One-Shot Segmentation in Clutter

We tackle the problem of one-shot segmentation: finding and segmenting a previously unseen object in a cluttered scene based on a single instruction example. We propose a novel dataset, which we call $\textit{cluttered Omniglot}$... (read more)

PDF Abstract ICML 2018 PDF ICML 2018 Abstract

Datasets


Introduced in the Paper:

Cluttered Omniglot

Mentioned in the Paper:

Omniglot ADE20K
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
One-Shot Segmentation Cluttered Omniglot Siamese-U-Net IoU [32 distractors] 62.4 # 2
IoU [4 distractors] 97.1 # 1
IoU [256 distractors] 38.4 # 2
One-Shot Segmentation Cluttered Omniglot MaskNet IoU [32 distractors] 65.6 # 1
IoU [4 distractors] 95.8 # 2
IoU [256 distractors] 43.7 # 1

Methods used in the Paper


METHOD TYPE
Concatenated Skip Connection
Skip Connections
ReLU
Activation Functions
Max Pooling
Pooling Operations
Convolution
Convolutions
U-Net
Semantic Segmentation Models