Learning Dense Convolutional Embeddings for Semantic Segmentation
원문 초록
This paper proposes a new deep convolutional neural network (DCNN) architecture that learns pixel embeddings, such that pairwise distances between the embeddings can be used to infer whether or not the pixels lie on the same region. That is, for any two pixels on the same object, the embeddings are trained to be similar; for any pair that straddles an object boundary, the embeddings are trained to be dissimilar. Experimental results show that when this embedding network is used in conjunction with a DCNN trained on semantic segmentation, there is a systematic improvement in per-pixel classification accuracy. Our contributions are integrated in the popular Caffe deep learning framework, and consist in straightforward modifications to convolution routines. As such, they can be exploited for any task involving convolution layers.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks
Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation
FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation
MACD R-CNN: An Abnormal Cell Nucleus Detection Method
토론
이 논문과 연결된 포럼 글이 아직 없습니다.