Channel Importance Matters in Few-Shot Image Classification

2022-06-16 · Xu Luo, Jing Xu, Zenglin Xu

Few-Shot Learning (FSL) requires vision models to quickly adapt to brand-new classification tasks with a shift in task distribution. Understanding the difficulties posed by this task distribution shift is central to FSL. In this paper, we show that a simple channel-wise feature transformation may be the key to unraveling this secret from a channel perspective. When facing novel few-shot tasks in the test-time datasets, this transformation can greatly improve the generalization ability of learned image representations, while being agnostic to the choice of training algorithms and datasets. Through an in-depth analysis of this transformation, we find that the difficulty of representation transfer in FSL stems from the severe channel bias problem of image representations: channels may have different importance in different tasks, while convolutional neural networks are likely to be insensitive, or respond incorrectly to such a shift. This points out a core problem of the generalization ability of modern vision systems and needs further attention in the future. Our code is available at https://github.com/Frankluox/Channel_Importance_FSL.

📄 PDF Abstract BibTeX arXiv:2206.08126

Code (1)

Frankluox/Channel_Importance_FSL 공식 구현 pytorch

Tasks

Few-Shot Image Classification Few-Shot Learning image-classification Image Classification

Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification

2023-07-28 · SuBeen Lee, WonJun Moon, Hyun Seok Seong, Jae-Pil Heo

The difficulty of the fine-grained image classification mainly comes from a shared overall appearance across classes. Thus, recognizing discriminative details, such as eyes and beaks for birds, is a key in the task. Howe…

Cross-Domain Few-Shot Fine-Grained Image Classification image-classification Image Classification

L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout

2019-04-08 · Heda Song, Mercedes Torres Torres, Ender Özcan, Isaac Triguero

Few-shot learning focuses on learning a new visual concept with very limited labelled examples. A successful approach to tackle this problem is to compare the similarity between examples in a learned metric space based o…

Few-Shot Learning Meta-Learning

Frequency Guidance Matters in Few-Shot Learning

2023-01-01 · ICCV 2023 1 · Hao Cheng, Siyuan Yang, Joey Tianyi Zhou, Lanqing Guo 외

Few-shot classification aims to learn a discriminative feature representation to recognize unseen classes with few labeled support samples. While most few-shot learning methods focus on exploiting the spatial informa…

Few-Shot Learning Metric Learning Triplet

SAGE: Training-Free Semantic Evidence Composition for Edge-Cloud Inference under Hard Uplink Budgets

2026-04-21 · Inhyeok Choi, Hyuncheol Park arxiv

Edge-cloud hybrid inference offloads difficult inputs to a powerful remote model, but the uplink channel imposes hard per-request constraints on the number of bits that can be transmitted. We show that selecting transmit…

Initialization matters in few-shot adaptation of vision-language models for histopathological image classification

2026-02-21 · Pablo Meseguer, Rocío del Amor, Valery Naranjo arxiv

Vision language models (VLM) pre-trained on datasets of histopathological image-caption pairs enabled zero-shot slide-level classification. The ability of VLM image encoders to extract discriminative features also opens …

Multiple Instance Learning Image Classification Few-Shot Learning Transfer Learning