Search Results for author:
Found 95 papers, 53 papers with code
Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces
In this paper, we relax the intra-class constraint of ArcFace to improve the robustness to label noise.
Signs as Tokens: An Autoregressive Multilingual Sign Language Generator
Most existing approaches treat SLG as a visual content generation task, employing techniques such as diffusion models to produce sign videos, 2D keypoints, or 3D avatars based on text inputs, overlooking the linguistic properties of sign languages.
ZeroGS: Training 3D Gaussian Splatting from Unposed Images
While previous methods can reconstruct from a few unposed images, they are not applicable when images are unordered or densely captured.
From Attention to Activation: Unravelling the Enigmas of Large Language Models
In summary, our methods reduce the attention proportion on the first token from 65% to 3. 3%, the activation kurtosis in the hidden states from 1657 to 3. 1, and perplexity penalty under 4-bit weight quantisation from 3565 to 0. 3.
Croc: Pretraining Large Multimodal Models with Cross-Modal Comprehension
Then, we conceptualize visual tokens as analogous to a "foreign language" for the LLMs and propose a mixed attention mechanism with bidirectional visual attention and unidirectional textual attention to comprehensively enhance the understanding of visual tokens.
Fractal Calibration for long-tailed object detection
FRACAL devises a logit adjustment method that utilises the fractal dimension to estimate how uniformly classes are distributed in image space.
TopoFR: A Closer Look at Topology Alignment on Face Recognition
To address this problem, we propose TopoFR, a novel FR model that leverages a topological structure alignment strategy called PTSA and a hard sample mining strategy named SDE.
WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild
In recent years, 3D hand pose estimation methods have garnered significant attention due to their extensive applications in human-computer interaction, virtual reality, and robotics.
Ranked #1 on
3D Hand Pose Estimation
on HO-3D v2
CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination
In this paper, we introduce CLIP-CID, a novel distillation mechanism that effectively transfers knowledge from a large vision-language foundation model to a smaller model.
Multi-label Cluster Discrimination for Visual Representation Learning
In this paper, we propose a novel Multi-Label Cluster Discrimination method named MLCD to enhance representation learning.
Ranked #2 on
Visual Question Answering (VQA)
on DocVQA test
(using extra training data)
Adaptive Parametric Activation
In this work, we delve deeper in this phenomenon by performing a comprehensive statistical analysis in the classification and intermediate layers of both balanced and imbalanced networks and we empirically show that aligning the activation function with the data distribution, enhances the performance in both balanced and imbalanced tasks.
Ranked #11 on
Long-tail Learning
on Places-LT
Graph in Graph Neural Network
Given a set of graphs or a data sample whose components can be represented by a set of graphs (called multi-graph data sample), our GIG network starts with a GIG sample generation (GSG) module which encodes the input as a \textbf{GIG sample}, where each GIG vertex includes a graph.
High-Fidelity Facial Albedo Estimation via Texture Quantization
In this paper, we present a novel facial albedo reconstruction model, HiFiAlbedo, which recovers the albedo map directly from a single image without the need for captured albedo data.
AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis
To obtain a material-aware and geometry-aware condition for audio synthesis, we learn an explicit point-based scene representation with an audio-guidance parameter on locally initialized Gaussian points, taking into account the space relation from the listener and sound source.
RWKV-CLIP: A Robust Vision-Language Representation Learner
Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites.
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
Large language models (LLMs) have recently emerged as powerful tools for tackling many language-processing tasks.
ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling
We propose ID-to-3D, a method to generate identity- and text-guided 3D human heads with disentangled expressions, starting from even a single casually captured in-the-wild image of a subject.
Improving face generation quality and prompt following with synthetic captions
We then use these synthetic captions to fine-tune a text-to-image diffusion model.
SAGS: Structure-Aware 3D Gaussian Splatting
In this work, we propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene, which reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
Unified Physical-Digital Attack Detection Challenge
Based on this dataset, we organized a Unified Physical-Digital Face Attack Detection Challenge to boost the research in Unified Attack Detections.
Monocular Identity-Conditioned Facial Reflectance Reconstruction
We first learn a high-quality prior for facial reflectance.
Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution
Following this, the Reality Guidance Refinement (RGR) process refines artifacts by integrating this mask with realistic latent representations, improving alignment with the original image.
Deep Active Learning: A Reality Check
By uncovering the limitations of current methods and understanding the impact of different experimental settings, we aim to inspire more efficient training of deep learning models in real-world scenarios with limited annotation budgets.
CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing
Specifically, we propose a novel Class Free Prompt Learning (CFPL) paradigm for DG FAS, which utilizes two lightweight transformers, namely Content Q-Former (CQF) and Style Q-Former (SQF), to learn the different semantic prompts conditioned on content and style features by using a set of learnable query vectors, respectively.
IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models
Leveraging Stable Diffusion for the generation of personalized portraits has emerged as a powerful and noteworthy tool, enabling users to create high-fidelity, custom character avatars based on their specific prompts.
WaveFace: Authentic Face Restoration with Efficient Frequency Recovery
Although diffusion models are rising as a powerful solution for blind face restoration, they are criticized for two problems: 1) slow training and inference speed, and 2) failure in preserving identity and recovering fine-grained facial details.
Arc2Face: A Foundation Model for ID-Consistent Human Faces
This paper presents Arc2Face, an identity-conditioned face foundation model, which, given the ArcFace embedding of a person, can generate diverse photo-realistic images with an unparalleled degree of face similarity than existing models.
Ranked #1 on
Diffusion Personalization Tuning Free
on AgeDB
$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections
Knowledge distillation is an effective method for training small and efficient deep learning models.
Ranked #2 on
Knowledge Distillation
on ImageNet
G3DR: Generative 3D Reconstruction in ImageNet
We introduce a novel 3D generative method, Generative 3D Reconstruction (G3DR) in ImageNet, capable of generating diverse and high-quality 3D objects from single images, addressing the limitations of existing methods.
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability.
AvatarMMC: 3D Head Avatar Generation and Editing with Multi-Modal Conditioning
To the best of our knowledge, our approach is the first to introduce multi-modal conditioning to 3D avatar generation and editing.
Spatio-temporal Prompting Network for Robust Video Feature Extraction
Then, these video prompts are prepended to the patch embeddings of the current frame as the updated input for video feature extraction.
Unified Physical-Digital Face Attack Detection
These three modules seamlessly form a robust unified attack detection framework.
VkD: Improving Knowledge Distillation using Orthogonal Projections
Knowledge distillation is an effective method for training small and efficient deep learning models.
Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning
For instance, on CIFAR-10-LT, CPE improves test accuracy by over 2. 22% compared to baselines.
Neural Sign Actors: A diffusion model for 3D sign language production from text
Sign Languages (SL) serve as the primary mode of communication for the Deaf and Hard of Hearing communities.
Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation
Previous methods mitigate this issue by exploring image enhancement or object detection techniques with real low-light image datasets.
Rethinking the Domain Gap in Near-infrared Face Recognition
Heterogeneous face recognition (HFR) involves the intricate task of matching face images across the visual domains of visible (VIS) and near-infrared (NIR).
Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images
Stable diffusion, a generative model used in text-to-image synthesis, frequently encounters resolution-induced composition problems when generating images of varying sizes.
TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective
We investigate the reasons for this phenomenon and discover that the existing data augmentation approach and hard sample mining strategy are incompatible with ViTs-based FR backbone due to the lack of tailored consideration on preserving face structural information and leveraging each local token information.
ALIP: Adaptive Language-Image Pre-training with Synthetic Caption
However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning.
Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowds
In real-world crowd-sourcing scenarios, noise transition matrices are both annotator- and instance-dependent.
FitMe: Deep Photorealistic 3D Morphable Model Avatars
In this paper, we introduce FitMe, a facial reflectance model and a differentiable rendering optimization pipeline, that can be used to acquire high-fidelity renderable human avatars from single or multiple images.
Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results
Leveraging the WFAS dataset and Protocol 1 (Known-Type), we host the Wild Face Anti-Spoofing Challenge at the CVPR2023 workshop.
Unicom: Universal and Compact Representation Learning for Image Retrieval
To further enhance the low-dimensional feature representation, we randomly select partial feature dimensions when calculating the similarities between embeddings and class-wise prototypes.
DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion
Concretely, we establish the denoising process in the Transformer decoder (e. g., DETR) by introducing a temporal location query design with faster convergence in training.
Regularization of polynomial networks for image recognition
We introduce a class of PNs, which are able to reach the performance of ResNet across a range of six benchmarks.
$α$Surf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity
While neural radiance field (NeRF) based methods can model semi-transparency and achieve photo-realistic quality in synthesized novel views, their volumetric geometry representation tightly couples geometry and opacity, and therefore cannot be easily converted into surfaces without introducing artifacts.
Holistic Label Correction for Noisy Multi-Label Classification
The issues are, that we do not understand why label dependence is helpful in the problem, and how to learn and utilize label dependence only using training data with noisy multiple labels.
Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes
The success of deep learning models on structured data has generated significant interest in extending their application to non-Euclidean domains.
Controllable Person Image Synthesis with Pose-Constrained Latent Diffusion
Controllable person image synthesis aims at rendering a source image based on user-specified changes in body pose or appearance.
Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues
Our key insight is that intrinsic semantic attributes such as race, skin color, and age can constrain the albedo map.
3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views
To close the gap between image domains, we create a large-scale dataset of diverse faces with gaze pseudo-annotations, which we extract based on the 3D geometry of the scene, and design a multi-view supervision framework to balance their effect during training.
Domain-General Crowd Counting in Unseen Scenarios
In this paper, we aim to train a model based on a single source domain which can generalize well on any unseen domain.
Confidence-guided Centroids for Unsupervised Person Re-Identification
Since samples with high confidence are exclusively involved in the formation of centroids, the identity information of low-confidence samples, i. e., boundary samples, are NOT likely to contribute to the corresponding centroid.
Physically-Based Face Rendering for NIR-VIS Face Recognition
Specifically, we reconstruct 3D face shape and reflectance from a large 2D facial dataset and introduce a novel method of transforming the VIS reflectance to NIR reflectance.
A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal
Second, we discuss the challenges of face restoration.
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models
Pretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts.
Inverse Image Frequency for Long-tailed Image Recognition
The long-tailed distribution is a common phenomenon in the real world.
Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression
Even though 3D face reconstruction has achieved impressive progress, most orthogonal projection-based face reconstruction methods can not achieve accurate and consistent reconstruction results when the face is very close to the camera due to the distortion under the perspective projection.
Redesigning Multi-Scale Neural Network for Crowd Counting
In this work, we redesign the multi-scale neural network by introducing a hierarchical mixture of density experts, which hierarchically merges multi-scale density maps for crowd counting.
Long-tailed Instance Segmentation using Gumbel Optimized Loss
Major advancements have been made in the field of object detection and segmentation recently.
Ranked #14 on
Instance Segmentation
on LVIS v1.0 val
FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders
Firstly, randomly masked face images are used to train the reconstruction module in FaceMAE.
Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline
To the best of our knowledge, this is the first large-scale dataset for gait recognition in the wild.
WebFace260M: A Benchmark for Million-Scale Deep Face Recognition
For a comprehensive evaluation of face matchers, three recognition tasks are performed under standard, masked and unbiased settings, respectively.
Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
Ranked #1 on
Face Recognition
on MFR
Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing
Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection.
Ranked #1 on
Face Parsing
on Helen
Facial Geometric Detail Recovery via Implicit Representation
Learning a dense 3D model with fine-scale details from a single facial image is highly challenging and ill-posed.
Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset
It is thus unclear how these algorithms perform on public face hallucination datasets.
Ranked #1 on
Image Super-Resolution
on WLFW
Masked Face Recognition Challenge: The InsightFace Track Report
In this workshop, we organize Masked Face Recognition (MFR) challenge and focus on bench-marking deep face recognition methods under the existence of facial masks.
Masked Face Recognition Challenge: The WebFace260M Track Report
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
Poly-NL: Linear Complexity Non-local Layers with Polynomials
Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions.
Ranked #1 on
Face Detection
on WIDER Face (Hard)
Variational Prototype Learning for Deep Face Recognition
Deep face recognition has achieved remarkable improvements due to the introduction of margin-based softmax loss, in which the prototype stored in the last linear layer represents the center of each class.
Sample and Computation Redistribution for Efficient Face Detection
Although tremendous strides have been made in uncontrolled face detection, efficient face detection with a low computation cost as well as high precision remains an open challenge.
Ranked #7 on
Face Detection
on WIDER Face (Medium)
Augmenting Deep Classifiers with Polynomial Neural Networks
The efficacy of the proposed models is evaluated on standard image and audio classification benchmarks.
Ranked #3 on
Audio Classification
on Speech Commands
MogFace: Towards a Deeper Appreciation on Face Detection
As a result, practical solutions on label assignment, scale-level data augmentation, and reducing false alarms are necessary for advancing face detectors.
Ranked #12 on
Face Detection
on WIDER Face (Easy)
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
Poly-NL: Linear Complexity Non-Local Layers With 3rd Order Polynomials
Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions.
OSTeC: One-Shot Texture Completion
Many recent 3D facial texture reconstruction and pose manipulation from a single image approaches still rely on large and clean face datasets to train image-to-image Generative Adversarial Networks (GANs).
Extended T: Learning with Mixed Closed-set and Open-set Noisy Labels
The traditional transition matrix is limited to model closed-set label noise, where noisy training data has true class labels within the noisy label set.
Deep Polynomial Neural Networks
We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks.
Ranked #1 on
Face Recognition
on CALFW
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimate transition matrices.
RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild
Though tremendous strides have been made in uncontrolled face detection, accurate and efficient 2D face alignment and 3D face reconstruction in-the-wild remain an open challenge.
$Π-$nets: Deep Polynomial Neural Networks
Deep Convolutional Neural Networks (DCNNs) is currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning.
Ranked #1 on
Graph Representation Learning
on COMA
Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks
In this paper, we present the first methodology that generates high-quality texture, shape, and normals jointly, which can be used for photo-realistic synthesis.
RetinaFace: Single-stage Dense Face Localisation in the Wild
Face Analysis Project on MXNet
Ranked #2 on
Face Detection
on WIDER Face (Medium)
Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders
3D Morphable Models (3DMMs) are statistical models that represent facial texture and shape variations using a set of linear bases and more particular Principal Component Analysis (PCA).
Stacked Dense U-Nets with Dual Transformers for Robust Face Alignment
Face Analysis Project on MXNet
Ranked #1 on
Face Alignment
on IBUG
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability.
Ranked #1 on
Face Verification
on Labeled Faces in the Wild
(using extra training data)
Side Information for Face Completion: a Robust PCA Approach
Robust principal component analysis (RPCA) is a powerful method for learning low-rank feature representation of various visual data.
UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
We demonstrate that by attaching the completed UV to the fitted mesh and generating instances of arbitrary poses, we can increase pose variations for training deep face recognition/verification models, and minimise pose discrepancy during testing, which lead to better performance.
Informed Non-convex Robust Principal Component Analysis with Features
We revisit the problem of robust principal component analysis with features acting as prior side information.
Joint Multi-view Face Alignment in the Wild
This encompasses two basic problems: i) the detection and deformable fitting steps are performed independently, while the detector might not provide best-suited initialisation for the fitting step, ii) the face appearance varies hugely across different poses, which makes the deformable face fitting very challenging and thus distinct models have to be used (\eg, one for profile and one for frontal faces).
