Self-Supervised Learning for Real-World Object Detection: a Survey

• URL: http://arxiv.org/abs/2410.07442v2
• Date: Fri, 11 Oct 2024 08:46:46 GMT
• Title: Self-Supervised Learning for Real-World Object Detection: a Survey
• Authors: Alina Ciocarlan, Sidonie Lefebvre, Sylvie Le Hégarat-Mascle, Arnaud Woiselle,
• Abstract summary: Self-Supervised Learning (SSL) has emerged as a promising approach in computer vision. SSL methods fall into two main categories: instance discrimination and Masked Image Modeling (MIM)
• Score: 1.2224547302812558
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-Supervised Learning (SSL) has emerged as a promising approach in computer vision, enabling networks to learn meaningful representations from large unlabeled datasets. SSL methods fall into two main categories: instance discrimination and Masked Image Modeling (MIM). While instance discrimination is fundamental to SSL, it was originally designed for classification and may be less effective for object detection, particularly for small objects. In this survey, we focus on SSL methods specifically tailored for real-world object detection, with an emphasis on detecting small objects in complex environments. Unlike previous surveys, we offer a detailed comparison of SSL strategies, including object-level instance discrimination and MIM methods, and assess their effectiveness for small object detection using both CNN and ViT-based architectures. Specifically, our benchmark is performed on the widely-used COCO dataset, as well as on a specialized real-world dataset focused on vehicle detection in infrared remote sensing imagery. We also assess the impact of pre-training on custom domain-specific datasets, highlighting how certain SSL strategies are better suited for handling uncurated data. Our findings highlight that instance discrimination methods perform well with CNN-based encoders, while MIM methods are better suited for ViT-based architectures and custom dataset pre-training. This survey provides a practical guide for selecting optimal SSL strategies, taking into account factors such as backbone architecture, object size, and custom pre-training requirements. Ultimately, we show that choosing an appropriate SSL pre-training strategy, along with a suitable encoder, significantly enhances performance in real-world object detection, particularly for small object detection in frugal settings.

Related papers

• Scale-Aware Self-Supervised Learning for Segmentation of Small and Sparse Structures [8.202335520689024]
  Self-supervised learning has emerged as a powerful strategy for representation learning under limited annotation regimes.<n>In this work, we propose a scale-aware SSL adaptation that integrates small-window cropping into the augmentation pipeline.<n>We evaluate this approach across two domains with markedly different data modalities: seismic imaging and neuroimaging.
  arXiv  Detail & Related papers  (2026-01-26T15:58:04Z)
• Extending Dataset Pruning to Object Detection: A Variance-based Approach [0.0]
  We present the first extension of classification pruning techniques to the object detection domain.<n>We propose tailored solutions, including a novel scoring method called Variance-based Prediction Score (VPS)<n>Our work bridges dataset pruning and object detection, paving the way for dataset pruning in complex vision tasks.
  arXiv  Detail & Related papers  (2025-05-22T19:46:51Z)
• Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning [51.170479006249195]
  We introduce a new dataset, benchmark, and a dynamic coarse-to-fine learning scheme in this study. Our proposed dataset, AI-TOD-R, features the smallest object sizes among all oriented object detection datasets. We present a benchmark spanning a broad range of detection paradigms, including both fully-supervised and label-efficient approaches.
  arXiv  Detail & Related papers  (2024-12-16T09:14:32Z)
• A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification [51.35500308126506]
  Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. We study how classification-based evaluation protocols for SSL correlate and how well they predict downstream performance on different dataset types.
  arXiv  Detail & Related papers  (2024-07-16T23:17:36Z)
• Self-supervised visual learning in the low-data regime: a comparative evaluation [40.27083924454058]
  Self-Supervised Learning (SSL) is a robust training methodology for contemporary Deep Neural Networks (DNNs) This work introduces a taxonomy of modern visual SSL methods, accompanied by detailed explanations and insights regarding the main categories of approaches. For domain-specific downstream tasks, in-domain low-data SSL pretraining outperforms the common approach of large-scale pretraining.
  arXiv  Detail & Related papers  (2024-04-26T07:23:14Z)
• Improved Region Proposal Network for Enhanced Few-Shot Object Detection [23.871860648919593]
  Few-shot object detection (FSOD) methods have emerged as a solution to the limitations of classic object detection approaches. We develop a semi-supervised algorithm to detect and then utilize unlabeled novel objects as positive samples during the FSOD training stage. Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception of the object detection model for large objects.
  arXiv  Detail & Related papers  (2023-08-15T02:35:59Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• In-Domain Self-Supervised Learning Improves Remote Sensing Image Scene Classification [5.323049242720532]
  Self-supervised learning has emerged as a promising approach for remote sensing image classification. We present a study of different self-supervised pre-training strategies and evaluate their effect across 14 downstream datasets.
  arXiv  Detail & Related papers  (2023-07-04T10:57:52Z)
• De-coupling and De-positioning Dense Self-supervised Learning [65.56679416475943]
  Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects. We show that they suffer from coupling and positional bias, which arise from the receptive field increasing with layer depth and zero-padding. We demonstrate the benefits of our method on COCO and on a new challenging benchmark, OpenImage-MINI, for object classification, semantic segmentation, and object detection.
  arXiv  Detail & Related papers  (2023-03-29T18:07:25Z)
• Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
  It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones. We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
  arXiv  Detail & Related papers  (2022-05-02T16:09:17Z)
• Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection [86.86602297364826]
  We propose a discoveryand-selection approach fused with multiple instance learning (DS-MIL) Our proposed DS-MIL approach can consistently improve the baselines, reporting state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-10-18T07:06:57Z)
• Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning [101.28281124670647]
  Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. We propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning. Our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2021-08-12T09:14:44Z)

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.