Related references
Note: Only part of the references are listed.
Article
Multidisciplinary Sciences
Xian Sun et al.
Summary: This study proposes an effective and low-cost method for detecting dumpsites using deep convolutional networks applied to satellite images. Compared with manual methods, the new method saves more than 96.8% of the investigation time while maintaining strong sensitivity to dumpsites. The approach allows for the timely and cost-efficient detection of dumpsites, which is crucial for environmental governance in various countries.
NATURE COMMUNICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Chunbo Lang et al.
Summary: This paper proposes a fresh and powerful scheme called BAM to tackle the issue of low generalization capability in most previous works when dealing with hard query samples. The scheme combines an auxiliary branch and a meta learner to identify regions that do not need segmentation and derive accurate segmentation predictions by adaptively integrating the results of the two learners.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Wenhai Wang et al.
Summary: Compared to vision transformers, large-scale models based on convolutional neural networks are still in an early stage. This work introduces a new CNN-based model, InternImage, that utilizes deformable convolution as the core operator to achieve a large effective receptive field and adaptive spatial aggregation. The effectiveness of the model is demonstrated on challenging benchmarks, outperforming current leading CNNs and ViTs.
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2023)
Article
Computer Science, Information Systems
Jiacheng Chen et al.
Summary: This paper presents an adaptive prototype representation method for few-shot semantic segmentation, which constructs complete sample pairs by introducing class-specific and class-agnostic prototypes, effectively enriching feature comparison and achieving an unbiased segmentation model.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Artificial Intelligence
Zhuotao Tian et al.
Summary: This article proposes a Prior Guided Feature Enrichment Network (PFENet) to address the challenges of reduced generalization ability on unseen classes and spatial inconsistency between query and support targets in few-shot segmentation. PFENet includes a training-free prior mask generation method and a Feature Enrichment Module (FEM). Experimental results demonstrate that PFENet significantly improves the baseline method and achieves outstanding performance even without labeled support samples.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Chunbo Lang et al.
Summary: This paper proposes a novel approach to address the bias issue in few-shot segmentation, where models are biased towards seen classes. By introducing an additional branch to explicitly identify the targets of base classes and integrating the results from two learners, the proposed method achieves significant performance improvements on different datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Wenjian Wang et al.
Summary: This paper proposes a challenging cross-domain few-shot semantic segmentation task and addresses the domain shift problem in few-shot learning by introducing a meta-memory bank and a contrastive learning strategy.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuanwei Liu et al.
Summary: This study proposes a Non-Target Region Eliminating (NTRE) network framework to explicitly mine and eliminate background and distracting object regions in the query. The proposed framework effectively distinguishes the target object from distracting objects, and experimental results demonstrate its effectiveness.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Article
Computer Science, Artificial Intelligence
Guangyu Gao et al.
Summary: DRNet proposes a Double Recalibration Network with two recalibration modules to enhance model robustness against intra-class variance. The method can more accurately mine target regions for query images.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhonghua Wu et al.
Summary: This study introduces the concept of meta-class and proposes a novel MM-Net method for explicitly learning meta-class representations in few-shot semantic segmentation tasks. Experimental results on PASCAL-5i and COCO datasets show state-of-the-art performance of the proposed method.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Juhong Min et al.
Summary: The paper introduces a model called HSNet, which utilizes multi-level feature correlation and efficient 4D convolutions to achieve semantic segmentation with few-shot learning.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhihe Lu et al.
Summary: A few-shot semantic segmentation model typically consists of a CNN encoder, a CNN decoder, and a simple classifier. This study proposes to simplify the meta-learning task by focusing solely on the classifier while leaving the encoder and decoder to pre-training. Introducing a Classifier Weight Transformer (CWT) for classifier meta-learning, the method outperforms existing alternatives on standard benchmarks.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Lihe Yang et al.
Summary: This research introduces a novel joint training framework that effectively addresses the issue of feature undermining in Few-shot segmentation tasks, improving feature embedding and achieving more stable prototypes through mining sub-clusters and rectification techniques on both background and foreground categories. Additionally, the transferable sub-clusters have the capability to leverage extra unlabeled data for further feature enhancement.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Bingfeng Zhang et al.
Summary: This paper proposes a simple yet effective self-guided learning approach to mine lost discriminative information for few-shot segmentation. By making initial predictions for annotated support images, better segmentation performance can be achieved on query images. The introduction of a cross-guided module enhances the final prediction in multiple shot segmentation without re-training.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Haoxin Chen et al.
Summary: This paper introduces a novel Domain Agent Network (DAN) for Few-Shot Video Object Segmentation (FSVOS) task, breaking down full-rank attention into two smaller ones to improve performance. By considering one single frame of the query video as the domain agent, DAN effectively bridges between support images and query videos, while a learning strategy combining meta-learning with online learning further enhances segmentation accuracy, achieving state-of-the-art performance on both computational cost and accuracy.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Binghao Liu et al.
Summary: This paper reformulates few-shot segmentation as a semantic reconstruction problem, converting base class features into basis vectors and introducing contrastive loss to maximize the orthogonality of basis vectors while minimizing semantic aliasing between classes. The proposed approach, anti-aliasing semantic reconstruction (ASR), provides a systematic yet interpretable solution for few-shot learning problems and achieves strong results compared with prior works in experiments on PASCAL VOC and MS COCO datasets.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Automation & Control Systems
Xiaolin Zhang et al.
IEEE TRANSACTIONS ON CYBERNETICS
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Mennatullah Siam et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Kaixin Wang et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Zitian Chen et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Muhammad Abdullah Jamal et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Computer Science, Artificial Intelligence
Liang-Chieh Chen et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Computer Science, Artificial Intelligence
Vijay Badrinarayanan et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Gao Huang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Bharath Hariharan et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Article
Computer Science, Artificial Intelligence
Olga Russakovsky et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2015)