Although end-to-end multi-object trackers like MOTR enjoy the merits of
simplicity, they suffer from the conflict between detection and association
seriously, resulting in unsatisfactory convergence dynamics. While MOTRv2
partly addresses this problem, it demands an additional detection network for
assistance. In this work, we serve as the first to reveal that this conflict
arises from the unfair label assignment between detect queries and track
queries during training, where these detect queries recognize targets and track
queries associate them. Based on this observation, we propose MOTRv3, which
balances the label assignment process using the developed release-fetch
supervision strategy. In this strategy, labels are first released for detection
and gradually fetched back for association. Besides, another two strategies
named pseudo label distillation and track group denoising are designed to
further improve the supervision for detection and association. Without the
assistance of an extra detection network during inference, MOTRv3 achieves
impressive performance across diverse benchmarks, e.g., MOT17, DanceTrack.

本文提出 MOTRv3，通过改进释放 - 获取监督策略来平衡检测和关联之间的不公平标签分配，同时设计伪标签蒸馏与轨迹组去噪来进一步提高检测与关联的监督效果，从而无需额外的检测网络，在 MOT17，DanceTrack 等各种基准测试中实现了卓越的性能。

MOTRv3: 基于 Release-Fetch 监督的端到端多目标跟踪

MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking

Self-supervised multi-object trackers have the potential to leverage the vast
amounts of raw data recorded worldwide. However, they still fall short in
re-identification accuracy compared to their supervised counterparts. We
hypothesize that this deficiency results from restricting self-supervised
objectives to single frames or frame pairs. Such designs lack sufficient visual
appearance variations during training to learn consistent re-identification
features. Therefore, we propose a training objective that learns
re-identification features over a sequence of frames by enforcing consistent
association scores across short and long timescales. Extensive evaluations on
the BDD100K and MOT17 benchmarks demonstrate that our learned ReID features
significantly reduce ID switches compared to other self-supervised methods,
setting the new state of the art for self-supervised multi-object tracking and
even performing on par with supervised methods on the BDD100k benchmark.

通过在图像序列帧上进行一致的关联性评分，我们提出了一种学习重新识别特征的训练目标，可以显著降低 ID 开关，即使在 BDD100k 基准测试中表现和受监督的方法相当，也能够设置自监督多目标跟踪的新颖技术。

基于时间尺度连续性的自监督多目标跟踪

Self-Supervised Multi-Object Tracking From Consistency Across Timescales

Most online multi-object trackers perform object detection stand-alone in a
neural net without any input from tracking. In this paper, we present a new
online joint detection and tracking model, TraDeS (TRAck to DEtect and
Segment), exploiting tracking clues to assist detection end-to-end. TraDeS
infers object tracking offset by a cost volume, which is used to propagate
previous object features for improving current object detection and
segmentation. Effectiveness and superiority of TraDeS are shown on 4 datasets,
including MOT (2D tracking), nuScenes (3D tracking), MOTS and Youtube-VIS
(instance segmentation tracking). Project page:
this https URL

本文提出了一种新的在线联合检测和跟踪模型 ——TraDeS，该模型充分利用跟踪线索来辅助检测，并通过代价体推断对象跟踪偏移量，用于传播先前对象特征，从而改善当前对象的检测和分割。