Image Deformation Meta-Networks for One-Shot Learning

Chen, Zitian; Fu, Yanwei; Wang, Yu-Xiong; Ma, Lin; Liu, Wei; Hebert, Martial

doi:10.1109/cvpr.2019.00888

Cited by 218 publications

(115 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments in the second block investigate the effect of the concentrator and projector, respectively. Removing each component alone results in a performance decrease (cases i, ii, iii) 3 . The accuracy is inferior (-3.93%, 1-shot case) if we remove the network part of the concentrator, implying that its dimension reduction and spatial downsampling is important to the final comparisons.…”

Section: Shallow Network Verificationmentioning

confidence: 99%

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Eigen

Dodge

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

352

159

View full text Add to dashboard Cite

Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more pragmatic terms, limited-example training situations are common in practice. Recent effective approaches to few-shot learning employ a metric-learning framework to learn a feature similarity comparison between a query (test) example, and the few support (training) examples. However, these approaches treat each support class independently from one another, never looking at the entire task as a whole. Because of this, they are constrained to use a single set of features for all possible test-time tasks, which hinders the ability to distinguish the most relevant dimensions for the task at hand. In this work, we introduce a Category Traversal Module that can be inserted as a plug-and-play module into most metric-learning based few-shot learners. This component traverses across the entire support set at once, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space. Incorporating our module improves performance considerably (5%-10% relative) over baseline systems on both mini-ImageNet and tieredImageNet benchmarks, with overall performance competitive with recent state-of-the-art systems.

show abstract

Section: Shallow Network Verificationmentioning

confidence: 99%

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Eigen

Dodge

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

352

159

View full text Add to dashboard Cite

show abstract

“…At present, the biggest challenge in few-shot learning scenarios is consistently the shortage of training samples, and therefore how to acquire more informative and meaningful labeled data is the core of issue. The hallucination based approaches [40][41][42][43] use a small number of labeled samples to generate more hallucination data, with the goal of achieving a robust and powerful network. Zhang et al [40] pretrained a saliency network to segment foreground and background of available image samples and generated additional data by combining the appropriate foregroundbackground pairs.…”

Section: Related Workmentioning

confidence: 99%

“…The authors utilized these operations to generate more hallucination data for training phase, and thus significantly improved classification performance. Chen et al [42] proposed to relate new concepts to the existing ones in semantic space, and leveraged the relationships to generate new additional samples by interpolating among concepts, further facilitating learning.…”

Section: Related Workmentioning

confidence: 99%

Task-wise attention guided part complementary learning for few-shot image classification

Cheng

Lang

et al. 2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

A general framework to tackle the problem of few-shot learning is meta-learning, which aims to train a well-generalized meta-learner (or backbone network) to learn a base-learner for each future task with small training data. Although a lot of work has produced relatively good results, there are still some challenges for few-shot image classification. First, meta-learning is a learning problem over a collection of tasks and the meta-learner is usually shared among all tasks. To achieve image classification of novel classes in different tasks, it is needed to learn a base-learner for each task. Under the circumstances, how to make the base-learner specialized, and thus respond to different inputs in an extremely task-wise manner for different tasks is a big challenge at present. Second, classification network usually inclines to identify local regions from the most discriminative object parts rather than the whole objects for recognition, thereby resulting in incomplete feature representations. To address the first challenge, we propose a task-wise attention (TWA) module to guide the base-learner to extract task-specific image features. To address the second challenge, under the guidance of TWA, we propose a part complementary learning (PCL) module to extract and fuse the features of multiple complementary parts of target objects, and thus we can obtain more specific and complete information. In addition, the proposed TWA module and PCL module can be embedded into a unified network for end-to-end training. Extensive experiments on two commonly-used benchmark datasets and comparison with state-of-the-art methods demonstrate the effectiveness of our proposed method.

show abstract

“…Most of these works evaluate their algorithms on some small-scale datasets, e.g., miniImageNet with 64 base categories, 16 validation categories, 20 novel categories. Recently, some works (Hariharan and Girshick 2017;Chen et al 2019c;Hui, Chen, and Chen 2019) switch to a more general and practical setting, where the algorithms aim to recognize hundreds of novel concepts with very limited samples given a set of based categories with sufficient training samples. To address this few-shot learning scenario, (Hariharan and Girshick 2017) learn a transformation function to hallucinate additional samples for novel categories.…”

Section: Related Workmentioning

confidence: 99%

Knowledge Graph Transfer Network for Few-Shot Recognition

Chen

Hui

et al. 2020

AAAI

View full text Add to dashboard Cite

Few-shot learning aims to learn novel categories from very few samples given some base categories with sufficient training samples. The main challenge of this task is the novel categories are prone to dominated by color, texture, shape of the object or background context (namely specificity), which are distinct for the given few training samples but not common for the corresponding categories (see Figure 1). Fortunately, we find that transferring information of the correlated based categories can help learn the novel concepts and thus avoid the novel concept being dominated by the specificity. Besides, incorporating semantic correlations among different categories can effectively regularize this information transfer. In this work, we represent the semantic correlations in the form of structured knowledge graph and integrate this graph into deep neural networks to promote few-shot learning by a novel Knowledge Graph Transfer Network (KGTN). Specifically, by initializing each node with the classifier weight of the corresponding category, a propagation mechanism is learned to adaptively propagate node message through the graph to explore node interaction and transfer classifier information of the base categories to those of the novel ones. Extensive experiments on the ImageNet dataset show significant performance improvement compared with current leading competitors. Furthermore, we construct an ImageNet-6K dataset that covers larger scale categories, i.e, 6,000 categories, and experiments on this dataset further demonstrate the effectiveness of our proposed model.

show abstract

Image Deformation Meta-Networks for One-Shot Learning

Cited by 218 publications

References 18 publications

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Task-wise attention guided part complementary learning for few-shot image classification

Knowledge Graph Transfer Network for Few-Shot Recognition

Contact Info

Product

Resources

About