Selecting high-quality proposals for weakly supervised object detection with bottom-up aggregated attention and phase-aware loss

Z Wu, C Liu, J Wen, Y Xu, J Yang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Weakly supervised object detection (WSOD) has received widespread attention since it
requires only image-category annotations for detector training. Many advanced approaches …

H2fa r-cnn: Holistic and hierarchical feature alignment for cross-domain weakly supervised object detection

Y Xu, Y Sun, Z Yang, J Miao… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Cross-domain weakly supervised object detection (CDWSOD) aims to adapt the detection
model to a novel target domain with easily acquired image-level annotations. How to align …

Multiple instance graph learning for weakly supervised remote sensing object detection

B Wang, Y Zhao, X Li - IEEE Transactions on Geoscience and …, 2021 - ieeexplore.ieee.org
Weakly supervised object detection (WSOD) has recently attracted much attention in the
field of remote sensing, where only image-level labels that distinguish the existence of an …

Cyclic-bootstrap labeling for weakly supervised object detection

Y Yin, J Deng, W Zhou, L Li… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Recent progress in weakly supervised object detection is featured by a combination of
multiple instance detection networks (MIDN) and ordinal online refinement. However, with …

Detecting prohibited objects with physical size constraint from cluttered X-ray baggage images

A Chang, Y Zhang, S Zhang, L Zhong… - Knowledge-Based Systems, 2022 - Elsevier
X-ray baggage image inspection aims to detect prohibited objects. Existing inspection
systems often rely on humans to scrutinize X-ray images. Although several deep-learning …

Learning an invariant and equivariant network for weakly supervised object detection

X Feng, X Yao, H Shen, G Cheng… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Weakly Supervised Object Detection (WSOD) is of increasing importance in the community
of computer vision as its extensive applications and low manual cost. Most of the advanced …

Weakly supervised RGB-D salient object detection with prediction consistency training and active scribble boosting

Y Xu, X Yu, J Zhang, L Zhu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
RGB-D salient object detection (SOD) has attracted increasingly more attention as it shows
more robust results in complex scenes compared with RGB SOD. However, state-of-the-art …

Parameter-efficient person re-identification in the 3d space

Z Zheng, X Wang, N Zheng… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
People live in a 3D world. However, existing works on person re-identification (re-id) mostly
consider the semantic representation learning in a 2D space, intrinsically limiting the …

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

Y Xu, C Zhou, X Yu, Y Yang - IEEE Transactions on Image …, 2023 - ieeexplore.ieee.org
Weakly-supervised object detection (WSOD), which requires only image-level annotations
for training detectors, has gained enormous attention. Despite recent rapid advance in …

Fi-wsod: Foreground information guided weakly supervised object detection

Y Yin, J Deng, W Zhou, L Li, H Li - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Existing solutions for weakly supervised object detection (WSOD) generally follow the
multiple instance learning (MIL) paradigm to formulate WSOD as a multi-class classification …