Explanation-Guided Training for Cross-Domain Few-Shot Classification

Sun, Jiamei; Lapuschkin, Sebastian; Samek, Wojciech; Zhao, Yunqing; Cheung, Ngai-Man; Binder, Alexander

doi:10.1109/icpr48806.2021.9412941

Cited by 40 publications

(30 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model-aware approaches [16], [17], [18], [19], [20], [21], [22], [23], [24], [25], [12], [26], on the other hand, take the internal structure of the model into account and therefore tend to yield more precise model based explanations. For example, LRP [2], a model-aware post-hoc XAI approach, has been widely used to explain the decisions of various deep neural networks, such as convolutional neural networks, recurrent neural networks and graph neural networks [27]. Because of its importance in general, and to this paper in particular, we briefly describe the basic idea of LRP.…”

Section: A Explainability Methodsmentioning

confidence: 99%

This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation

Gautam¹,

Höhne²,

Hansen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the understanding and traceability of the underlying decisionmaking strategies. As a remedy, many post-hoc explanation and self-explanatory methods have been developed to interpret the models' behavior. These methods, in addition, enable the identification of artifacts that can be learned by the model as class-relevant features. In this work, we provide a detailed case study of the self-explaining network, ProtoPNet, in the presence of a spectrum of artifacts. Accordingly, we identify the main drawbacks of ProtoPNet, especially, its coarse and spatially imprecise explanations. We address these limitations by introducing Prototypical Relevance Propagation (PRP), a novel method for generating more precise model-aware explanations. Furthermore, in order to obtain a clean dataset, we propose to use multi-view clustering strategies for segregating the artifact images using the PRP explanations, thereby suppressing the potential artifact learning in the models.

show abstract

Section: A Explainability Methodsmentioning

confidence: 99%

This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation

Gautam¹,

Höhne²,

Hansen³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on this, FRN [84] explores the potential space for few-shot image classification, using ridge regression to reconstruct and normalize the feature map without adding new learning parameters. FWT [85] utilizes only the source data for the affine transformation of features, as do LRP-GNN [86] and SBMTL [87]. FD-MIXUP [88] constructs auxiliary datasets by mixup and uses encoders to learn domain-irrelevant features to guide the network generalization to other tasks.…”

Section: Cross-domain Few-shot Learningmentioning

confidence: 99%

A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities

Song¹,

Wang²,

Mondal³

et al. 2022

Preprint

View full text Add to dashboard Cite

Few-shot learning (FSL) has emerged as an effective learning method and shows great potential. Despite the recent creative works in tackling FSL tasks, learning valid information rapidly from just a few or even zero samples still remains a serious challenge. In this context, we extensively investigated 200+ latest papers on FSL published in the past three years, aiming to present a timely and comprehensive overview of the most recent advances in FSL along with impartial comparisons of strengths and weaknesses of the existing works. For the sake of avoiding conceptual confusion, we first elaborate and compare a set of similar concepts including few-shot learning, transfer learning, and meta-learning. Furthermore, we propose a novel taxonomy to classify the existing work according to the level of abstraction of knowledge in accordance with the challenges of FSL. To enrich this survey, in each subsection we provide in-depth analysis and insightful discussion about recent advances on these topics. Moreover, taking computer vision as an example, we highlight the important application of FSL, covering various research hotspots. Finally, we conclude the survey with unique insights into the technology evolution trends together with potential future research opportunities in the hope of providing guidance to follow-up research.

show abstract

“…Few-shot image generation. Conventional few-shot learning [24][25][26] aims at learning a discriminative classifier for classification [27][28][29][30], segmentation [31,32] or detection [33][34][35] tasks. Differently, few-shot image generation (FSIG) [14,18,19] aims at learning a generator for new and diverse samples given extremely limited samples (e.g., 10 shots).…”

Section: Related Workmentioning

confidence: 99%

Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Zhao¹,

Keshigeyan²,

Abdollahzadeh³

et al. 2022

Preprint

View full text Add to dashboard Cite

Few-shot image generation (FSIG) aims to learn to generate new and diverse samples given an extremely limited number of samples from a domain, e.g., 10 training samples. Recent work has addressed the problem using transfer learning approach, leveraging a GAN pretrained on a large-scale source domain dataset and adapting that model to the target domain based on very limited target domain samples. Central to recent FSIG methods are knowledge preserving criteria, which aim to select a subset of source model's knowledge to be preserved into the adapted model. However, a major limitation of existing methods is that their knowledge preserving criteria consider only source domain/source task, and they fail to consider target domain/adaptation task in selecting source model's knowledge, casting doubt on their suitability for setups of different proximity between source and target domain.Our work makes two contributions. As our first contribution, we revisit recent FSIG works and their experiments. Our important finding is that, under setups which assumption of close proximity between source and target domains is relaxed, existing state-of-the-art (SOTA) methods which consider only source domain in knowledge preserving perform no better than a baseline fine-tuning method. To address the limitation of existing methods, as our second contribution, we propose Adaptation-Aware kernel Modulation (AdAM) to address general FSIG of different source-target domain proximity. Extensive experimental results show that the proposed method consistently achieves SOTA performance across source/target domains of different proximity, including challenging setups when source and target domains are more apart. Project Page: https://yunqing-me.github.io/AdAM/ * Equal Contribution : Corresponding Author Preprint. Under review.

show abstract

Explanation-Guided Training for Cross-Domain Few-Shot Classification

Cited by 40 publications

References 23 publications

This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation

This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation

A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities

Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Contact Info

Product

Resources

About