Discovering class-specific pixels for weakly-supervised semantic segmentation

Discovering class-specific pixels for weakly-supervised semantic segmentation

We propose an approach to discover class-speciﬁc pixels for the weakly-supervised semantic segmentation task. We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of signiﬁcantly boosting the performance. First, we propose a simple yet powerful hierar...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Chaudhry, A, Dokania, PK, Torr, PHS
Format:	Conference item
Sprog:	English
Udgivet:	British Machine Vision Association 2017

Lignende værker

Bottom-up top-down cues for weakly-supervised semantic segmentation
af: Hou, Q, et al.
Udgivet: (2018)

Addressing Noisy Pixels in Weakly Supervised Semantic Segmentation with Weights Assigned
af: Feng Qian, et al.
Udgivet: (2024-08-01)

Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation
af: Yeong Woo Kim, et al.
Udgivet: (2024-01-01)

RSS-Net: weakly-supervised multi-class semantic segmentation with FMCW radar
af: Kaul, P, et al.
Udgivet: (2021)

Continual learning in low-rank orthogonal subspaces
af: Chaudhry, A, et al.
Udgivet: (2020)

Weakly- and semi-supervised panoptic segmentation
af: Li, Q, et al.
Udgivet: (2018)

Box2Seg: Attention weighted loss and discriminative feature learning for weakly supervised segmentation
af: Kulharia, V, et al.
Udgivet: (2020)

Rethinking CAM in Weakly-Supervised Semantic Segmentation
af: Yuqi Song, et al.
Udgivet: (2022-01-01)

Reliable Label-Supervised Pixel Attention Mechanism for Weakly Supervised Building Segmentation in UAV Imagery
af: Jun Chen, et al.
Udgivet: (2022-07-01)

Extracting Structured Supervision From Captions for Weakly Supervised Semantic Segmentation
af: Daniel R. Vilar, et al.
Udgivet: (2021-01-01)

Polarized Attention Weak Supervised Semantic Segmentation Network
af: Min Dai, et al.
Udgivet: (2024-01-01)

WAILS: Watershed Algorithm With Image-Level Supervision for Weakly Supervised Semantic Segmentation
af: Hongming Zhou, et al.
Udgivet: (2019-01-01)

Placing objects in context via inpainting for out-of-distribution segmentation
af: De Jorge, P, et al.
Udgivet: (2024)

GDumb: A simple approach that questions our progress in continual learning
af: Prabhu, A, et al.
Udgivet: (2020)

Learning class-specific edges for object detection and segmentation
af: Prasad, M, et al.
Udgivet: (2006)

Non-target feature filtering for weakly supervised semantic segmentation
af: Xuesheng Zhou, et al.
Udgivet: (2024-12-01)

Learning graph structures with transformer for weakly supervised semantic segmentation
af: Wanchun Sun, et al.
Udgivet: (2023-07-01)

Scale-Aware Feature Network for Weakly Supervised Semantic Segmentation
af: Lian Xu, et al.
Udgivet: (2020-01-01)

Mixed-UNet: Refined class activation mapping for weakly-supervised semantic segmentation with multi-scale inference
af: Yang Liu, et al.
Udgivet: (2022-11-01)

On the robustness of semantic segmentation models to adversarial attacks
af: Arnab, A, et al.
Udgivet: (2019)

Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions
af: Xinying Xu, et al.
Udgivet: (2019-01-01)

Weakly Supervised Semantic Segmentation in Aerial Imagery via Cross-Image Semantic Mining
af: Ruixue Zhou, et al.
Udgivet: (2023-02-01)

Semantic-aware auto-encoders for self-supervised representation learning
af: Wang, G, et al.
Udgivet: (2022)

Weakly supervised semantic segmentation for MRI: exploring the advantages and disadvantages of class activation maps for biological image segmentation with soft boundaries
af: Shaheen Syed, et al.
Udgivet: (2023-02-01)

Affinity attention graph neural network for weakly supervised semantic segmentation
af: Zhang, B, et al.
Udgivet: (2021)

Semantic segmentation of point clouds of ancient buildings based on weak supervision
af: Jianghong Zhao, et al.
Udgivet: (2024-07-01)

Weakly-Supervised Image Semantic Segmentation Based on Superpixel Region Merging
af: Quanchun Jiang, et al.
Udgivet: (2019-06-01)

Scalable cascade inference for semantic image segmentation
af: Sturgess, P, et al.
Udgivet: (2012)

Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR Images
af: Kai Wang, et al.
Udgivet: (2025-01-01)

A survey on weakly supervised 3D point cloud semantic segmentation
af: Jingyi Wang, et al.
Udgivet: (2024-04-01)

Activation extending based on long-range dependencies for weakly supervised semantic segmentation.
af: Haipeng Liu, et al.
Udgivet: (2023-01-01)

Activation extending based on long-range dependencies for weakly supervised semantic segmentation
af: Haipeng Liu, et al.
Udgivet: (2023-01-01)

Weakly Supervised Building Semantic Segmentation Based on Spot-Seeds and Refinement Process
af: Khaled Moghalles, et al.
Udgivet: (2022-05-01)

Weakly Supervised Conditional Random Fields Model for Semantic Segmentation with Image Patches
af: Xinying Xu, et al.
Udgivet: (2020-03-01)

EXPLORING LABEL INITIALIZATION FOR WEAKLY SUPERVISED ALS POINT CLOUD SEMANTIC SEGMENTATION
af: P. Wang, et al.
Udgivet: (2022-05-01)

Saliency Guided Self-Attention Network for Weakly and Semi-Supervised Semantic Segmentation
af: Qi Yao, et al.
Udgivet: (2020-01-01)

Weakly-Supervised Learning of a Deep Convolutional Neural Networks for Semantic Segmentation
af: Yanqing Feng, et al.
Udgivet: (2019-01-01)

Class-Wise Adaptive Strategy for Semi Supervised Semantic Segmentation
af: Jingi Ju, et al.
Udgivet: (2024-01-01)

Deep FusionNet for point cloud semantic segmentation
af: Zhang, F, et al.
Udgivet: (2020)

Erroneous pixel prediction for semantic image segmentation
af: Lixue Gong, et al.
Udgivet: (2021-10-01)