Conditional Networks for Few-Shot Semantic Segmentation

By Kate Rakelly, Evan Shelhamer, Trevor Darrell, Alexei A. Efros, Sergey Levine. 2018

241 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Meta & Continual Learning

Citations in the corpus

Language-driven Semantic Segmentation (2022, methodology): “Few-shot approaches (Shaban et al., 2017; Rakelly et al., 2018; Siam et al., 2019; Wang et al., 2019; Zhang et al., 2019; Nguyen & Todorovic, 2019; Liu et al., 2020b; Wang et al., 2020; Tian et al., 2020; Boudiaf et al., 2021; Min et al., 2021) offer ways to learn to segment novel classes based on…”
Few-Shot Semantic Segmentation with Democratic Attention Networks (2020, methodology): “In contrast, FB-IoU [25] ignores the difference among the object categories and regards all the categories as foreground class, and then averages the IoU of foreground and background over all test images.”
Hypercorrelation Squeeze for Few-Shot Segmenation (2021, background): “However, given only a few annotated training examples, the problem of poor generalization ability of the deep networks is yet the primary concern that many few-shot segmentation methods [10, 12, 13, 19, 33, 36, 37, 46, 54, 61, 63, 69, 70, 74, 75, 80, 83, 86, 87, 89] struggle to address.”
Progressive One-shot Human Parsing (2020, unknown): “…2015; Finn, Abbeel, and Levine 2017; Snell, Swersky, and Zemel 2017; Sung et al. 2018; Chen et al. 2020; Liu et al. 2020a; Tian et al. 2020b), a typical OS3 solution is to learn a good metric (Zhang et al. 2018; Kate et al. 2018; Zhang et al. 2019b,a; Hu et al. 2019; Tian et al. 2020a).”
Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need? (2020, background): “Early frameworks followed a dual-branch architecture, with two independent branches [29, 7, 25], one generating the prototypes from the support images and the other segmenting the query images with the learned prototypes.”
Adaptive Prototype Learning and Allocation for Few-Shot Segmentation (2021, methodology): “To explore the effect of different fusion methods, we compare our k-shot setting with two other commonly used solutions: 1) feature average fusion [21] and 2) attention weighted summation [40].”
Prior Guided Feature Enrichment Network for Few-Shot Segmentation (2020, unknown): “7M co-FCN2018 [29] 36.”
Zero-Shot Semantic Segmentation via Variational Mapping (2019, methodology): “There is no overlap between the seen classes in the training set and the unseen classes in the test set. tion [26, 23, 7, 13].”
Semantic Projection Network for Zero- and Few-Label Semantic Segmentation (2019, methodology): “For few-shot semantic segmentation, previous approaches [42, 37, 11, 56] follow the meta-learning setup [46, 44], which uses a support set to predict an query image.”
Few-Shot Semantic Segmentation with Prototype Learning (2018, methodology): “Following [26, 31], we adopt two-branched architecture.”
PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (2019, methodology): “We also compare our PANet with two baseline models FG-BG and fine-tuning from [16].”
Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation (2019, methodology): “The second evaluation metric is the one proposed in [15].”
Part-aware Prototype Network for Few-shot Semantic Segmentation (2020, methodology): “old with each run containing 1000 tasks. Baseline: We adopt ResNet-50 [12] as feature extractor in PANet [33] to be our baseline model, denoted as PANet*. Evaluation Metrics: Following previous works [3,37,22,33,35], mean-IoU and binary-IoU are adopted for model evaluation. Mean-IoU measures the ave”
One-shot Texture Segmentation (2018, background): “One-Shot Learning While the corpus of work on one-shot learning is quite extensive [20, 19, 43, 38, 40, 37, 32, 39], more complex tasks like one-shot segmentation [3, 17] have been established only recently.”
Adaptive Masked Weight Imprinting for Few-Shot Segmentation (2019, methodology): “(Rakelly et al., 2018) proposed another 2-branch method where the second branch acts as a conditioning branch instead.”
AMP: Adaptive Masked Proxies for Few-Shot Segmentation (2019, methodology): “1-NN [28] Siamese [28] FT [28] OSLSM [28] co-FCN [25] AMP-1 (ours) AMP-2 (ours)”
FGN: Fully Guided Network for Few-Shot Instance Segmentation (2020, background): “The majority of existing FSL models focus on visual classiﬁcation, and a minority on semantic segmentation [32, 22, 26, 5].”
CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning (2019, methodology): “While in [24, 5], they ignore the image categories and calculate the mean of foreground IoU and background IoU over all test images (FB-IoU).”