NegCosIC: Negative Cosine Similarity-Invariance- Covariance Regularization for Few-Shot Learning
Few-shot learning continues to pose a challenge as it is inherently difficult for visual recognition models to generalize with limited labeled examples. When the training data is limited, the process of training and fine-tuning the model will be unstable and inefficient due to overfitting. In this p...
Main Authors: | Wei Han Liu, Kian Ming Lim, Thian Song Ong, Chin Poo Lee |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10495027/ |
Similar Items
-
Enhancing Few-Shot Image Classification With Cosine Transformer
by: Quang-Huy Nguyen, et al.
Published: (2023-01-01) -
Memristive Cosine‐Similarity‐Based Few‐Shot Learning with Lifelong Memory Adaptation
by: Houji Zhou, et al.
Published: (2023-02-01) -
Robust Compare Network for Few-Shot Learning
by: Yixin Yang, et al.
Published: (2020-01-01) -
Multi-Similarity Enhancement Network for Few-Shot Segmentation
by: Hao Chen, et al.
Published: (2023-01-01) -
Multilevel Features-Guided Network for Few-Shot Segmentation
by: Chenjing Xin, et al.
Published: (2022-10-01)