Deep Regionlets for Object Detection

Abstract

In this paper, we propose a novel object detection framework named "Deep Regionlets" by establishing a bridge between deep neural networks and conventional detection schema for accurate generic object detection. Motivated by the abilities of regionlets for modeling object deformation and multiple aspect ratios, we incorporate regionlets into an end-to-end trainable deep learning framework. The deep regionlets framework consists of a region selection network and a deep regionlet learning module. Specifically, given a detection bounding box proposal, the region selection network provides guidance on where to select regions to learn the features from. The regionlet learning module focuses on local feature selection and transformation to alleviate local variations. To this end, we first realize non-rectangular region selection within the detection framework to accommodate variations in object appearance. Moreover, we design a "gating network" within the regionlet leaning module to enable soft regionlet selection and pooling. The Deep Regionlets framework is trained end-to-end without additional efforts. We perform ablation studies and conduct extensive experiments on the PASCAL VOC and Microsoft COCO datasets. The proposed framework outperforms state-of-the-art algorithms, such as RetinaNet and Mask R-CNN, even without additional segmentation labels.

Accepted to ECCV 2018

References in corpus (24)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• DSSD : Deconvolutional Single Shot Detector
• Focal Loss for Dense Object Detection
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• Fully Convolutional Networks for Semantic Segmentation
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Feature Pyramid Networks for Object Detection
• YOLO9000: Better, Faster, Stronger
• Deformable Convolutional Networks
• Cascade R-CNN: Delving into High Quality Object Detection
• Aggregated Residual Transformations for Deep Neural Networks
• Speed/accuracy trade-offs for modern convolutional object detectors
• Relation Networks for Object Detection
• Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
• Soft Sampling for Robust Object Detection
• Dynamic Zoom-in Network for Fast Object Detection in Large Images
• Single-Shot Object Detection with Enriched Semantics
• An Analysis of Scale Invariance in Object Detection - SNIP
• Multi-scale Location-aware Kernel Representation for Object Detection
• The Role of Context Selection in Object Detection
• Cross-Domain Visual Recognition via Domain Adaptive Dictionary Learning
• Pseudo Mask Augmented Object Detection

Cited by in corpus (6)

• CornerNet: Detecting Objects as Paired Keypoints
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• Learning Rich Features for Image Manipulation Detection
• NISP: Pruning Networks using Neuron Importance Score Propagation
• Prime Sample Attention in Object Detection
• Cross-Domain Visual Recognition via Domain Adaptive Dictionary Learning