HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities
원문 초록
Event cameras detect changes in per-pixel intensity to generate asynchronous `event streams'. They offer great potential for accurate semantic map retrieval in real-time autonomous systems owing to their much higher temporal resolution and high dynamic range (HDR) compared to conventional cameras. However, existing implementations for event-based segmentation suffer from sub-optimal performance since these temporally dense events only measure the varying component of a visual signal, limiting their ability to encode dense spatial context compared to frames. To address this issue, we propose a hybrid end-to-end learning framework HALSIE, utilizing three key concepts to reduce inference cost by up to $20\times$ versus prior art while retaining similar performance: First, a simple and efficient cross-domain learning scheme to extract complementary spatio-temporal embeddings from both frames and events. Second, a specially designed dual-encoder scheme with Spiking Neural Network (SNN) and Artificial Neural Network (ANN) branches to minimize latency while retaining cross-domain feature aggregation. Third, a multi-scale cue mixer to model rich representations of the fused embeddings. These qualities of HALSIE allow for a very lightweight architecture achieving state-of-the-art segmentation performance on DDD-17, MVSEC, and DSEC-Semantic datasets with up to $33\times$ higher parameter efficiency and favorable inference cost (17.9mJ per cycle). Our ablation study also brings new insights into effective design choices that can prove beneficial for research across other vision tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
VideoMolmo: Spatio-Temporal Grounding Meets Pointing
GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization
Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
A New Dataset and Performance Benchmark for Real-time Spacecraft Segmentation in Onboard Flight Computers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.