TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)
Min Seok Lee, Woo-Seok Shin, Sung Won Han
Abstract
Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge features and aggregating multi-level features to improve SOD performance. However, both performance gain and computational efficiency cannot be achieved, which has motivated us to study the inefficiencies in existing encoder-decoder structures to avoid this trade-off. We propose TRACER which excludes multi-decoder structures and minimizes the learning parameters usage by employing attention guided tracing modules (ATMs), as shown in Fig. 1.
Topics & Concepts
TracingSalientComputer scienceEncoderEnhanced Data Rates for GSM EvolutionFocus (optics)Object (grammar)Artificial intelligenceRay tracing (physics)AutoencoderComputer visionDeep learningProgramming languageOperating systemOpticsPhysicsQuantum mechanicsVisual Attention and Saliency DetectionVideo Surveillance and Tracking MethodsAdvanced Image and Video Retrieval Techniques