paper-with-me

홈 › Papers

BootsTAP: Bootstrapped Training for Tracking-Any-Point

2024-02-01 · Carl Doersch, Pauline Luc, Yi Yang, Dilara Gokay, Skanda Koppula, Ankush Gupta, Joseph Heyward, Ignacio Rocco, Ross Goroshin, João Carreira, Andrew Zisserman

To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform in real scenes. This can be formalized as Tracking-Any-Point (TAP), which requires the algorithm to track any point on solid surfaces in a video, potentially densely in space and time. Large-scale groundtruth training data for TAP is only available in simulation, which currently has a limited variety of objects and motion. In this work, we demonstrate how large-scale, unlabeled, uncurated real-world data can improve a TAP model with minimal architectural changes, using a selfsupervised student-teacher setup. We demonstrate state-of-the-art performance on the TAP-Vid benchmark surpassing previous results by a wide margin: for example, TAP-Vid-DAVIS performance improves from 61.3% to 67.4%, and TAP-Vid-Kinetics from 57.2% to 62.5%. For visualizations, see our project webpage at https://bootstap.github.io/

📄 PDF Abstract BibTeX arXiv:2402.00847

Code (2)

google-deepmind/tapnet 공식 구현 jax
deepmind/tapnet jax

Tasks

Point Tracking

Similar Papers 제목 키워드 기반

Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation

2021-03-19 · Yihao Zhang, John J. Leonard

For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge. We formalize this as a bootstrapped self-supervised learning problem where a system …

Depth EstimationSelf-Supervised LearningSemantic Segmentation

Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise

2022-03-02 · Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad

Q-learning is one of the most well-known Reinforcement Learning algorithms. There have been tremendous efforts to develop this algorithm using neural networks. Bootstrapped Deep Q-Learning Network is amongst them. It uti…

Atari GamesDiversityQ-Learning

Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games

2020-09-24 · EMNLP 2020 11 · Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula, Michiaki Tatsubori 외

We show that Reinforcement Learning (RL) methods for solving Text-Based Games (TBGs) often fail to generalize on unseen games, especially in small data regimes. To address this issue, we propose Context Relevant Episodic…

Q-LearningReinforcement Learning (RL)text-based games

Bootstrapped Training of Event Extraction Classifiers

2012-04-01 · EACL 2012 4 · Ruihong Huang, Ellen Riloff
Event ExtractionSentence Classification

Choice Between Partial Trajectories: Disentangling Goals from Beliefs

2024-10-30 · Henrik Marklund, Benjamin Van Roy

As AI agents generate increasingly sophisticated behaviors, manually encoding human preferences to guide these agents becomes more challenging. To address this, it has been suggested that agents instead learn preferences…