3 papers
cs.CV2026
Context-Guided Semantic Alignment for Feature Fusion Networks
Hyungseop Lee, Jiho Lee, Woochul Kang
Feature fusion networks are fundamental components in modern object detectors, aggregating multi-scale features to detect objects of varying sizes. However, directly fusing feature…
cs.CV2026
AnyDepth-DETR/-YOLO: Any-depth object detection with a single network
Woochul Kang, Hyungseop Lee, Jiho Lee
Modern object detectors are static, fixed-depth networks optimized for a single operating point, requiring separate models for different deployment scenarios. We present an any-dep…
cs.CV2023
Adaptive Depth Networks with Skippable Sub-Paths
Woochul Kang, Hyungseop Lee
Predictable adaptation of network depths can be an effective way to control inference latency and meet the resource condition of various devices. However, previous adaptive depth n…