Drop-dtw: Aligning Common Signal Between Sequences While Dropping Outliers

Abstract

In this work, we consider the problem of sequence-to-sequence alignment for signals containing outliers. Assuming the absence of outliers, the standard Dynamic Time Warping (DTW) algorithm efficiently computes the optimal alignment between two (generally) variable-length sequences. While DTW is robust to temporal shifts and dilations of the signal, it fails to align sequences in a meaningful way in the presence of outliers that can be arbitrarily interspersed in the sequences. To address this problem, we introduce Drop-DTW, a novel algorithm that aligns the common signal between the sequences while automatically dropping the outlier elements from the matching. The entire procedure is implemented as a single dynamic program that is efficient and fully differentiable. In our experiments, we show that Drop-DTW is a robust similarity measure for sequence retrieval and demonstrate its effectiveness as a training loss on diverse applications. With Drop-DTW, we address temporal step localizat

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydvornik2021drop

Related papers

• Elastic Bands Across The Path: A New Framework And Methods To Lower Bound DTW (2018)10.35
• Representation Learning Via Global Temporal Alignment And Cycle-consistency (2021)12.81
• Sync From The Sea: Retrieving Alignable Videos From Large-scale Datasets (2024)4.52
• Asymmetric Learning Vector Quantization For Efficient Nearest Neighbor Classification In Dynamic Time Warping Spaces (2017)9.92
• DAC: 2D-3D Retrieval With Noisy Labels Via Divide-and-conquer Alignment And Correction (2024)3.58
• Dynamic Uncertainty Learning With Noisy Correspondence For Text-based Person Search (2025)7.50
• Cross-domain Diffusion With Progressive Alignment For Efficient Adaptive Retrieval (2025)6.34
• Disentangle And Denoise: Tackling Context Misalignment For Video Moment Retrieval (2024)0.00