Few-Shot Semantic Segmentation with Prototype Learning

By Nanqing Dong, Eric P. Xing. 2018

565 citations recorded by the source corpus.

How researchers see this paper

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

1. Yi Yang
2. Luc Van Gool
3. Yunchao Wei
4. Wenguan Wang
5. Trevor Darrell
6. Bernt Schiele
7. Dacheng Tao
8. X. Wang

Citations in the corpus

• Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations (2021, methodology): “Prototypes-based regularizing terms gained a great interest and, in particular, have been largely used in the literature of few-shot learning [15, 63, 60], to learn prototypical representations of each category, and domain adaptation, to enforce orthogonality [50, 65] or centroid matching [70, 12].”
• GroupViT: Semantic Segmentation Emerges from Text Supervision (2022, methodology): “For example, few-shot learning [21, 43, 50, 55, 70, 77, 84] and active learning [8, 62, 66, 67, 83] are proposed to perform segmentation with as few pixel-wise labels as possible.”
• Prototype-based Incremental Few-Shot Segmentation (2020, methodology): “Few-shot Learning approaches can be split in two groups: optimization-based [12, 32, 37, 41] and metric-learning [6, 8, 15, 35, 43, 44, 45, 48, 49].”
• Feature Weighting and Boosting for Few-Shot Segmentation (2019, methodology): “For PASCAL-5, we use the same 4-fold cross-validation setup as prior work [26, 20, 6].”
• A Few Guidelines for Incremental Few-Shot Segmentation (2020, methodology): “As in previous few-shot segmentation works [38, 9, 41], we use the simplest strategy to extract class prototypes from multiple pixels, i.”
• Part-aware Prototype Network for Few-shot Semantic Segmentation (2020, background): “matching and specic decoding networks to generate segmentation, and hence it is non-trivial or computationally expensive to generalize to the multi-way setting. Second, other prototype-based methods [7,27,33] typically use a holistic representation for each semantic class, which is dicult to cope wi”
• Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation (2019, methodology): “…the weights between the query nodes and all support nodes, we can extend our model to Model IoU co-FCN [15] 60.1 Reduced-DFCN8s [19] 60.9 PL [3] 61.2 A-MCG-Conv-LSTM [9] 61.2 OSLSM [18] 61.3 SG-One [27] 63.1 CANet [26] 66.2 Ours 69.9 Table 7: Comparison with the state-of-the-art 1-shot…”
• 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].”
• SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation (2018, methodology): “We also test the proposed model regarding the evaluation method in co-FCN [17] and PL+SEG [7].”
• 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 Masked Weight Imprinting for Few-Shot Segmentation (2019, methodology): “Quantitative results for 1-way 1-shot and 5-shot segmentation on PASCAL-5 i dataset following evaluation in (Dong & Xing, 2018).”
• Prototype Mixture Models for Few-shot Semantic Segmentation (2020, methodology): “[16] contributed early few-shot semantic segmentation methods.”
• Few-Shot Semantic Segmentation with Democratic Attention Networks (2020, methodology): “Inspired by this, few-shot semantic segmentation has recently received growing interest in the computer vision community [4, 28, 39].”
• Progressive One-shot Human Parsing (2020, unknown): “Note that in the prior methods (Dong and Xing 2018) that a ‘background prototype’ is learned to represent non-foreground regions.”
• Few-shot Semantic Image Synthesis Using StyleGAN Prior (2021, unknown): “An alternative approach might be to use few-shot semantic segmentation [9, 35, 20, 33, 34, 39] to annotate unlabeled images to train image-to-image translation models.”
• Adaptive Prototype Learning and Allocation for Few-Shot Segmentation (2021, background): “networks [40, 42, 32, 29, 4] merely generate a single prototype by masked average pooling as shown in Figure 1(a), thus losing information as well as discriminability.”
• PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (2019, methodology): “Implementation details We initialize the VGG-16 network with the weights pre-trained on ILSVRC [19] as in previous works [21, 4, 28].”