordinary distance and Hausdorff distance), we further propose a hybrid distance metric, tailored for the set-aware triplet loss. Also, we propose a hard positive set construction strategy using the learned class prototypes in a batch. Our proposed method achieves state-of-the-art results across several standard benchmarks, demonstrating the advantages of the proposed method.
Person re-identification (ReID) is an important task in wide area video surveillance which focuses on identifying people across different cameras. Recently, deep learning networks with a triplet loss become a common framework for person ReID. However , the triplet loss pays main attentions on obtaining correct orders on the training set. It still suffers from a weaker generalization capability from the training set to the testing set, thus resulting in inferior performance. In this paper, we design a quadruplet loss, which can lead to the model output with a larger inter-class variation and a smaller intra-class variation compared to the triplet loss. As a result, our model has a better generalization ability and can achieve a higher performance on the testing set. In particular, a quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID. In extensive experiments, the proposed network outperforms most of the state-of-the-art algorithms on representative datasets which clearly demonstrates the effectiveness of our proposed method.
In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning. The person re-identification subfield is n o exception to this. Unfortunately, a prevailing belief in the community seems to be that the triplet loss is inferior to using surrogate losses (classification, verification) followed by a separate metric learning step. We show that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا