【VSA】One-shot video-based person re-identification with variance subsampling algorithm

目錄

• 解決了什麼問題
• 主要貢獻和創新點
• 基本框架
• 提出的方法
  • 01 variance confidence方差置信度
  • 02 Variance Subsampling Algorithm 方差二次採樣算法
  • 03 Variance decay strategy 方差衰減策略
• 實驗
  • 01 性能
  • 02 Ablation - sampling criterions

導言
針對現有工做中存在的錯誤僞標籤問題，文章經過優化樣本間的類似性度量和僞標籤置信度評估策略來改善這個問題，從而提供模型性能。具體地，文章提出了方差置信度的概念，並設計了方差二次採樣算法將方差置信度和距離置信度結合起來做爲採樣準則，同時還提出了方差衰減策略來更好了優化選擇出來的僞標籤樣本。最終，該方法將MARS數據集上的mAP和Rank1分別提升了 3.94%和4.55%。

引用

@article{DBLP:journals/jvca/ZhaoYYHYZ20,
author = {Jing Zhao and
Wenjing Yang and
Mingliang Yang and
Wanrong Huang and
Qiong Yang and
Hongguang Zhang},
title = {One-shot video-based person re-identification with variance subsampling
algorithm},
journal = {Comput. Animat. Virtual Worlds},
volume = {31},
number = {4-5},
year = {2020}
}

相關連接

原文連接：https://onlinelibrary.wiley.com/doi/10.1002/cav.1964
或者下方↓公衆號後臺回覆「VSA」，便可得到論文電子資源。

解決了什麼問題

Previous works propose the distance-based sampling for unlabeled datapoints to address the few-shot person re-identification task, however, many selected samples may be assigned with wrong labels due to poor feature quality in these works, which negatively affects the learning procedure.

主要貢獻和創新點

• We propose the variance confidence to measure the credibility of pseudo-labels, which can be widely used as a general similarity measurement.
• We propose a novel VSA（variance subsampling algorithm） to improve the accuracy of pseudo-labels for selected samples. It combines distance confidence and variance confidence as the sampling criterion, and adopt a variance decay strategy as the sampling strategy.

創新點主要有三個：

• 一是提出了方差置信度（variance confidence）的概念
• 二是提出了VSA（方差二次採樣算法）
• 三是提出了方差衰減策略（variance decay strategy）。

基本框架

The dataset extension process. Both labeled and unlabeled samples are extracted into the feature space through the backbone network in step 1. As shown in feature space (a), the gray points indicate unlabeled samples, and the colored hollow points indicate labeled samples. Different colors indicate different person identity. Then label estimation is performed according to the criterion that the unlabeled sample has the same label as the nearest labeled sample in step 2. We call the sample after label estimation a pseudo-label sample, which is the colored solid point in the feature space (b). Finally, the pseudo-label samples with higher confidence are preferred, which are closer to the labeled samples in feature space (c)

總體框架採用監督訓練和數據擴展交叉迭代進行的模式。數據擴展的過程如上圖所示，具體包括了特徵提取、標籤估計和僞標籤樣本採樣三個環節。

提出的方法

01 variance confidence方差置信度

A distribution situation in the feature space. U1 and U2 represent two unlabeled samples, and L1 and L2 are the two labeled samples with the closest distance to both U1 and U2 in the feature space. di,i∈[1,4], represent the Euclidean distance between samples and satisfy Equation (7). The solid line represents the distance between the unlabeled sample and its nearest labeled sample. While U1 is similar to L1, it is also similar to L2 with the same extent. On the contrary, although U2 is slightly similar to L1, it is very different from L2. Therefore, it is more believable that U2 is more likely than U1 to fall into the same category as L1

做者舉例了特徵空間中的一種分佈狀況。 U1和U2是無標註樣本，L1和L2是距離U1和U2最近的帶標註樣本。di表示樣本之間的歐幾里得距離，且知足\(d_1<d_2<d_3<d_4\)。 若是僅根據距離來度量樣本標籤的可靠性的話，那U1優於U2（由於d1<d3）。 但做者認爲，當一個樣本（U1）同時和兩個不一樣的樣本（L1和L2）類似的時候（d1和d2相差很小），那這個樣本就誰都不像了。

做者用無標籤樣本與其距離最近的兩個帶標註樣本的距離方差來表示方差置信度，且方差越大，置信度越高。

02 Variance Subsampling Algorithm 方差二次採樣算法

The sampling criterion of variance subsampling algorithm. Hollow points in the feature space represent labeled samples, and solid points represent pseudo-label samples. The first sampling is based on the distance confidence. The number of sampling is extended to e, corresponding to the range of the red squares and circles in the figure. The second sampling is based on the variance confidence, and the number of samples is restored to ns, which corresponds to the range of the yellow box and the circle in the figure.

做者經過二次採樣的形式，將距離置信度和方差置信度結合了起來，做爲採樣準則。

03 Variance decay strategy 方差衰減策略

The partial distribution of the real feature space. Colors is used to distinguish different people identity, and shapes is used to distinguish the camera. Black dots in the center of the sample indicate that this is the original labeled sample. The distribution in the first iteration is relatively uniform, while the distribution after the seventh iteration has shown a clustering distribution。

做者在實驗過程當中可視化了特徵空間的真實分佈狀況。 發現模型訓練到中後期時，提取出的特徵空間已經呈現出了聚類分佈。

Obviously, in the case of the feature distribution of model 7 in Figure 5, the situation described in Figure 3 will hardly occur. This shows that the situation described in Figure 3 is gradually reduced during the iteration process. Therefore, a variance decay strategy is proposed as the sampling strategy. A stopping factor 𝜂 is taken to control the number of steps in which the variance confidence is disabled. In addition, 𝜖 is also set to be variable and calculated by Equation (13).

在聚類分佈造成的狀況下， 方差置信度將再也不適用，所以做者提出了方差衰減策略。

總體的算法：

實驗

01 性能

Our method is evaluated on the MARS and DukeMTMC-VideoReID dataset, and compared with recent related works including the baseline work EUG.10 Table 1 reports the final results of different methods. One-shot refers to the experimental results obtained by supervised learning on the labeled dataset L only. DGM9 and SMP8 do not train their model in crossiterative manner. The results demonstrate that our method performs better than EUG on both the two datasets. Specifically, our mAP, Rank-1, Rank5, and Rank20 on the MARS dataset are 38.62%,62.17%,74.34%, and 83.43%, which surpasses the baseline10 by 3.94%, 4.55%, 4.70%, and 5.35%, respectively. Though we outperform10 on the four types of accuracy, the benefits of our method on DukeMTMC-VideoReID dataset is lower than the improvements on MARS dataset as the number of unlabeled samples in the DukeMTMC-VideoReID dataset is merely 1/5 of that in MARS dataset, which reduce the impacts of using sampling strategies.

02 Ablation - sampling criterions

We compared the number of error labels contained in the selected pseudo-label samples under different sampling strategies. Specifically, there are 1,494 unlabeled samples in the DukeMTMC-VideoReID dataset, of which 663 samples have correct labels after label estimation. As shown in Figure 7, the colored bar is where the wrong label is located. Among the 300 samples, 29 samples have error labels according to distance confidence only and 19 samples have error labels according to the variance confidence only, respectively. When we combine distance confidence and variance confidence as a two-round sampling criterion, the number of erroneous labels drops to 16, which means that the accuracy of selected sample labels is improved to 95% (90% with the distance confidence only). The result effectively illustrates that the VSA does effectively reduce the number of wrong labels in the selected samples.

將距離置信度和方差置信度結合起來，有效地提升了採樣出來的爲標籤樣本的標籤準確率。