↓Skip to main content

Object Detection

AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection
·3853 words·19 mins· loading · loading
AI Generated Computer Vision Object Detection 🏢 Shanghai AI Laboratory
AdaptiveISP uses reinforcement learning to create a scene-adaptive ISP pipeline that dynamically optimizes for object detection, surpassing existing methods in accuracy and efficiency.
Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection
·2760 words·13 mins· loading · loading
Computer Vision Object Detection 🏢 Rochester Institute of Technology
AIRS framework, guided by Evidential Q-learning, dynamically balances exploration and exploitation to achieve superior dense object detection accuracy by adaptively selecting important regions.
Accelerating Non-Maximum Suppression: A Graph Theory Perspective
·3325 words·16 mins· loading · loading
AI Generated Computer Vision Object Detection 🏢 School of Computer Science and Technology, MOEKLINNS Lab, Xi'an Jiaotong University
This paper presents QSI-NMS and BOE-NMS, novel graph theory-based algorithms that significantly speed up non-maximum suppression (NMS) in object detection without significant accuracy loss, and introd…
A Siamese Transformer with Hierarchical Refinement for Lane Detection
·2636 words·13 mins· loading · loading
AI Generated Computer Vision Object Detection 🏢 Shanghai Jiao Tong University
Siamese Transformer with Hierarchical Refinement achieves state-of-the-art lane detection accuracy by integrating global and local features and a novel Curve-IoU loss.
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
·2616 words·13 mins· loading · loading
AI Generated Computer Vision Object Detection 🏢 Faculty of Computer and Information Science, University of Ljubljana
GeCo: A novel single-stage low-shot counter achieving ~25% improvement in count accuracy, via unified object detection, segmentation, and counting.