Semantic Segmentation

Semantic segmentation, the task of assigning a semantic label to each pixel in an image, aims to achieve precise pixel-level scene understanding. Current research emphasizes improving accuracy and efficiency across diverse data modalities (RGB, depth, lidar, hyperspectral, and time series) and challenging conditions (low light, adverse weather, imbalanced datasets), often employing advanced architectures like transformers and diffusion models alongside innovative loss functions and training strategies. This field is crucial for numerous applications, including autonomous driving, medical image analysis, remote sensing, and robotics, driving advancements in both model robustness and interpretability.

Papers

February 20, 2024

Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model
Claudia Cuttano, Antonio Tavera, Fabio Cermelli, Giuseppe Averta, Barbara Caputo
Semantic Segmentation Unsupervised Domain Adaptation Black Box Pseudo Labeling Semantic Segmentation Model Domain Transfer Lightweight Segmentation

February 19, 2024

Towards Explainable LiDAR Point Cloud Semantic Segmentation via Gradient Based Target Localization
Abhishek Kuriyal, Vaibhav Kumar
Semantic Segmentation LiDAR Point Cloud Saliency Map Lidar Semantic Segmentation Point Cloud Semantic Segmentation Gradient Tracking

February 18, 2024

Key Patch Proposer: Key Patches Contain Rich Information
Jing Xu, Beiwen Tian, Hao Zhao
Semantic Segmentation Active Learning

February 17, 2024

A Decoding Scheme with Successive Aggregation of Multi-Level Features for Light-Weight Semantic Segmentation
Jiwon Yoo, Jangwon Lee, Gyeonghwan Kim
Semantic Segmentation Semantic Segmentation Model Hierarchical Vision Transformer Multi Level Feature Lightweight Semantic Segmentation Numerical Aggregation

February 16, 2024

February 14, 2024

Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion
Edgar Heinert, Matthias Rottmann, Kira Maag, Karsten Kahl
Convolutional Neural Network Deep Neural Network Semantic Segmentation Texture Bias

February 9, 2024

February 8, 2024

February 7, 2024

Multi-Scale Semantic Segmentation with Modified MBConv Blocks
Xi Chen, Yang Cai, Yuan Wu, Bo Xiong, Taesung Park
Semantic Segmentation Multi Scale Segmentation Capability ConvBN Block

February 6, 2024

Energy-based Domain-Adaptive Segmentation with Depth Guidance
Jinjing Zhu, Zhedong Hu, Tae-Kyun Kim, Lin Wang
Semantic Segmentation Feature Fusion Self Supervised Depth Poor Segmentation Depth Cue Domain Adaptive Segmentation

February 4, 2024

February 3, 2024

Multi-Level Aggregation and Recursive Alignment Architecture for Efficient Parallel Inference Segmentation Network
Yanhua Zhang, Ke Zhang, Jingyu Wang, Yulin Wu, Wuwei Wang
Semantic Segmentation Efficient Segmentation Dual Path Spatial Alignment Level Aggregation Parallel Inference

February 2, 2024

Semantic Segmentation

Papers

Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model

Towards Explainable LiDAR Point Cloud Semantic Segmentation via Gradient Based Target Localization

Key Patch Proposer: Key Patches Contain Rich Information

A Decoding Scheme with Successive Aggregation of Multi-Level Features for Light-Weight Semantic Segmentation

Selective Prediction for Semantic Segmentation using Post-Hoc Confidence Estimation and Its Performance under Distribution Shift

Efficient Multi-task Uncertainties for Joint Semantic Segmentation and Monocular Depth Estimation

Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion

More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation

Hybridnet for depth estimation and semantic segmentation

ControlUDA: Controllable Diffusion-assisted Unsupervised Domain Adaptation for Cross-Weather Semantic Segmentation

Early Fusion of Features for Semantic Segmentation

Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery

On the Effect of Image Resolution on Semantic Segmentation

Multi-Scale Semantic Segmentation with Modified MBConv Blocks

Energy-based Domain-Adaptive Segmentation with Depth Guidance

Exploring Intrinsic Properties of Medical Images for Self-Supervised Binary Semantic Segmentation

Region-Based Representations Revisited

Multi-Level Aggregation and Recursive Alignment Architecture for Efficient Parallel Inference Segmentation Network

Delving into Decision-based Black-box Attacks on Semantic Segmentation

Scale Equalization for Multi-Level Feature Fusion