Multiple receptive fields and small-object-focusing weakly-supervised segmentation network for fast object detection

04/19/2019
by   Siyang Sun, et al.
0

Object detection plays an important role in various visual applications. However, the precision and speed of detector are usually contradictory. One main reason for fast detectors' precision reduction is that small objects are hard to be detected. To address this problem, we propose a multiple receptive field and small-object-focusing weakly-supervised segmentation network (MRFSWSnet) to achieve fast object detection. In MRFSWSnet, multiple receptive fields block (MRF) is used to pay attention to the object and its adjacent background's different spatial location with different weights to enhance the feature's discriminability. In addition, in order to improve the accuracy of small object detection, a small-object-focusing weakly-supervised segmentation module which only focuses on small object instead of all objects is integrated into the detection network for auxiliary training to improve the precision of small object detection. Extensive experiments show the effectiveness of our method on both PASCAL VOC and MS COCO detection datasets. In particular, with a lower resolution version of 300x300, MRFSWSnet achieves 80.9 test with an inference speed of 15 milliseconds per frame, which is the state-of-the-art detector among real-time detectors.

READ FULL TEXT
research
11/25/2017

Multiple Instance Curriculum Learning for Weakly Supervised Object Detection

When supervising an object detector with weakly labeled data, most exist...
research
12/01/2017

Single-Shot Object Detection with Enriched Semantics

We propose a novel single shot object detection network named Detection ...
research
04/07/2016

A MultiPath Network for Object Detection

The recent COCO object detection dataset presents several new challenges...
research
11/09/2020

Real-time object detection method based on improved YOLOv4-tiny

The "You only look once v4"(YOLOv4) is one type of object detection meth...
research
07/20/2017

Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors

Object detection aims at high speed and accuracy simultaneously. However...
research
10/22/2020

Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection

Weakly Supervised Object Detection (WSOD) has emerged as an effective to...
research
10/11/2022

Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors

Recent object detection models require large amounts of annotated data f...

Please sign up or login with your details

Forgot password? Click here to reset