TempoFormer: A Transformer for Temporally-aware Representations in Change Detection
This addresses the need for temporally-aware models in change detection, offering a flexible foundation for other architectures, though it is incremental by building on transformer methods.
The paper tackled the problem of learning dynamic representations for understanding linguistic content evolution over time, achieving new state-of-the-art performance on three real-time change detection tasks.
Dynamic representation learning plays a pivotal role in understanding the evolution of linguistic content over time. On this front both context and time dynamics as well as their interplay are of prime importance. Current approaches model context via pre-trained representations, which are typically temporally agnostic. Previous work on modelling context and temporal dynamics has used recurrent methods, which are slow and prone to overfitting. Here we introduce TempoFormer, the first task-agnostic transformer-based and temporally-aware model for dynamic representation learning. Our approach is jointly trained on inter and intra context dynamics and introduces a novel temporal variation of rotary positional embeddings. The architecture is flexible and can be used as the temporal representation foundation of other models or applied to different transformer-based architectures. We show new SOTA performance on three different real-time change detection tasks.