REVIEW 12 cited by
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
read the original abstract
Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability. In this paper, we first introduce an Additive Angular Margin Loss (ArcFace), which not only has a clear geometric interpretation but also significantly enhances the discriminative power. Since ArcFace is susceptible to the massive label noise, we further propose sub-center ArcFace, in which each class contains $K$ sub-centers and training samples only need to be close to any of the $K$ positive sub-centers. Sub-center ArcFace encourages one dominant sub-class that contains the majority of clean faces and non-dominant sub-classes that include hard or noisy faces. Based on this self-propelled isolation, we boost the performance through automatically purifying raw web faces under massive real-world noise. Besides discriminative feature embedding, we also explore the inverse problem, mapping feature vectors to face images. Without training any additional generator or discriminator, the pre-trained ArcFace model can generate identity-preserved face images for both subjects inside and outside the training data only by using the network gradient and Batch Normalization (BN) priors. Extensive experiments demonstrate that ArcFace can enhance the discriminative feature embedding as well as strengthen the generative face synthesis.
Forward citations
Cited by 12 Pith papers
-
DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification
A multi-vehicle naturalistic benchmark finds learned driving embeddings retain driver identity under condition matching, while descriptors collapse and video re-ID is mostly route leakage.
-
GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
GVCC achieves the lowest LPIPS on UVG at bitrates down to 0.003 bpp by encoding stochastic innovations in a marginal-preserving stochastic process derived from a pretrained rectified-flow video model, with 65% LPIPS r...
-
Switchable Normalization for Learning-to-Normalize Deep Representation
Switchable Normalization learns per-layer weights to combine channel, layer, and minibatch normalizers, claiming robustness to batch size and better results than fixed normalizers on ImageNet, COCO, CityScapes, ADE20K...
-
Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping
For video face swapping, adaptively adding swapped anchor frames at the moments of worst identity drift should make synthetic training pairs more faithful than the current first-and-last-frame-only scheme.
-
SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data
SoftReason learns a differentiable soft deductive closure operator over perceptual facts and reports 94.3% Hit@1 on KVQA entity linking.
-
Multiple-Identity Image Attacks Against Face-based Identity Verification
The paper shows that multiple-identity image attacks succeed due to modest angular separation between matching (~90°) and non-matching (40-60°) face representations, with image morphing and representation inversion re...
-
TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation
Anchor-guided fixed-capacity multimodal memory plus stage-parallel few-step denoising stabilizes long-form causal audio-video digital humans at real-time speed.
-
Adaptive Calibration for Fair and Performant Facial Recognition
Adaptive Calibration maps cosine similarities to probabilities using local context, improving accuracy and fairness in facial recognition without demographic metadata.
-
Personalized Face Privacy Protection From a Single Image
FaceCloak learns a lightweight identity-specific cloaking mask from a single image via synthetic face generation and iterative embedding perturbation to evade multiple recognition models.
-
Find the Differences: Differential Morphing Attack Detection vs Face Recognition
Face recognition systems can be repurposed for morphing attack detection using a new threshold that bounds vulnerability even to unknown morph types.
-
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
Common feature learning transforms features from heterogeneous teacher networks into a shared space so a student model can imitate them all and outperform individual teachers without annotations.
-
Primate Face Identification in the Wild
A pairwise-augmented loss on CNNs is reported to deliver state-of-the-art accuracy on primate face classification, verification, closed-set and open-set identification for two species.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.