Efficient Multi-Timescale Event Representations for Feed-Forward Object Detection
Autonomous systems require robust low-latency perception under rapidly changing scene dynamics and challenging illumination. In event cameras object detection commonly relies on recurrent architectures to accumulate sparse temporal information over time. This work investigates how temporal information can be encoded directly within the event representation. We propose a confidence-normalized continuous multi-timescale representation based on logarithmic B-spline temporal encoding together with a geometry-aware local confidence mechanism that exploits the spatial structure of event generation. Using a fixed feed-forward EventCenterNet detector, we show that the proposed representations consistently outperform the compact CSTR representation on PEDRo and Gen1 datasets. We further introduce a recursive exponential-polynomial approximation that enables efficient event-by-event updates while largely preserving detection performance. These results demonstrate that carefully designed event representations can capture a substantial portion of the temporal information learned through recurrent temporal modeling, providing a promising foundation for efficient feed-forward, event-driven, and future neuromorphic object detection.
Code (0)
등록된 구현이 없습니다.
Tasks
Object DetectionSimilar Papers 제목 키워드 기반
Brain-Inspired Architectures for Efficient and Meaningful Learning from Temporally Smooth Data
How can learning systems exploit the temporal smoothness of real-world training data? We tested the learning of neural networks equipped with two architectural features inspired by the temporal properties of neural circu…
Thalamocortical interactions shape hierarchical neural variability during stimulus perception
The brain is hierarchically organized to process sensory signals. But, to what extent do functional connections within and across areas shape this hierarchical order? We addressed this problem in the thalamocortical netw…
Functional ConnectivityDoes Feedback Alignment Work at Biological Timescales?
Feedback alignment and related weight-transport-free algorithms are often proposed as biologically plausible alternatives to backpropagation, yet they are typically formulated in discrete phases with implicitly synchroni…
Towards efficient keyword spotting using spike-based time difference encoders
Keyword spotting in edge devices is becoming increasingly important as voice-activated assistants are widely used. However, its deployment is often limited by the extreme low-power constraints of the target embedded syst…
Keyword SpottingMulti-Timescale Conductance Spiking Networks: A Sparse, Gradient-Trainable Framework with Rich Firing Dynamics for Enhanced Temporal Processing
Spiking neural networks (SNNs) promise low-power event-driven computation for temporally rich tasks, but commonly used neuron models often trade off gradient-based trainability, dynamical richness, and high activity spar…