Search Results for author:
Found 160 papers, 63 papers with code
Hierarchical Face Aging through Disentangled Latent Characteristics
To explore the age effects on facial images, we propose a Disentangled Adversarial Autoencoder (DAAE) to disentangle the facial images into three independent factors: age, identity and extraneous information.
R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
However, due to their inherent vulnerability and the common practice of selecting from a limited set of open-source models, VLMs suffer from a higher risk of adversarial attacks than traditional vision models.
Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited.
ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation
Personalized text-to-image models allow users to generate images of new concepts from several reference photos, thereby leading to critical concerns regarding civil privacy.
Survey on AI-Generated Media Detection: From Non-MLLM to MLLM
Despite significant progress in this field, there remains a gap in literature regarding a comprehensive survey that examines the transition from domain-specific to general-purpose detection methods.
InfoBFR: Real-World Blind Face Restoration via Information Bottleneck
Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of data degradation patterns.
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction.
Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain Adaptation
Given the potential risk of source data leakage via model inversion attacks, this paper introduces a novel setting called black-box domain adaptation, where the source model is accessible only through an API that provides the predicted label along with the corresponding confidence value for each query.
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
Towards Compatible Fine-tuning for Vision-Language Model Updates
So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules.
Sample Correlation for Fingerprinting Deep Face Recognition
Face recognition has witnessed remarkable advancements in recent years, thanks to the development of deep learning techniques. However, an off-the-shelf face recognition model as a commercial service could be stolen by model stealing attacks, posing great threats to the rights of the model owner. Model fingerprinting, as a model stealing detection method, aims to verify whether a suspect model is stolen from the victim model, gaining more and more attention nowadays. Previous methods always utilize transferable adversarial examples as the model fingerprint, but this method is known to be sensitive to adversarial defense and transfer learning techniques. To address this issue, we consider the pairwise relationship between samples instead and propose a novel yet simple model stealing detection method based on SAmple Correlation (SAC). Specifically, we present SAC-JC that selects JPEG compressed samples as model inputs and calculates the correlation matrix among their model outputs. Extensive results validate that SAC successfully defends against various model stealing attacks in deep face recognition, encompassing face verification and face emotion recognition, exhibiting the highest performance in terms of AUC, p-value and F1 score. Furthermore, we extend our evaluation of SAC-JC to object recognition datasets including Tiny-ImageNet and CIFAR10, which also demonstrates the superior performance of SAC-JC to previous methods. The code will be available at \url{https://github. com/guanjiyang/SAC_JC}.
T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs
In this work, our study of these approaches harvests an effective data augmentation method.
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs
As a prominent direction of Artificial General Intelligence (AGI), Multimodal Large Language Models (MLLMs) have garnered increased attention from both industry and academia.
Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
Consequently, understanding the methods of jailbreak attacks and existing defense mechanisms is essential to ensure the safe deployment of multimodal generative models in real-world scenarios, particularly in security-sensitive applications.
Breaking the Low-Rank Dilemma of Linear Attention
The Softmax attention mechanism in Transformer models is notoriously computationally expensive, particularly due to its quadratic complexity, posing significant challenges in vision applications.
Not Just Object, But State: Compositional Incremental Learning without Forgetting
Most incremental learners excessively prioritize coarse classes of objects while neglecting various kinds of states (e. g. color and material) attached to the objects.
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration
In the pre-training stage, we enhance the pre-trained CLIP model by introducing a simple mechanism that scales it to higher resolutions, allowing us to extract robust degradation representations that adaptively guide the IR network.
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
Pre-training on large-scale, high-quality datasets is crucial for enhancing the reasoning capabilities of Large Language Models (LLMs), especially in specialized domains such as mathematics.
ZePo: Zero-Shot Portrait Stylization with Faster Sampling
To blend the Consistency Features extracted from both content and style images, we introduce a Style Enhancement Attention Control technique that meticulously merges content and style features within the attention space of the target image.
VITA: Towards Open-Source Interactive Omni Multimodal LLM
The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas.
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
And this low-rank gradient can be expressed in terms of the gradients of the two low-rank matrices in LoRA.
STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
In particular, the memory bank is dynamically updated by selecting low-entropy and label-consistent samples in a class-balanced manner.
ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation
Previous methods promote the frame rate by either training a video interpolation model in pixel space as a postprocessing stage or training an interpolation model in latent space for a specific base video model.
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
In the realm of Multimodal Large Language Models (MLLMs), vision-language connector plays a crucial role to link the pre-trained vision encoders with Large Language Models (LLMs).
Vision Transformer with Sparse Scan Prior
In recent years, Transformers have achieved remarkable progress in computer vision tasks.
Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens
The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess.
Band-Attention Modulated RetNet for Face Forgery Detection
The transformer networks are extensively utilized in face forgery detection due to their scalability across large datasets. Despite their success, transformers face challenges in balancing the capture of global context, which is crucial for unveiling forgery clues, with computational complexity. To mitigate this issue, we introduce Band-Attention modulated RetNet (BAR-Net), a lightweight network designed to efficiently process extensive visual contexts while avoiding catastrophic forgetting. Our approach empowers the target token to perceive global information by assigning differential attention levels to tokens at varying distances.
ViTAR: Vision Transformer with Any Resolution
Firstly, we propose a novel module for dynamic resolution adjustment, designed with a single Transformer block, specifically to achieve highly efficient incremental token integration.
DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration
Experimental results demonstrate the superiority of DiffMAC over state-of-the-art methods, with a high degree of generalization in real-world and heterogeneous settings.
CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning
Inspired by this, we propose a novel A-O disentangled framework for CZSL, namely Class-specified Cascaded Network (CSCNet).
InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding
Multimodal Large Language Models (MLLMs) have experienced significant advancements recently.
Ranked #120 on
Visual Question Answering
on MM-Vet
Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
This paper proposes a \textbf{C}ollabo\textbf{ra}tive \textbf{F}ine-\textbf{T}uning (\textbf{CraFT}) approach for fine-tuning black-box VLMs to downstream tasks, where one only has access to the input prompts and the output predictions of the model.
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Extensive results on 17 datasets validate that our method surpasses or achieves comparable results with state-of-the-art methods on few-shot classification, imbalanced learning, and out-of-distribution generalization.
Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
Even for single-image reconstruction, we still lack an analysis-based algorithm to recover augmented soft labels.
Exploring Vacant Classes in Label-Skewed Federated Learning
As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training.
Backdoor Defense via Test-Time Detecting and Repairing
In this paper we investigate the possibility of defending against backdoor attacks by utilizing test-time partially poisoned data to remove the backdoor from the model.
Portrait Diffusion: Training-free Face Stylization with Chain-of-Painting
Face stylization refers to the transformation of a face into a specific portrait style.
Exploring Straighter Trajectories of Flow Matching with Diffusion Guidance
First, we propose a coupling strategy to straighten trajectories, creating couplings between image and noise samples under diffusion model guidance.
ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models
Our work also suggests that a pre-trained diffusion model trained on low-resolution images can be directly used for high-resolution visual generation without further tuning, which may provide insights for future research on ultra-high-resolution image and video synthesis.
Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling
This paper proposes Video-Teller, a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment to significantly enhance the video-to-text generation task.
Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models
These analogous problems are related to the input one, with reusable solutions and problem-solving strategies.
RMT: Retentive Networks Meet Vision Transformers
To alleviate these issues, we draw inspiration from the recent Retentive Network (RetNet) in the field of NLP, and propose RMT, a strong vision backbone with explicit spatial prior for general purposes.
Audio-Driven Dubbing for User Generated Contents via Style-Aware Semi-Parametric Synthesis
Existing automated dubbing methods are usually designed for Professionally Generated Content (PGC) production, which requires massive training data and training time to learn a person-specific audio-video mapping.
Learning Cross-modality Information Bottleneck Representation for Heterogeneous Person Re-Identification
Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance.
Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
The emergence of vision-language models, such as CLIP, has spurred a significant research effort towards their application for downstream supervised learning tasks.
Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
Thereafter, we fine-tune CLIP with off-the-shelf methods by combining labeled and synthesized features.
TALL: Thumbnail Layout for Deepfake Video Detection
This paper introduces a simple yet effective strategy named Thumbnail Layout (TALL), which transforms a video clip into a pre-defined layout to realize the preservation of spatial and temporal dependencies.
Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
To implement this benchmark, we have developed a unified framework in PyTorch, which allows for consistent evaluation and comparison of the TTA methods across the different datasets and network architectures.
Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification
Consequently, we propose a cross-modal ordinal pairwise loss to refine the CLIP feature space, where texts and images maintain both semantic alignment and ordering alignment.
Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion
When decreasing the number of sampling steps (i. e., the number of line segments used to fit the path), the ease of fitting straight lines compared to curves allows us to generate higher quality samples from a random noise with fewer iterations.
Lightweight Vision Transformer with Bidirectional Interaction
This paper proposes a Fully Adaptive Self-Attention (FASA) mechanism for vision transformer to model the local and global information as well as the bidirectional interaction between them in context-aware ways.
Rethinking Local Perception in Lightweight Vision Transformer
The combination of the AttnConv and vanilla attention which uses pooling to reduce FLOPs in CloFormer enables the model to perceive high-frequency and low-frequency information.
Ranked #622 on
Image Classification
on ImageNet
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer
Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) by accessing both the source and target data.
Mind the Label Shift of Augmentation-based Graph OOD Generalization
Recent works employ different graph editions to generate augmented environments and learn an invariant GNN for generalization.
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.
AUTO: Adaptive Outlier Optimization for Online Test-Time OOD Detection
Out-of-distribution (OOD) detection is a crucial aspect of deploying machine learning models in open-world applications.
Pluralistic Aging Diffusion Autoencoder
Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input.
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
To address this issue, we propose a model preprocessing framework, named AdaptGuard, to improve the security of model adaptation algorithms.
MODIFY: Model-driven Face Stylization without Style Images
Briefly, MODIFY first trains a generative model in the target domain and then translates a source input to the target domain via the provided style model.
Masked Relation Learning for DeepFake Detection
A relation learning module masks partial correlations between regions to reduce redundancy and then propagates the relational information across regions to capture the irregularity from a global view of the graph.
MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection
Existing cross-domain keypoint detection methods always require accessing the source data during adaptation, which may violate the data privacy law and pose serious security concerns.
MSRA-SR: Image Super-resolution Transformer with Multi-scale Shared Representation Acquisition
In particular, self-attention with cross-scale matching and convolution filters with different kernel sizes are designed to exploit the multi-scale features in images.
Vision Transformer with Super Token Sampling
STA decomposes vanilla global attention into multiplications of a sparse association map and a low-dimensional attention, leading to high efficiency in capturing global dependencies.
ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data
Then, we optimize the augmented samples by minimizing the norms of the data scores, i. e., the gradients of the log-density functions.
Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks
To reduce the training time, we further develop SAC-m that selects CutMix Augmented samples as model inputs, without the need for training the surrogate models or generating adversarial examples.
Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification
To alleviate these two issues, we propose a simple yet effective method with Parallel Augmentation and Dual Enhancement (PADE), which is robust on both occluded and non-occluded data and does not require any auxiliary clues.
Finding Diverse and Predictable Subgraphs for Graph Domain Generalization
Extensive experiments on both node-level and graph-level benchmarks shows that the proposed DPS achieves impressive performance for various graph domain generalization tasks.
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
First of all, to avoid additional parameters and explore the information in the source model, ProxyMix defines the weights of the classifier as the class prototypes and then constructs a class-balanced proxy source domain by the nearest neighbors of the prototypes to bridge the unseen source domain and the target domain.
A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery.
Styleverse: Towards Identity Stylization across Heterogeneous Domains
We propose a new challenging task namely IDentity Stylization (IDS) across heterogeneous domains.
Rethinking Image Cropping: Exploring Diverse Compositions From Global Views
In this paper, we regard image cropping as a set prediction problem.
Few-shot Backdoor Defense Using Shapley Estimation
Deep neural networks have achieved impressive performance in a variety of tasks over the last decade, such as autonomous driving, face recognition, and medical diagnosis.
Towards the Explanation of Graph Neural Networks in Digital Pathology with Information Flows
In this work, we address these key challenges and propose IFEXPLAINER, which generates a necessary and sufficient explanation for GNNs.
Improving Subgraph Recognition with Variational Graph Information Bottleneck
Subgraph recognition aims at discovering a compressed substructure of a graph that is most informative to the graph property.
UMAD: Universal Model Adaptation under Domain and Category Shift
To achieve bilateral adaptation in the target domain, we further maximize localized mutual information to align known samples with the source classifier and employ an entropic loss to push unknown samples far away from the source classification boundary, respectively.
Ranked #7 on
Universal Domain Adaptation
on VisDA2017
Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learning
To make further efforts on accurate and reliable iris segmentation, we propose a bilateral self-attention module and design Bilateral Transformer (BiTrans) with hierarchical architecture by exploring spatial and visual relationships.
Causal Representation Learning for Context-Aware Face Transfer
Human face synthesis involves transferring knowledge about the identity and identity-dependent face shape (IDFS) of a human face to target face images where the context (e. g., facial expressions, head poses, and other background factors) may change dramatically.
Universal Face Restoration With Memorized Modulation
Blind face restoration (BFR) is a challenging problem because of the uncertainty of the degradation patterns.
FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains
In this work, we propose a novel two-stage framework named FaceInpainter to implement controllable Identity-Guided Face Inpainting (IGFI) under heterogeneous domains.
Memory Oriented Transfer Learning for Semi-Supervised Image Deraining
To address this issue, we propose a memory-oriented semi-supervised (MOSS) method which enables the network to explore and exploit the properties of rain streaks from both synthetic and real data.
Pareidolia Face Reenactment
We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video.
Information Bottleneck Disentanglement for Identity Swapping
In this work, we propose a novel information disentangling and swapping network, called InfoSwap, to extract the most expressive information for identity representation from a pre-trained face recognition model.
PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal
In this paper, we address the makeup transfer and removal tasks simultaneously, which aim to transfer the makeup from a reference image to a source image and remove the makeup from the with-makeup image respectively.
Everything's Talkin': Pareidolia Face Reenactment
We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video.
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target).
ReMix: Towards Image-to-Image Translation with Limited Data
We interpolate training samples at the feature level and propose a novel content loss based on the perceptual relations among samples.
Recognizing Predictive Substructures with Subgraph Information Bottleneck
The emergence of Graph Convolutional Network (GCN) has greatly boosted the progress of graph learning.
CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification
Visible-Infrared person re-identification (VI-ReID) aims to match cross-modality pedestrian images, breaking through the limitation of single-modality person ReID in dark environment.
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain.
Ranked #5 on
Source-Free Domain Adaptation
on VisDA-2017
Unsupervised Contrastive Photo-to-Caricature Translation based on Auto-distortion
Considering the intuitive artifacts in the existing methods, we propose a contrastive style loss for style rendering to enforce the similarity between the style of rendered photo and the caricature, and simultaneously enhance its discrepancy to the photos.
Lets Play Music: Audio-driven Performance Video Generation
We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip.
AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection
However, due to the lack of Deepfakes datasets with large variance in appearance, which can be hardly produced by recent identity swapping methods, the detection algorithm may fail in this situation.
Ranked #7 on
Visual Object Tracking
on DiDi
$P^2$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation
We propose a refinement stage for the pyramid features to further boost the accuracy of our network.
Graph Information Bottleneck for Subgraph Recognition
In this paper, we propose a framework of Graph Information Bottleneck (GIB) for the subgraph recognition problem in deep graph learning.
DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition
As a consequence, massive new diverse paired heterogeneous images with the same identity can be generated from noises.
Deep Momentum Uncertainty Hashing
It embodies the uncertainty of the hashing network to the corresponding input image.
TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search
In this paper, we rethink three freedoms of differentiable NAS, i. e. operation-level, depth-level and width-level, and propose a novel method, named Three-Freedom NAS (TF-NAS), to achieve both good classification accuracy and precise latency constraint.
Recapture as You Want
LGR module utilizes body skeleton knowledge to construct a layout graph that connects all relevant part features, where graph reasoning mechanism is used to propagate information among part nodes to mine their relations.
Cosmetic-Aware Makeup Cleanser
Face verification aims at determining whether a pair of face images belongs to the same identity.
Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation
At last, we proposed a differentiable auto data augmentation method to further improve estimation accuracy.
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
On one hand, negative transfer results in misclassification of target samples to the classes only present in the source domain.
Ranked #2 on
Partial Domain Adaptation
on ImageNet-Caltech
Everybody's Talkin': Let Me Talk as You Want
The audio-translated expression parameters are then used to synthesize a photo-realistic human subject in each video frame, with the movement of the mouth regions precisely mapped to the source audio.
Deep Audio-Visual Learning: A Survey
Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully.
Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models.
Exploiting Style and Attention in Real-World Super-Resolution
Real-world image super-resolution (SR) is a challenging image translation problem.
LAMP-HQ: A Large-Scale Multi-Pose High-Quality Database and Benchmark for NIR-VIS Face Recognition
A spectral conditional attention module is introduced to reduce the domain gap between NIR and VIS data and then improve the performance of NIR-VIS heterogeneous face recognition on various databases including the LAMP-HQ.
Dual Variational Generation for Low Shot Heterogeneous Face Recognition
Specifically, we first introduce a dual variational autoencoder to represent a joint distribution of paired heterogeneous images.
Spectral Graph Transformer Networks for Brain Surface Parcellation
Our alignment and graph processing method provides a fast analysis of brain surfaces.
PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
In this paper, we address the makeup transfer task, which aims to transfer the makeup from a reference image to a source image.
Augmented Data Science: Towards Industrialization and Democratization of Data Science
Conversion of raw data into insights and knowledge requires substantial amounts of effort from data scientists.
Cross-Spectral Face Hallucination via Disentangling Independent Factors
The cross-sensor gap is one of the challenges that have aroused much research interests in Heterogeneous Face Recognition (HFR).
Make a Face: Towards Arbitrary High Fidelity Face Manipulation
Recent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to low-resolution and lack of diversity.
Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs
RoM pooling pools image features and discards extra padded features to eliminate the side effects of padding.
Attributes Guided Feature Learning for Vehicle Re-identification
In particular, our network is end-to-end trained and contains three subnetworks of deep features embedded by the corresponding attributes (i. e., camera view, vehicle type and vehicle color).
Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
In this work, we present a novel training framework for GANs, namely biphasic learning, to achieve image-to-image translation in multiple visual domains at $1024^2$ resolution.
PyramidBox++: High Performance Detector for Finding Tiny Face
With the rapid development of deep convolutional neural network, face detection has made great progress in recent years.
M2FPA: A Multi-Yaw Multi-Pitch High-Quality Database and Benchmark for Facial Pose Analysis
In this paper, a new large-scale Multi-yaw Multi-pitch high-quality database is proposed for Facial Pose Analysis (M2FPA), including face frontalization, face rotation, facial pose estimation and pose-invariant face recognition.
UVA: A Universal Variational Framework for Continuous Age Analysis
UVA is the first attempt to achieve facial age analysis tasks, including age translation, age generation and age estimation, in a universal framework.
High Fidelity Face Manipulation with Extreme Poses and Expressions
Furthermore, due to the lack of high-resolution face manipulation databases to verify the effectiveness of our method, we collect a new high-quality Multi-View Face (MVF-HQ) database.
Dual Variational Generation for Low-Shot Heterogeneous Face Recognition
Then, in order to ensure the identity consistency of the generated paired heterogeneous images, we impose a distribution alignment in the latent space and a pairwise identity preserving in the image space.
Ranked #1 on
Face Verification
on CASIA NIR-VIS 2.0
Cross-spectral Face Completion for NIR-VIS Heterogeneous Face Recognition
This paper models high resolution heterogeneous face synthesis as a complementary combination of two components, a texture inpainting component and pose correction component.
Joint Iris Segmentation and Localization Using Deep Multi-task Learning Framework
In this paper, we propose a deep multi-task learning framework, named as IrisParseNet, to exploit the inherent correlations between pupil, iris and sclera to boost up the performance of iris segmentation and localization in a unified model.
Ranked #1 on
Iris Segmentation
on CASIA
A Survey of Deep Facial Attribute Analysis
Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes.
Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning
Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image.
A Coupled Evolutionary Network for Age Estimation
Inspired by the biological evolutionary mechanism, we propose a Coupled Evolutionary Network (CEN) with two concurrent evolutionary processes: evolutionary label distribution learning and evolutionary slack regression.
Global and Local Consistent Wavelet-domain Age Synthesis
%Moreover, to achieve accurate age generation under the premise of preserving the identity information, age estimation network and face verification network are employed.
Geometry-Aware Face Completion and Editing
Extensive experimental results qualitatively and quantitatively demonstrate that our network is able to generate visually pleasing face completion results and edit face attributes as well.
Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing
It generates hashing bits by the output neurons of a deep hashing network.
Disentangled Variational Representation for Heterogeneous Face Recognition
Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms.
Ranked #2 on
Face Verification
on CASIA NIR-VIS 2.0
IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
On the other hand, the inference model is encouraged to classify between the generated and real samples while the generator tries to fool it as GANs.
Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization
We decompose the prerequisite of warping into dense correspondence field estimation and facial texture map recovering, which are both well addressed by deep networks.
Pose-Guided Photorealistic Face Rotation
Face rotation provides an effective and cheap way for data augmentation and representation learning of face recognition.
Load Balanced GANs for Multi-view Face Image Synthesis
Multi-view face synthesis from a single image is an ill-posed problem and often suffers from serious appearance distortion.
Global and Local Consistent Age Generative Adversarial Networks
To utilize both global and local facial information, we propose a Global and Local Consistent Age Generative Adversarial Network (GLCA-GAN).
Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
We treat the face completion and corruption as disentangling and fusing processes of clean faces and occlusions, and propose a jointly disentangling and fusing Generative Adversarial Network (DF-GAN).
Geometry Guided Adversarial Facial Expression Synthesis
An expression invariant face recognition experiment is also performed to further show the advantages of our proposed method.
Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution
Most modern face super-resolution methods resort to convolutional neural networks (CNN) to infer high-resolution (HR) face images.
Ranked #3 on
Face Hallucination
on FFHQ 512 x 512 - 16x upscaling
Adversarial Occlusion-aware Face Detection
This paper introduces an Adversarial Occlusion-aware Face Detector (AOFD) by simultaneously detecting occluded faces and segmenting occluded areas.
Ranked #2 on
Occluded Face Detection
on MAFA
Adversarial Discriminative Heterogeneous Face Recognition
This framework integrates cross-spectral face hallucination and discriminative feature learning into an end-to-end adversarial network.
Joint Adaptive Neighbours and Metric Learning for Multi-view Subspace Clustering
In this method, we use the subspace representations of different views to adaptively learn a consensus similarity matrix, uncovering the subspace structure and avoiding noisy nature of original data.
Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification
This paper proposes a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN).
Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition
To avoid the over-fitting problem on small-scale heterogeneous face data, a correlation prior is introduced on the fully-connected layers of WCNN network to reduce parameter space.
Ranked #3 on
Face Verification
on BUAA-VisNir
Recent Progress of Face Image Synthesis
Face synthesis has been a fascinating yet challenging problem in computer vision and machine learning.
Deep Supervised Discrete Hashing
Benefit from recent advances in deep learning, deep hashing methods have achieved promising results for image retrieval.
Robust Localized Multi-view Subspace Clustering
In multi-view clustering, different views may have different confidence levels when learning a consensus representation.
Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.
Attention-Set based Metric Learning for Video Face Recognition
In this paper, we propose a novel Attention-Set based Metric Learning (ASML) method to measure the statistical characteristics of image sets.
Coupled Deep Learning for Heterogeneous Face Recognition
CDL seeks a shared feature space in which the heterogeneous face matching problem can be approximately treated as a homogeneous face matching problem.
DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
The occlusions incurred by random meshes severely degenerate the performance of face verification systems, which raises the MeshFace verification problem between MeshFace and daily photos.
Self-Paced Learning: an Implicit Regularization Perspective
In this paper, we focus on the minimizer function, and study a group of new regularizer, named self-paced implicit regularizer that is deduced from robust loss function.
Locally Imposing Function for Generalized Constraint Neural Networks - A Study on Equality Constraints
A new method called locally imposing function (LIF) is proposed to provide a local correction to the GCNN prediction function, which therefore falls within Locally Imposing Scheme (LIS).
Deep Aesthetic Quality Assessment with Semantic Information
Human beings often assess the aesthetic quality of an image coupled with the identification of the image's semantic content.
Ranked #5 on
Aesthetics Quality Assessment
on AVA
A Light CNN for Deep Face Representation with Noisy Labels
This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels.
Ranked #2 on
Age-Invariant Face Recognition
on CAFR
Learning Structured Ordinal Measures for Video based Face Recognition
This paper presents a structured ordinal measure method for video-based face recognition that simultaneously learns ordinal filters and structured ordinal features.
Cross-Modal Learning via Pairwise Constraints
For unsupervised learning, we propose a cross-modal subspace clustering method to learn a common structure for different modalities.
Information-Theoretic Measures for Objective Evaluation of Classifications
This work presents a systematic study of objective evaluations of abstaining classifications using Information-Theoretic Measures (ITMs).
