Wei Wu, Bo Li, Wanli Ouyang, Xin Li, Jinyang Guo, Qiuhong Shen, Weihao Gan, Weitao Feng, Peixia Li, Lei Qiao
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable to track objects with strong variation over a long time span. As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forwardbackward. We present a novel unsupervised tracking framework, in which we can learn temporal correspondence both on the classification branch and regression branch. Specifically, to propagate reliable template feature in the forward propagation process so that the tracker can be trained in the cycle, we first propose a consistency propagation transformation. We then identify an ill-posed penalty problem in conventional cycle training in backward propagation process. Thus, a differentiable region mask is proposed to select features as well as to implicitly penalize tracking errors on intermediate frames. Moreover, since noisy labels may degrade training, we propose a mask-guided loss reweighting strategy to assign dynamic weights based on the quality of pseudo labels. In extensive experiments, our tracker outperforms preceding unsupervised methods by a substantial margin, performing on par with supervised methods on large-scale datasets such as TrackingNet and LaSOT. Code is available at https://github.com/FlorinShum/ULAST.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2204.01475")
get_code_for_paper("2204.01475")
have("2204.01475")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2204.01475.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2204.01475)
Connect an agent — have() is free.