Robust Tiny Object Detection in Aerial Images amidst Label Noise
- URL: http://arxiv.org/abs/2401.08056v1
- Date: Tue, 16 Jan 2024 02:14:33 GMT
- Title: Robust Tiny Object Detection in Aerial Images amidst Label Noise
- Authors: Haoran Zhu, Chang Xu, Wen Yang, Ruixiang Zhang, Yan Zhang, Gui-Song
Xia
- Abstract summary: 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.
- Score: 50.257696872021164
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Precise detection of tiny objects in remote sensing imagery remains a
significant challenge due to their limited visual information and frequent
occurrence within scenes. This challenge is further exacerbated by the
practical burden and inherent errors associated with manual annotation:
annotating tiny objects is laborious and prone to errors (i.e., label noise).
Training detectors for such objects using noisy labels often leads to
suboptimal performance, with networks tending to overfit on noisy labels. In
this study, we address the intricate issue of tiny object detection under noisy
label supervision. We systematically investigate the impact of various types of
noise on network training, revealing the vulnerability of object detectors to
class shifts and inaccurate bounding boxes for tiny objects. To mitigate these
challenges, we propose a DeNoising Tiny Object Detector (DN-TOD), which
incorporates a Class-aware Label Correction (CLC) scheme to address class
shifts and a Trend-guided Learning Strategy (TLS) to handle bounding box noise.
CLC mitigates inaccurate class supervision by identifying and filtering out
class-shifted positive samples, while TLS reduces noisy box-induced erroneous
supervision through sample reweighting and bounding box regeneration.
Additionally, Our method can be seamlessly integrated into both one-stage and
two-stage object detection pipelines. Comprehensive experiments conducted on
synthetic (i.e., noisy AI-TOD-v2.0 and DOTA-v2.0) and real-world (i.e., AI-TOD)
noisy datasets demonstrate the robustness of DN-TOD under various types of
label noise. Notably, when applied to the strong baseline RFLA, DN-TOD exhibits
a noteworthy performance improvement of 4.9 points under 40% mixed noise.
Datasets, codes, and models will be made publicly available.
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) - SoftPatch: Unsupervised Anomaly Detection with Noisy Data [67.38948127630644]
This paper considers label-level noise in image sensory anomaly detection for the first time.
We propose a memory-based unsupervised AD method, SoftPatch, which efficiently denoises the data at the patch level.
Compared with existing methods, SoftPatch maintains a strong modeling ability of normal data and alleviates the overconfidence problem in coreset.
arXiv Detail & Related papers (2024-03-21T08:49:34Z) - Detecting tiny objects in aerial images: A normalized Wasserstein
distance and a new benchmark [45.10513110142015]
We propose a new evaluation metric dubbed Normalized Wasserstein Distance (NWD) and a new RanKing-based Assigning (RKA) strategy for tiny object detection.
The proposed NWD-RKA strategy can be easily embedded into all kinds of anchor-based detectors to replace the standard IoU threshold-based one.
Tested on four datasets, NWD-RKA can consistently improve tiny object detection performance by a large margin.
arXiv Detail & Related papers (2022-06-28T13:33:06Z) - Incremental-DETR: Incremental Few-Shot Object Detection via
Self-Supervised Learning [60.64535309016623]
We propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector.
To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision.
We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting.
arXiv Detail & Related papers (2022-05-09T05:08:08Z) - SWIPENET: Object detection in noisy underwater images [41.35601054297707]
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.
arXiv Detail & Related papers (2020-10-19T16:41:20Z) - SCRDet++: Detecting Small, Cluttered and Rotated Objects via
Instance-Level Feature Denoising and Rotation Loss Smoothing [131.04304632759033]
Small and cluttered objects are common in real-world which are challenging for detection.
In this paper, we first innovatively introduce the idea of denoising to object detection.
Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects.
arXiv Detail & Related papers (2020-04-28T06:03:54Z) - Towards Noise-resistant Object Detection with Noisy Annotations [119.63458519946691]
Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates.
Noisy annotations are much more easily accessible, but they could be detrimental for learning.
We address the challenging problem of training object detectors with noisy annotations, where the noise contains a mixture of label noise and bounding box noise.
arXiv Detail & Related papers (2020-03-03T01:32:16Z) - Progressive Object Transfer Detection [84.48927705173494]
We propose a novel Progressive Object Transfer Detection (POTD) framework.
First, POTD can leverage various object supervision of different domains effectively into a progressive detection procedure.
Second, POTD consists of two delicate transfer stages, i.e., Low-Shot Transfer Detection (LSTD), and Weakly-Supervised Transfer Detection (WSTD)
arXiv Detail & Related papers (2020-02-12T00:16:24Z)
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.