CORE: Consistent Representation Learning for Face Forgery Detection

• URL: http://arxiv.org/abs/2206.02749v1
• Date: Mon, 6 Jun 2022 17:15:56 GMT
• Title: CORE: Consistent Representation Learning for Face Forgery Detection
• Authors: Yunsheng Ni, Depu Meng, Changqian Yu, Chengbin Quan, Dongchun Ren, Youjian Zhao
• Abstract summary: Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is a trend to introduce some erasing-based augmentations. We find that these methods indeed attempt to implicitly induce more consistent representations for different augmentations. However, due to the lack of explicit regularization, the consistency between different representations is less satisfactory.
• Score: 11.750814179329343
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is a trend to introduce some erasing-based augmentations. We find that these methods indeed attempt to implicitly induce more consistent representations for different augmentations via assigning the same label for different augmented images. However, due to the lack of explicit regularization, the consistency between different representations is less satisfactory. Therefore, we constrain the consistency of different representations explicitly and propose a simple yet effective framework, COnsistent REpresentation Learning (CORE). Specifically, we first capture the different representations with different augmentations, then regularize the cosine distance of the representations to enhance the consistency. Extensive experiments (in-dataset and cross-dataset) demonstrate that CORE performs favorably against state-of-the-art face forgery detection methods.

Related papers

• Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning [71.14084801851381]
  Change captioning aims to succinctly describe the semantic change between a pair of similar images. Most existing methods directly capture the difference between them, which risk obtaining error-prone difference features. We propose a distractors-immune representation learning network that correlates the corresponding channels of two image representations.
  arXiv  Detail & Related papers  (2024-07-16T13:00:33Z)
• Contrastive Learning of View-Invariant Representations for Facial Expressions Recognition [27.75143621836449]
  We propose ViewFX, a novel view-invariant FER framework based on contrastive learning. We test the proposed framework on two public multi-view facial expression recognition datasets.
  arXiv  Detail & Related papers  (2023-11-12T14:05:09Z)
• Learning Invariance from Generated Variance for Unsupervised Person Re-identification [15.096776375794356]
  We propose to replace traditional data augmentation with a generative adversarial network (GAN) A 3D mesh guided person image generator is proposed to disentangle a person image into id-related and id-unrelated features. By jointly training the generative and the contrastive modules, our method achieves new state-of-the-art unsupervised person ReID performance on mainstream large-scale benchmarks.
  arXiv  Detail & Related papers  (2023-01-02T15:40:14Z)
• Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning [15.242064747740116]
  It is unavoidable to construct undesirable views containing different semantic concepts during the augmentation procedure. It would damage the semantic consistency of representation to pull these augmentations closer in the feature space indiscriminately. In this study, we introduce feature-level augmentation and propose a novel semantics-consistent feature search (SCFS) method to mitigate this negative effect.
  arXiv  Detail & Related papers  (2022-12-13T11:13:59Z)
• Adversarial Cross-View Disentangled Graph Contrastive Learning [30.97720522293301]
  We introduce ACDGCL, which follows the information bottleneck principle to learn minimal yet sufficient representations from graph data. We empirically demonstrate that our proposed model outperforms the state-of-the-arts on graph classification task over multiple benchmark datasets.
  arXiv  Detail & Related papers  (2022-09-16T03:48:39Z)
• R\'enyiCL: Contrastive Representation Learning with Skew R\'enyi Divergence [78.15455360335925]
  We present a new robust contrastive learning scheme, coined R'enyiCL, which can effectively manage harder augmentations. Our method is built upon the variational lower bound of R'enyi divergence. We show that R'enyi contrastive learning objectives perform innate hard negative sampling and easy positive sampling simultaneously.
  arXiv  Detail & Related papers  (2022-08-12T13:37:05Z)
• LTT-GAN: Looking Through Turbulence by Inverting GANs [86.25869403782957]
  We propose the first turbulence mitigation method that makes use of visual priors encapsulated by a well-trained GAN. Based on the visual priors, we propose to learn to preserve the identity of restored images on a periodic contextual distance. Our method significantly outperforms prior art in both the visual quality and face verification accuracy of restored results.
  arXiv  Detail & Related papers  (2021-12-04T16:42:13Z)
• Improving Transferability of Representations via Augmentation-Aware Self-Supervision [117.15012005163322]
  AugSelf is an auxiliary self-supervised loss that learns the difference of augmentation parameters between two randomly augmented samples. Our intuition is that AugSelf encourages to preserve augmentation-aware information in learned representations, which could be beneficial for their transferability. AugSelf can easily be incorporated into recent state-of-the-art representation learning methods with a negligible additional training cost.
  arXiv  Detail & Related papers  (2021-11-18T10:43:50Z)
• Residual Relaxation for Multi-view Representation Learning [64.40142301026805]
  Multi-view methods learn by aligning multiple views of the same image. Some useful augmentations, such as image rotation, are harmful for multi-view methods because they cause a semantic shift. We develop a generic approach, Pretext-aware Residual Relaxation (Prelax), that relaxes the exact alignment.
  arXiv  Detail & Related papers  (2021-10-28T17:57:17Z)
• Adversarial Semantic Data Augmentation for Human Pose Estimation [96.75411357541438]
  We propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. We also propose Adversarial Semantic Data Augmentation (ASDA), which exploits a generative network to dynamiclly predict tailored pasting configuration. State-of-the-art results are achieved on challenging benchmarks.
  arXiv  Detail & Related papers  (2020-08-03T07:56:04Z)

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.