The DFDC dataset is the largest public collection of face-swapped videos and supports detectors that generalize to in-the-wild deepfakes.
See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image guided by these attention maps, including attention cropping and attention dropping. The proposed WS-DAN improves the classification accuracy in two folds. In the first stage, images can be seen better since more discriminative parts' features will be extracted. In the second stage, attention regions provide accurate location of object, which ensures our model to look at the object closer and further improve the performance. Comprehensive experiments in common fine-grained visual classification datasets show that our WS-DAN surpasses the state-of-the-art methods, which demonstrates its effectiveness.
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 3roles
method 1polarities
use method 1representative citing papers
Proposes Ratio 1-2 metric for teacher selection in knowledge distillation for fine-grained image recognition, validated across 1000+ experiments showing 18% better selection and up to 17% student accuracy gains.
Large-scale experiments demonstrate that data-aware augmentations applied only during training allow fine-grained image models to reach high accuracy without using discriminative crops at inference, lowering costs.
citing papers explorer
-
The DeepFake Detection Challenge (DFDC) Dataset
The DFDC dataset is the largest public collection of face-swapped videos and supports detectors that generalize to in-the-wild deepfakes.
-
How to Choose Your Teacher for Fine Grained Image Recognition
Proposes Ratio 1-2 metric for teacher selection in knowledge distillation for fine-grained image recognition, validated across 1000+ experiments showing 18% better selection and up to 17% student accuracy gains.
-
A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition
Large-scale experiments demonstrate that data-aware augmentations applied only during training allow fine-grained image models to reach high accuracy without using discriminative crops at inference, lowering costs.