SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping
We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by $36\%$ to $40\%$ (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net and FlowNet2. Our method integrates architecture improvements from supervised optical flow, i.e. the RAFT model, with new ideas for unsupervised learning that include a sequence-aware self-supervision loss, a technique for handling out-of-frame motion, and an approach for learning effectively from multi-frame video data while still only requiring two frames for inference.
Code (3)
Tasks
Optical Flow EstimationSimilar Papers 제목 키워드 기반
Smurfs: Leveraging Multiple Proficiency Agents with Context-Efficiency for Tool Planning
The emergence of large language models (LLMs) has opened up unprecedented possibilities for automating complex tasks that are often comparable to human performance. Despite their capabilities, LLMs still encounter diffic…
SMURFF: a High-Performance Framework for Matrix Factorization
Bayesian Matrix Factorization (BMF) is a powerful technique for recommender systems because it produces good results and is relatively robust against overfitting. Yet BMF is more computationally intensive and thus more c…
Activity PredictionRecommendation SystemsVocal Bursts Intensity PredictionSearching for Smurfs: Testing if Money Launderers Know Alert Thresholds
To combat money laundering, banks raise and review alerts on transactions that exceed confidential thresholds. This paper presents a data-driven approach to detect smurfing, i.e., money launderers seeking to evade detect…
counterfactualSMUDLP: Self-Teaching Multi-Frame Unsupervised Endoscopic Depth Estimation with Learnable Patchmatch
Unsupervised monocular trained depth estimation models make use of adjacent frames as a supervisory signal during the training phase. However, temporally correlated frames are also available at inference time for many cl…
Depth EstimationGARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Laundering
Money laundering poses a significant challenge as it is estimated to account for 2%-5% of the global GDP. This has compelled regulators to impose stringent controls on financial institutions. One prominent laundering met…
Computational EfficiencyFraud DetectionNetwork Embedding