Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection

• URL: http://arxiv.org/abs/2504.20602v1
• Date: Tue, 29 Apr 2025 10:11:03 GMT
• Title: Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection
• Authors: Siwei Wang, Zhiwei Chen, Liujuan Cao, Rongrong Ji,
• Abstract summary: PLUSNet is a high-quality Small object detection framework.<n>It comprises three components: the Hierarchical Feature (HFP) framework for purifying upstream features, the Multiple Criteria Label Assignment (MCLA) for improving the quality of midstream training samples, and the Frequency Decoupled Head (FDHead) for more effectively exploiting information to accomplish downstream tasks.
• Score: 83.90563802153707
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Small object detection is a broadly investigated research task and is commonly conceptualized as a "pipeline-style" engineering process. In the upstream, images serve as raw materials for processing in the detection pipeline, where pre-trained models are employed to generate initial feature maps. In the midstream, an assigner selects training positive and negative samples. Subsequently, these samples and features are fed into the downstream for classification and regression. Previous small object detection methods often focused on improving isolated stages of the pipeline, thereby neglecting holistic optimization and consequently constraining overall performance gains. To address this issue, we have optimized three key aspects, namely Purifying, Labeling, and Utilizing, in this pipeline, proposing a high-quality Small object detection framework termed PLUSNet. Specifically, PLUSNet comprises three sequential components: the Hierarchical Feature Purifier (HFP) for purifying upstream features, the Multiple Criteria Label Assignment (MCLA) for improving the quality of midstream training samples, and the Frequency Decoupled Head (FDHead) for more effectively exploiting information to accomplish downstream tasks. The proposed PLUS modules are readily integrable into various object detectors, thus enhancing their detection capabilities in multi-scale scenarios. Extensive experiments demonstrate the proposed PLUSNet consistently achieves significant and consistent improvements across multiple datasets for small object detection.

Related papers

• CS-Net:Contribution-based Sampling Network for Point Cloud Simplification [50.55658910053004]
  Point cloud sampling plays a crucial role in reducing computation costs and storage requirements for various vision tasks.<n>Traditional sampling methods, such as farthest point sampling, lack task-specific information.<n>We propose a contribution-based sampling network (CS-Net), where the sampling operation is formulated as a Top-k operation.
  arXiv  Detail & Related papers  (2025-01-18T14:56:09Z)
• Multi-Point Positional Insertion Tuning for Small Object Detection [10.852047082856487]
  Small object detection aims to localize and classify small objects within images.<n>Finetuning pretrained object detection models is computationally and memory expensive.<n>This paper introduces multi-point positional insertion (MPI) tuning, a parameter-efficient finetuning (PEFT) method for small object detection.
  arXiv  Detail & Related papers  (2024-12-24T02:04:47Z)
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization [87.21285093582446]
  Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments. Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
  arXiv  Detail & Related papers  (2023-10-04T09:39:05Z)
• 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)
• Label-Efficient Object Detection via Region Proposal Network Pre-Training [58.50615557874024]
  We propose a simple pretext task that provides an effective pre-training for the region proposal network (RPN) In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance.
  arXiv  Detail & Related papers  (2022-11-16T16:28:18Z)
• Comprehensive Analysis of the Object Detection Pipeline on UAVs [16.071349046409885]
  We first empirically analyze the influence of seven parameters (quantization, compression, resolution, color model, image distortion, gamma correction, additional channels) in remote sensing applications. We show that not all parameters have an equal impact on detection accuracy and data throughput, and that by using a suitable compromise between parameters we are able to improve detection accuracy for lightweight object detection models.
  arXiv  Detail & Related papers  (2022-03-01T09:30:01Z)
• CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images [0.9462808515258465]
  In this paper, we discuss the role of discriminative features in object detection. We then propose a Critical Feature Capturing Network (CFC-Net) to improve detection accuracy. We show that our method achieves superior detection performance compared with many state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-01-18T02:31:09Z)
• 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.