On Feature Normalization and Data Augmentation
- URL: http://arxiv.org/abs/2002.11102v3
- Date: Tue, 30 Mar 2021 18:00:00 GMT
- Title: On Feature Normalization and Data Augmentation
- Authors: Boyi Li and Felix Wu and Ser-Nam Lim and Serge Belongie and Kilian Q.
Weinberger
- Abstract summary: Moment Exchange encourages the model to utilize the moment information also for recognition models.
We replace the moments of the learned features of one training image by those of another, and also interpolate the target labels.
As our approach is fast, operates entirely in feature space, and mixes different signals than prior methods, one can effectively combine it with existing augmentation approaches.
- Score: 55.115583969831
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The moments (a.k.a., mean and standard deviation) of latent features are
often removed as noise when training image recognition models, to increase
stability and reduce training time. However, in the field of image generation,
the moments play a much more central role. Studies have shown that the moments
extracted from instance normalization and positional normalization can roughly
capture style and shape information of an image. Instead of being discarded,
these moments are instrumental to the generation process. In this paper we
propose Moment Exchange, an implicit data augmentation method that encourages
the model to utilize the moment information also for recognition models.
Specifically, we replace the moments of the learned features of one training
image by those of another, and also interpolate the target labels -- forcing
the model to extract training signal from the moments in addition to the
normalized features. As our approach is fast, operates entirely in feature
space, and mixes different signals than prior methods, one can effectively
combine it with existing augmentation approaches. We demonstrate its efficacy
across several recognition benchmark data sets where it improves the
generalization capability of highly competitive baseline networks with
remarkable consistency.
Related papers
- CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning [62.69917996026769]
A class-incremental learning task requires learning and preserving both spatial appearance and temporal action involvement.
We propose a framework that equips separate adapters to learn new class patterns, accommodating the incremental information requirements unique to each class.
A causal compensation mechanism is proposed to reduce the conflicts during increment and memorization for between different types of information.
arXiv Detail & Related papers (2025-01-13T11:34:55Z) - Time Step Generating: A Universal Synthesized Deepfake Image Detector [0.4488895231267077]
We propose a universal synthetic image detector Time Step Generating (TSG)
TSG does not rely on pre-trained models' reconstructing ability, specific datasets, or sampling algorithms.
We test the proposed TSG on the large-scale GenImage benchmark and it achieves significant improvements in both accuracy and generalizability.
arXiv Detail & Related papers (2024-11-17T09:39:50Z) - Enhancing Fine-Grained Visual Recognition in the Low-Data Regime Through Feature Magnitude Regularization [23.78498670529746]
We introduce a regularization technique to ensure that the magnitudes of the extracted features are evenly distributed.
Despite its apparent simplicity, our approach has demonstrated significant performance improvements across various fine-grained visual recognition datasets.
arXiv Detail & Related papers (2024-09-03T07:32:46Z) - Boosting Unconstrained Face Recognition with Targeted Style Adversary [10.428185253933004]
We present a simple yet effective method to expand the training data by interpolating between instance-level feature statistics across labeled and unlabeled sets.
Our method, dubbed Targeted Style Adversary (TSA), is motivated by two observations: (i) the input domain is reflected in feature statistics, and (ii) face recognition model performance is influenced by style information.
arXiv Detail & Related papers (2024-08-14T16:13:03Z) - Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination [13.238373528922194]
We propose a novel technique for post-processing Consistency-based generated images, enhancing their perceptual quality.
Our approach utilizes a joint classifier-discriminator model, in which both portions are trained adversarially.
By employing example-specific projected gradient under the guidance of this joint machine, we refine synthesized images and achieve an improved FID scores on the ImageNet 64x64 dataset.
arXiv Detail & Related papers (2024-05-25T14:53:52Z) - EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training [79.96741042766524]
We reformulate the training curriculum as a soft-selection function.
We show that exposing the contents of natural images can be readily achieved by the intensity of data augmentation.
The resulting method, EfficientTrain++, is simple, general, yet surprisingly effective.
arXiv Detail & Related papers (2024-05-14T17:00:43Z) - Combating Missing Modalities in Egocentric Videos at Test Time [92.38662956154256]
Real-world applications often face challenges with incomplete modalities due to privacy concerns, efficiency needs, or hardware issues.
We propose a novel approach to address this issue at test time without requiring retraining.
MiDl represents the first self-supervised, online solution for handling missing modalities exclusively at test time.
arXiv Detail & Related papers (2024-04-23T16:01:33Z) - Training on Thin Air: Improve Image Classification with Generated Data [28.96941414724037]
Diffusion Inversion is a simple yet effective method to generate diverse, high-quality training data for image classification.
Our approach captures the original data distribution and ensures data coverage by inverting images to the latent space of Stable Diffusion.
We identify three key components that allow our generated images to successfully supplant the original dataset.
arXiv Detail & Related papers (2023-05-24T16:33:02Z) - Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms.
Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
arXiv Detail & Related papers (2021-11-27T12:12:57Z) - Encoding Robustness to Image Style via Adversarial Feature Perturbations [72.81911076841408]
We adapt adversarial training by directly perturbing feature statistics, rather than image pixels, to produce robust models.
Our proposed method, Adversarial Batch Normalization (AdvBN), is a single network layer that generates worst-case feature perturbations during training.
arXiv Detail & Related papers (2020-09-18T17:52:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.