Cyclic self-training with proposal weight modulation for cross-supervised object detection

Turnitin 降AI改写 早检测系统 早降重系统 Turnitin-UK版 万方检测-期刊版 维普编辑部版 Grammarly检测 Paperpass检测 checkpass检测 PaperYY检测

Misclassification in weakly supervised object detection

Z Wu, Y Xu, J Yang, X Li - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
Weakly supervised object detection (WSOD) aims to train detectors using only image-
category labels. Current methods typically first generate dense class-agnostic proposals and …
Uložit Citovat Počet citací tohoto článku: 5 Související články Všechny verze (počet: 5)
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Weakly-supervised contrastive learning for unsupervised object discovery

Y Lv, J Zhang, N Barnes, Y Dai - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of
objects from the background within a scene without relying on labeled datasets, which …
Uložit Citovat Počet citací tohoto článku: 14 Související články Všechny verze (počet: 7)

Weighted multi-error information entropy based you only look once network for underwater object detection

H Ma, Y Zhang, S Sun, W Zhang, M Fei… - Engineering Applications of …, 2024 - Elsevier
Underwater object detection is considered as one of the most challenging issues in
computer vision. In this paper, a weighted multi-error information entropy based YOLO (You …
Uložit Citovat Počet citací tohoto článku: 9 Související články Všechny verze (počet: 5)

Single-stage oriented object detection via Corona Heatmap and Multi-stage Angle Prediction

B Song, J Li, J Wu, S Xue, J Chang, J Wan - Knowledge-Based Systems, 2024 - Elsevier
Oriented-object detection is a pivotal research subject within computer vision. Nevertheless,
extant-oriented detection methodologies frequently grapple with boundary problems when …
Uložit Citovat Počet citací tohoto článku: 4 Související články Všechny verze (počet: 4)

TGADHead: An efficient and accurate task-guided attention-decoupled head for single-stage object detection

F Zuo, J Liu, Z Chen, M Fu, L Wang - Knowledge-Based Systems, 2024 - Elsevier
In object detection, localization and classification of the targets are two fundamental
subtasks that underpin the application of many knowledge-based intelligent models in …
Uložit Citovat Počet citací tohoto článku: 1 Související články Všechny verze (počet: 2)
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation

Y Du, Z Fu, Q Liu - IEEE Transactions on Image Processing, 2024 - ieeexplore.ieee.org
Recent attention has been devoted to the pursuit of learning semantic segmentation models
exclusively from image tags, a paradigm known as image-level Weakly Supervised …
Uložit Citovat Související články Všechny verze (počet: 6)

HDNet: Human-like discrimination with visual key for few-shot cross-domain object detection

M Liu, X Di, W Wang - Knowledge-Based Systems, 2024 - Elsevier
Most existing few-shot object detection (FSD) methods implicitly assume that the target
domain data with few samples conform to the same statistical distribution as the source …
Uložit Citovat Související články Všechny verze (počet: 2)