Multi-stage Object Detection with Group Recursive Learning

نویسندگان

  • Jianan Li
  • Xiaodan Liang
  • Jianshu Li
  • Tingfa Xu
  • Jiashi Feng
  • Shuicheng Yan
چکیده

Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial layout correlations among proposals are often ignored, which are actually useful for more accurate object detection. In this work, we propose a new EM-like group recursive learning approach to iteratively refine object proposals by incorporating such context of surrounding proposals and provide an optimal spatial configuration of object detections. In addition, we propose to incorporate the weakly-supervised object segmentation cues and region-based object detection into a multi-stage architecture in order to fully exploit the learned segmentation features for better object detection in an end-toend way. The proposed architecture consists of three cascaded networks which respectively learn to perform weakly-supervised object segmentation, object proposal generation and recursive detection refinement. Combining the group recursive learning and the multi-stage architecture provides competitive mAPs of 78.6% and 74.9% on the PASCAL VOC2007 and VOC2012 datasets respectively, which outperforms many well-established baselines [10] [20] significantly.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Multi-stage Sampling with Boosting Cascades for Pedestrian Detection in Images and Videos

Many works address the problem of object detection by means of machine learning with boosted classifiers. They exploit sliding window search, spanning the whole image: the patches, at all possible positions and sizes, are sent to the classifier. Several methods have been proposed to speed up the search (adding complementary features or using specialized hardware). In this paper we propose a sta...

متن کامل

Part and Appearance Sharing: Recursive Compositional Models for Multi-View Multi-Object Detection

We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object subparts). We represent the set of objects by a family of RCMs where each RCM is a probability distribution defined over a hierarchical graph which corresponds to a specific object and viewpoint. An RCM is constructed f...

متن کامل

Detection and Recognition of Multi-language Traffic Sign Context by Intelligent Driver Assistance Systems

Design of a new intelligent driver assistance system based on traffic sign detection with Persian context is concerned in this paper. The primary aim of this system is to increase the precision of drivers in choosing their path with regard to traffic signs. To achieve this goal, a new framework that implements fuzzy logic was used to detect traffic signs in videos captured along a highway f...

متن کامل

DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection

In this paper, we propose multi-stage and deformable deep convolutional neural networks for object detection. This new deep learning object detection diagram has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (defpooling) layer models the deformation of object parts with geometric constraint and penalty. With the proposed multistage...

متن کامل

Unsupervised Learning Models of Invariant Features in Images: Recent Developments in Multistage Architecture Approach for Object Detection

Object detection and recognition are important problems in computer vision and pattern recognition domain. Human beings are able to detect and classify objects effortlessly but replication of this ability on computer based systems has proved to be a non-trivial task. In particular, despite significant research efforts focused on meta-heuristic object detection and recognition, robust and reliab...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1608.05159  شماره 

صفحات  -

تاریخ انتشار 2016