个人理解

为什么：
- 深度学习中常见的回归和分类问题一般是把可微分的评价标准（准确率等）直接放入损失函数，引导整个神经网络的学习。
- MOT(多目标追踪)算法的评价标准一般是基于MOTA, MOTP等，但和普通的回归或分类问题不同的是，MOTA，MOTP等不可微分，也不能直接放入作为神经网络的损失函数。
创新点：
- 受到标准MOT评估措施[6]的启发，提出了新的损失函数，用于多目标跟踪器的端到端训练。
- 为了在网络中反向传播损失，提出了一个新的网络模块——深度匈牙利网（DHN）——它学习以可微分的方式将预测轨道与 GT 对象匹配
怎么做：
1. 将匈牙利算法融入神经网络（本文提出的DHN）
2. 将MOTA和MOTP表示为损失函数（将MOTA 和 MOTP 变成可微分的）
3. 实现从目标检测到最终评价标准的完整深度学习模型。

一、摘要

The recent trend in vision-based multi-object tracking (MOT) is heading towards leveraging the representational power of deep learning to jointly learn to detect and track objects. However, existing methods train only certain submodules using loss functions that often do not correlate with established tracking evaluation measures such as MultiObject Tracking Accuracy (MOTA) and Precision (MOTP). As these measures are not differentiable, the choice of appropriate loss functions for end-to-end training of multiobject tracking methods is still an open research problem. In this paper, we bridge this gap by proposing a differentiable proxy of MOTA and MOTP, which we combine in a loss function suitable for end-to-end training of deep multiobject trackers. As a key ingredient, we propose a Deep Hungarian Net (DHN) module that approximates the Hungarian matching algorithm. DHN allows estimating the correspondence between object tracks and ground truth objects to compute differentiable proxies of MOTA and MOTP, which are in turn used to optimize deep trackers directly. We experimentally demonstrate that the proposed differentiable framework improves the performance of existing multi-object trackers, and we establish a new state of the art on the MOTChallenge benchmark.

基于视觉的多目标跟踪(MOT)最近的趋势是利用深度学习的表示法来联合学习检测和跟踪对象。然而，现有的方法只使用损失函数训练某些子模块，这些函数通常与建立的跟踪评估指标(如多目标跟踪精度(MOTA)和精度(MOTP)不相关。即只训练了检测器，跟踪器一般没有训练
本文提出MOTA和MOTP的可微分代理来弥合这一差距，并将其组合在一个适合于深度多目标跟踪器端到端训练的损失函数中