SWIPENET: Object detection in noisy underwater images
- URL: http://arxiv.org/abs/2010.10006v3
- Date: Sun, 13 Mar 2022 04:45:54 GMT
- Title: SWIPENET: Object detection in noisy underwater images
- Authors: Long Chen, Feixiang Zhou, Shengke Wang, Junyu Dong, Ning Li, Haiping
Ma, Xin Wang and Huiyu Zhou
- Abstract summary: We propose a novel Sample-WeIghted hyPEr Network (SWIPENET), and a robust training paradigm named Curriculum Multi-Class Adaboost (CMA) to address these two problems.
The backbone of SWIPENET produces multiple high resolution and semantic-rich Hyper Feature Maps, which significantly improve small object detection.
Inspired by the human education process that drives the learning from easy to hard concepts, we here propose the CMA training paradigm that first trains a clean detector which is free from the influence of noisy data.
- Score: 41.35601054297707
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In recent years, deep learning based object detection methods have achieved
promising performance in controlled environments. However, these methods lack
sufficient capabilities to handle underwater object detection due to these
challenges: (1) images in the underwater datasets and real applications are
blurry whilst accompanying severe noise that confuses the detectors and (2)
objects in real applications are usually small. In this paper, we propose a
novel Sample-WeIghted hyPEr Network (SWIPENET), and a robust training paradigm
named Curriculum Multi-Class Adaboost (CMA), to address these two problems at
the same time. Firstly, the backbone of SWIPENET produces multiple high
resolution and semantic-rich Hyper Feature Maps, which significantly improve
small object detection. Secondly, a novel sample-weighted detection loss
function is designed for SWIPENET, which focuses on learning high weight
samples and ignore learning low weight samples. Moreover, inspired by the human
education process that drives the learning from easy to hard concepts, we here
propose the CMA training paradigm that first trains a clean detector which is
free from the influence of noisy data. Then, based on the clean detector,
multiple detectors focusing on learning diverse noisy data are trained and
incorporated into a unified deep ensemble of strong noise immunity. Experiments
on two underwater robot picking contest datasets (URPC2017 and URPC2018) show
that the proposed SWIPENET+CMA framework achieves better accuracy in object
detection against several state-of-the-art approaches.
Related papers
- Dynamic Loss Decay based Robust Oriented Object Detection on Remote Sensing Images with Noisy Labels [17.211935951030114]
We propose a robust oriented remote sensing object detection method through dynamic loss decay (DLD) mechanism.
Our solution has won the 2st place in the "fine-grained object detection based on sub-meter remote sensing imagery" track with noisy labels of 2023 National Big Data and Computing Intelligence Challenge.
arXiv Detail & Related papers (2024-05-15T01:29:28Z) - Efficient Meta-Learning Enabled Lightweight Multiscale Few-Shot Object Detection in Remote Sensing Images [15.12889076965307]
YOLOv7 one-stage detector is subjected to a novel meta-learning training framework.
This transformation allows the detector to adeptly address FSOD tasks while capitalizing on its inherent advantage of lightweight.
To validate the effectiveness of our proposed detector, we conducted performance comparisons with current state-of-the-art detectors.
arXiv Detail & Related papers (2024-04-29T04:56:52Z) - Robust Tiny Object Detection in Aerial Images amidst Label Noise [50.257696872021164]
This study addresses the issue of tiny object detection under noisy label supervision.
We propose a DeNoising Tiny Object Detector (DN-TOD), which incorporates a Class-aware Label Correction scheme.
Our method can be seamlessly integrated into both one-stage and two-stage object detection pipelines.
arXiv Detail & Related papers (2024-01-16T02:14:33Z) - Small Object Detection via Coarse-to-fine Proposal Generation and
Imitation Learning [52.06176253457522]
We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning.
CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
arXiv Detail & Related papers (2023-08-18T13:13:09Z) - Cascaded Zoom-in Detector for High Resolution Aerial Images [12.944309759825902]
We propose an efficient Cascaded Zoom-in (CZ) detector that re-purposes the detector itself for density-guided training and inference.
During training, density crops are located, labeled as a new class, and employed to augment the training dataset.
This approach is easily integrated into any detector, and creates no significant change in the standard detection process.
arXiv Detail & Related papers (2023-03-15T16:39:21Z) - Activation to Saliency: Forming High-Quality Labels for Unsupervised
Salient Object Detection [54.92703325989853]
We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues.
No human annotations are involved in our framework during the whole training process.
Our framework reports significant performance compared with existing USOD methods.
arXiv Detail & Related papers (2021-12-07T11:54:06Z) - Few-Cost Salient Object Detection with Adversarial-Paced Learning [95.0220555274653]
This paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only.
We name this task as the few-cost salient object detection and propose an adversarial-paced learning (APL)-based framework to facilitate the few-cost learning scenario.
arXiv Detail & Related papers (2021-04-05T14:15:49Z) - Underwater object detection using Invert Multi-Class Adaboost with deep
learning [37.14538666012363]
We propose a novel neural network architecture, namely Sample-WeIghted hyPEr Network (SWIPENet), for small object detection.
We show that the proposed SWIPENet+IMA framework achieves better performance in detection accuracy against several state-of-the-art object detection approaches.
arXiv Detail & Related papers (2020-05-23T15:30:38Z) - One-Shot Object Detection without Fine-Tuning [62.39210447209698]
We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module.
We also propose novel training strategies that effectively improve detection performance.
Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
arXiv Detail & Related papers (2020-05-08T01:59:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.