Search Results for author:
Found 115 papers, 54 papers with code
SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
Inspired by model pruning which lightens large pre-trained models by removing unimportant parameters, we propose a novel model fine-tuning method to make full use of these ineffective parameters and enable the pre-trained model with new task-specified capabilities.
PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model
Domain Generalization (DG) has been recently explored to improve the generalizability of point cloud classification (PCC) models toward unseen domains.
Source-Free Test-Time Adaptation For Online Surface-Defect Detection
In this paper, we propose a novel test-time adaptation surface-defect detection approach that adapts pre-trained models to new domains and classes during inference.
LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description
In this paper, we propose a Large Language-and-Vision Assistant for Visual Spatial Description, named LLaVA-VSD, which is designed for the classification, description, and open-ended description of visual spatial relationships.
DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding
In this paper, we introduce a novel, practical, multi-domain multi-task setting, handling multiple domains and multiple tasks within one unified model for domain generalized point cloud understanding.
Portrait3D: 3D Head Generation from Single In-the-wild Portrait Image
We then use the canny map, ID features of the portrait image, and a pre-trained text-to-normal/depth diffusion model to generate ID-aware geometry supervision, and 3D-GAN inversion is employed to generate ID-aware geometry initialization.
PIG: Prompt Images Guidance for Night-Time Scene Parsing
In this paper, we leverage Prompt Images Guidance (PIG) to enhance UDA with supplementary night knowledge.
M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising
Existing industrial anomaly detection methods primarily concentrate on unsupervised learning with pristine RGB images.
Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models
In particular, we introduce a new attack method, namely Style-aligned Distribution Biasing (SDB), to improve the capacity of black-box attacks on both FR and FAS models.
FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis
Text-to-motion synthesis is a crucial task in computer vision.
Ranked #4 on
Motion Synthesis
on InterHuman
GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision
Nevertheless, current models still encounter two main challenges: modeling depth accurately in the 2D-3D view transformation stage, and overcoming the lack of generalizability issues due to sparse LiDAR supervision.
Efficient Multimodal Large Language Models: A Survey
In the past year, Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning.
MotionMaster: Training-free Camera Motion Transfer For Video Generation
Furthermore, we propose a few-shot camera motion disentanglement method to extract the common camera motion from multiple videos with similar camera motions, which employs a window-based clustering technique to extract the common features in temporal attention maps of multiple videos.
DGMamba: Domain Generalization via Generalized State Space Model
SPR strives to encourage the model to concentrate more on objects rather than context, consisting of two designs: Prior-Free Scanning~(PFS), and Domain Context Interchange~(DCI).
PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering.
Learning Topology Uniformed Face Mesh by Volume Rendering for Multi-view Reconstruction
Our goal is to leverage the superiority of neural volume rendering into multi-view reconstruction of face mesh with consistent topology.
SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
To mitigate the problem of under-fitting, we design a transformer module named Multi-Cycled Transformer(MCT) based on multiple-cycled forwards to more fully exploit the potential of small model parameters.
Test-Time Domain Generalization for Face Anti-Spoofing
Our method, consisting of Test-Time Style Projection (TTSP) and Diverse Style Shifts Simulation (DSSS), effectively projects the unseen data to the seen domain space.
Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text
Creating and animating 3D biped cartoon characters is crucial and valuable in various applications.
Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection
Finally, we report the results of popular IAD methods on the Real-IAD dataset, providing a highly challenging benchmark to promote the development of the IAD field.
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse.
DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception
To handle this problem, we propose the first Dynamic Environment MOtion Synthesis framework (DEMOS) to predict future motion instantly according to the current scene, and use it to dynamically update the latent motion for final motion synthesis.
SU-SAM: A Simple Unified Framework for Adapting Segment Anything Model in Underperformed Scenes
To address this issue, we present a simple and unified framework, namely SU-SAM, that can easily and efficiently fine-tune the SAM model with parameter-efficient techniques while maintaining excellent generalizability toward various downstream tasks.
Rethinking Impersonation and Dodging Attacks on Face Recognition Systems
Then, Biased Gradient Adaptation is presented to adapt the adversarial examples to traverse the decision boundaries of both the attacker and victim by adding perturbations favoring dodging attacks on the vacated regions, preserving the prioritized features of the original perturbations while boosting dodging performance.
Continuous Piecewise-Affine Based Motion Model for Image Animation
To address this issue, we propose to model motion from the source image to the driving frame in highly-expressive diffeomorphism spaces.
Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization
Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding.
BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model
To this end, we propose Scalable Bias-Mode Attention Mask (BA-SAM) to enhance SAM's adaptability to varying image resolutions while eliminating the need for structure modifications.
Re-thinking Data Availability Attacks Against Deep Neural Networks
In this paper we re-examine the existing availability attack methods and propose a novel two-stage min-max-min optimization paradigm to generate robust unlearnable noise.
Rethinking Generalizable Face Anti-spoofing via Hierarchical Prototype-guided Distribution Refinement in Hyperbolic Space
In detail we propose the Hierarchical Prototype Learning to simultaneously guide domain alignment and improve the discriminative ability via constraining the multi-level relations between prototypes and instances in hyperbolic space.
A Theory of Non-Acyclic Generative Flow Networks
GFlowNets is a novel flow-based method for learning a stochastic policy to generate objects via a sequence of actions and with probability proportional to a given positive reward.
COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities.
Generalized Category Discovery in Semantic Segmentation
This paper explores a novel setting called Generalized Category Discovery in Semantic Segmentation (GCDSS), aiming to segment unlabeled images given prior knowledge from a labeled set of base classes.
Diverse Target and Contribution Scheduling for Domain Generalization
In specific, DTS employs distinct soft labels as training targets to account for various feature distributions across domains and thereby mitigates the gradient conflicts, and DCB dynamically balances the contributions of source domains by ensuring a fair decline in losses of different source domains.
Rethinking Domain Generalization: Discriminability and Generalizability
On the one hand, the simultaneous attainment of generalizability and discriminability of features presents a complex challenge, often entailing inherent contradictions.
Contrastive Pseudo Learning for Open-World DeepFake Attribution
The challenge in sourcing attribution for forgery faces has gained widespread attention due to the rapid development of generative techniques.
Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region
To solve the problem, we propose Compositional Neural Painter, a novel stroke-based rendering framework which dynamically predicts the next painting region based on the current canvas, instead of dividing the image plane uniformly into painting regions.
Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption
To address these problems, we propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss, which targets different learning objectives at distinct training stages of the diffusion model.
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment
3D panoptic segmentation is a challenging perception task that requires both semantic segmentation and instance segmentation.
RFENet: Towards Reciprocal Feature Evolution for Glass Segmentation
Glass-like objects are widespread in daily life but remain intractable to be segmented for most existing methods.
Towards Generalizable Data Protection With Transferable Unlearnable Examples
One of the crucial factors contributing to this success has been the access to an abundance of high-quality data for constructing machine learning models.
Re-thinking Data Availablity Attacks Against Deep Neural Networks
The unauthorized use of personal data for commercial purposes and the clandestine acquisition of private data for training machine learning models continue to raise concerns.
Instance-Aware Domain Generalization for Face Anti-Spoofing
To address these issues, we propose a novel perspective for DG FAS that aligns features on the instance level without the need for domain labels.
Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
In this work, we investigate the problem of creating high-fidelity 3D content from only a single image.
CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame
CRIN directly takes the coordinates of points as input and transforms local points into rotation-invariant representations via centrifugal reference frames.
Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection
Specifically, we first propose a normality recall memory (NR Memory) to strengthen the normality of student-generated features by recalling the stored normal information.
Ranked #13 on
Anomaly Detection
on MVTec AD
Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling
In this paper, we propose a space decoupling (SD) algorithm to decouple the feature space into a pair of complementary subspaces, i. e., the stability space I, and the plasticity space R. I is established by conducting space intersection between the historic and current feature space, and thus I contains more task-shared bases.
DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution
Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation.
Rethinking Implicit Neural Representations for Vision Learners
Existing INRs methods suffer from two problems: 1) narrow theoretical definitions of INRs are inapplicable to high-level tasks; 2) lack of representation capabilities to deep networks.
Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning
In this paper, we propose a novel cross-modality weakly supervised method for 3D segmentation, incorporating complementary information from unlabeled images.
3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs.
Prototype-Aware Heterogeneous Task for Point Cloud Completion
Moreover, for effective training, we consider difficulty-based sampling strategy to encourage the network to pay more attention to some partial point clouds with fewer geometric information.
Boosting Night-time Scene Parsing with Learnable Frequency
Based on this, we propose to exploit the image frequency distributions for night-time scene parsing.
Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofing
Existing DG-based FAS approaches always capture the domain-invariant features for generalizing on the various unseen domains.
Generative Domain Adaptation for Face Anti-Spoofing
Most existing UDA FAS methods typically fit the trained models to the target domain via aligning the distribution of semantic high-level features.
Variational Distillation for Multi-View Learning
Information Bottleneck (IB) based multi-view learning provides an information theoretic principle for seeking shared information contained in heterogeneous data descriptions.
MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet
U-Nets have achieved tremendous success in medical image segmentation.
LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints
An asymmetric keypoint locator, including an unsupervised multi-scale keypoint detector and a complete keypoint generator, is proposed for localizing aligned keypoints from complete and partial point clouds.
CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning
We propose a new encoder which embeds real faces into Z+ space and proposes a dual-path training strategy to better cope with the adapted decoder and eliminate the artifacts.
Rethinking Efficient Lane Detection via Curve Modeling
This paper presents a novel parametric curve-based method for lane detection in RGB images.
Ranked #2 on
Lane Detection
on LLAMAS
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.
Ranked #5 on
Video Object Detection
on ImageNet VID
(using extra training data)
HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization
To address the huge labeling cost in large-scale point cloud semantic segmentation, we propose a novel hybrid contrastive regularization (HybridCR) framework in weakly-supervised setting, which obtains competitive performance compared to its fully-supervised counterpart.
ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation
The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation.
Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofing
However, the improvement is still limited by two issues: 1) It is difficult to perfectly map all faces to a shared feature space.
Exploring Versatile Prior for Human Motion via Motion Frequency Guidance
Prior plays an important role in providing the plausible constraint on human motion.
Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine
Pixel-level 2D object semantic understanding is an important topic in computer vision and could help machine deeply understand objects (e. g. functionality and affordance) in our daily life.
Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization
In this paper, we propose a novel and fully end-to-end trainable approach, called regional contrastive consistency regularization (RCCR) for domain adaptive semantic segmentation.
Spatiotemporal Inconsistency Learning for DeepFake Video Detection
To address this issue, we term this task as a Spatial-Temporal Inconsistency Learning (STIL) process and instantiate it into a novel STIL block, which consists of a Spatial Inconsistency Module (SIM), a Temporal Inconsistency Module (TIM), and an Information Supplement Module (ISM).
PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation
Extensive experiments demonstrate that our method can soundly boost the performance on both cross-domain object detection and segmentation for state-of-the-art techniques.
Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling
Inspired by this, we propose a novel semi-supervised framework based on pseudo-labeling for outdoor 3D object detection tasks.
Self-Adversarial Disentangling for Specific Domain Adaptation
In this paper, we study a practical setting called Specific Domain Adaptation (SDA) that aligns the source and target domains in a demanded-specific dimension.
Image-to-Image Translation on Cityscapes-to-Foggy Cityscapes
object-detection
+3
Context-Aware Mixup for Domain Adaptive Semantic Segmentation
The generated contextual mask is critical in this work and will guide the context-aware domain mixup on three different levels.
Ranked #5 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing
However, little attention has been paid to the feature extraction process for the FAS task, especially the influence of normalization, which also has a great impact on the generalization of the learned representation.
Dual Reweighting Domain Generalization for Face Presentation Attack Detection
Face anti-spoofing approaches based on domain generalization (DG) have drawn growing attention due to their robustness for unseen scenarios.
Novelty Detection via Contrastive Learning with Negative Data Augmentation
Moreover, our model is more stable for training in a non-adversarial manner, compared to other adversarial based novelty detection methods.
End-to-End Video Object Detection with Spatial-Temporal Transformers
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
Our method can significantly improve the backbones in all three datasets.
Ranked #2 on
Semantic Segmentation
on Semantic3D
Contrastive Learning for Compact Single Image Dehazing
In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
Ranked #5 on
Image Dehazing
on RS-Haze
Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification
The Information Bottleneck (IB) provides an information theoretic principle for representation learning, by retaining all information relevant for predicting label while minimizing the redundancy.
Cross-Modality Person Re-identification
Cross-Modal Person Re-Identification
+3
"Forget" the Forget Gate: Estimating Anomalies in Videos using Self-contained Long Short-Term Memory Networks
Abnormal event detection is a challenging task that requires effectively handling intricate features of appearance and motion.
PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
Spherical Voxel Convolution and Point Re-sampling are proposed to extract rotation invariant features for each point.
Learn from Concepts: Towards the Purified Memory for Few-shot Learning
In this paper, we present a novel purified memory mechanism that simulates the recognition process of human beings.
Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds
Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects.
Weakly-Supervised Saliency Detection via Salient Object Subitizing
This allows the supervision to be aligned with the property of saliency detection, where the salient objects of an image could be from more than one class.
Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes
In the work, we disentangle the direct offset into Local Canonical Coordinates (LCC), box scales and box orientations.
Face Anti-Spoofing Via Disentangled Representation Learning
Face anti-spoofing is crucial to security of face recognition systems.
Brain Tumor Anomaly Detection via Latent Regularized Adversarial Network
The brain structure in the collected data is complicated, thence, doctors are required to spend plentiful energy when diagnosing brain abnormalities.
Semi-supervised Anomaly Detection
Supervised Anomaly Detection
Spoof Face Detection Via Semi-Supervised Adversarial Training
To capture the underlying structure of live faces data in latent representation space, we propose to train the live face data only, with a convolutional Encoder-Decoder network acting as a Generator.
NTIRE 2020 Challenge on NonHomogeneous Dehazing
We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor.
Fine-Grained Expression Manipulation via Structured Latent Space
Most existing expression manipulation methods resort to discrete expression labels, which mainly edit global expressions and ignore the manipulation of fine details.
Semantic Correspondence via 2D-3D-2D Cycle
Visual semantic correspondence is an important topic in computer vision and could help machine understand objects in our daily life.
Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
Guided by this mask, we propose a ClassOut strategy to realize effective regional consistency in a fine-grained manner.
DMT: Dynamic Mutual Training for Semi-Supervised Learning
Instead, leveraging inter-model disagreement between different models is a key to locate pseudo label errors.
SiTGRU: Single-Tunnelled Gated Recurrent Unit for Abnormality Detection
In this paper, we propose a novel version of Gated Recurrent Unit (GRU), called Single Tunnelled GRU for abnormality detection.
Monocular Human Pose and Shape Reconstruction using Part Differentiable Rendering
In this paper, we introduce body part segmentation as critical supervision.
Ranked #103 on
3D Human Pose Estimation
on Human3.6M
(PA-MPJPE metric)
J$\hat{\text{A}}$A-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention
Moreover, to extract precise local features, we propose an adaptive attention learning module to refine the attention map of each AU adaptively.
Night-time Scene Parsing with a Large Real Dataset
Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions.
KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
Detecting 3D objects keypoints is of great interest to the areas of both graphics and computer vision.
Anomaly Detection by One Class Latent Regularized Networks
Anomaly detection is a fundamental problem in computer vision area with many real-world applications.
Acoustic anomaly detection via latent regularized gaussian mixture generative adversarial networks
Acoustic anomaly detection aims at distinguishing abnormal acoustic signals from the normal ones.
Novelty Detection via Non-Adversarial Generative Network
One-class novelty detection is the process of determining if a query example differs from the training examples (the target class).
SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
Besides local features, global information plays an essential role in semantic segmentation, while recent works usually fail to explicitly extract the meaningful global information and make full use of it.
Human Correspondence Consensus for 3D Object Semantic Understanding
Semantic understanding of 3D objects is crucial in many applications such as object manipulation.
Explicit Facial Expression Transfer via Fine-Grained Representations
Instead of using an intermediate estimated guidance, we propose to explicitly transfer facial expression by directly mapping two unpaired input images to two synthesized images with swapped expressions.
FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds
We then introduce a proposal generation network to predict 3D region proposals from the generated maps and further extrude objects of interest from the whole point cloud.
Unconstrained Facial Action Unit Detection via Latent Feature Domain
Due to the combination of source AU-related information and target AU-free information, the latent feature domain with transferred source label can be learned by maximizing the target-domain AU detection performance.
Efficient Super Resolution Using Binarized Neural Network
As a way to significantly reduce model size and computation time, binarized neural network has only been shown to excel on semantic-level tasks such as image classification and recognition.
Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution
Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown.
Facial Action Unit Detection Using Attention and Relation Learning
By finding the region of interest of each AU with the attention mechanism, AU-related local features can be captured.
Deep Multi-Center Learning for Face Alignment
Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks.
Ranked #3 on
Face Alignment
on AFLW2000
Deep attention-guided fusion network for lesion segmentation
We participated the Task 1: Lesion Segmentation.
DRPose3D: Depth Ranking in 3D Human Pose Estimation
In this paper, we propose a two-stage depth ranking based method (DRPose3D) to tackle the problem of 3D human pose estimation.
Mask-aware Photorealistic Face Attribute Manipulation
The task of face attribute manipulation has found increasing applications, but still remains challeng- ing with the requirement of editing the attributes of a face image while preserving its unique details.
Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment
Facial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection.
Ranked #7 on
Facial Action Unit Detection
on DISFA
Multi-Scale Video Frame-Synthesis Network with Transitive Consistency Loss
Traditional approaches to interpolate/extrapolate frames in a video sequence require accurate pixel correspondences between images, e. g., using optical flow.
Learning deep representation from coarse to fine for face alignment
In this paper, we propose a novel face alignment method that trains deep convolutional network from coarse to fine.
