Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
Ranked #3 on
Video Semantic Segmentation
on Cityscapes val
LESION SEGMENTATION REAL-TIME SEMANTIC SEGMENTATION SCENE PARSING VIDEO SEMANTIC SEGMENTATION
Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.
Ranked #3 on
Human Part Segmentation
on PASCAL-Part
IMAGE CLASSIFICATION META-LEARNING SEMANTIC SEGMENTATION STREET SCENE PARSING
Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision.
A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation.
OPTICAL FLOW ESTIMATION REAL-TIME SEMANTIC SEGMENTATION SCENE PARSING
To capture richer context information, we further combine our interlaced sparse self-attention scheme with the conventional multi-scale context schemes including pyramid pooling~\citep{zhao2017pyramid} and atrous spatial pyramid pooling~\citep{chen2018deeplab}.
Ranked #20 on
Semantic Segmentation
on Cityscapes test
We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes.
Ranked #20 on
Semantic Segmentation
on ADE20K val
Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications.
This mental model captures geometric and semantic aspects of the scene, describes the environment at multiple levels of abstractions (e. g., objects, rooms, buildings), includes static and dynamic entities and their relations (e. g., a person is in a room at a given time).
3D RECONSTRUCTION OBJECT LOCALIZATION SCENE PARSING VISUAL LOCALIZATION
We further propose to distill the structured knowledge from cumbersome networks into compact networks, which is motivated by the fact that semantic segmentation is a structured prediction problem.
IMAGE CLASSIFICATION KNOWLEDGE DISTILLATION SCENE PARSING SEMANTIC SEGMENTATION STRUCTURED PREDICTION
Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem.
DEPTH ESTIMATION IMAGE CLASSIFICATION KNOWLEDGE DISTILLATION OBJECT DETECTION SCENE PARSING SEMANTIC SEGMENTATION STRUCTURED PREDICTION