Search Results for author:
Found 99 papers, 49 papers with code
API-Net: Robust Generative Classifier via a Single Discriminator
On the contrary, a discriminative classifier only models the conditional distribution of labels given inputs, but benefits from effective optimization owing to its succinct structure.
Wavelet-Based Dual-Branch Network for Image Demoiréing
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality.
Large-Scale Few-Shot Learning via Multi-Modal Knowledge Discovery
It is a challenging problem since (1) the identifying process is susceptible to over-fitting with limited samples of an object, and (2) the sample imbalance between a base (known knowledge) category and a novel category is easy to bias the recognition results.
MagicEraser: Erasing Any Objects via Semantics-Aware Control
However, the object erasure task, which is in increasing demand, aims to erase objects and generate harmonious background.
TraDiffusion: Trajectory-Based Training-Free Image Generation
In this work, we propose a training-free, trajectory-based controllable T2I approach, termed TraDiffusion.
UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation
In this work we design a Unified Voxelization framework for explicit learning of scene representations, dubbed UniVoxel, which allows for efficient modeling of the geometry, materials and illumination jointly, thereby accelerating the inverse rendering significantly.
Correctable Landmark Discovery via Large Models for Vision-Language Navigation
To mitigate the noise in the priors due to the lack of visual constraints, we introduce a learnable cooccurrence scoring module, which corrects the importance of each cooccurrence according to actual observations for accurate landmark discovery.
MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections
To tackle this problem, we present MirrorGaussian, the first method for mirror scene reconstruction with real-time rendering based on 3D Gaussian Splatting.
MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck
One can learn this representation by maximizing the mutual information between the representation and the supervised view while eliminating superfluous information.
Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation
To mitigate these issues, we propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information. Specifically, we leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings.
VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed.
Diffusion Model-Based Image Editing: A Survey
In this survey, we provide an exhaustive overview of existing methods using diffusion models for image editing, covering both theoretical and practical aspects in the field.
UV-IDM: Identity-Conditioned Latent Diffusion Model for Face UV-Texture Generation
To solve these problems we introduce an Identity-Conditioned Latent Diffusion Model for face UV-texture generation (UV-IDM) to generate photo-realistic textures based on the Basel Face Model (BFM).
ZONE: Zero-Shot Instruction-Guided Local Editing
We then propose a Region-IoU scheme for precise image layer extraction from an off-the-shelf segment model.
Learning Unorthogonalized Matrices for Rotation Estimation
Estimating 3D rotations is a common procedure for 3D computer vision.
Ranked #15 on
3D Human Pose Estimation
on 3DPW
CoSeR: Bridging Image and Language for Cognitive Super-Resolution
We achieve this by marrying image appearance and language understanding to generate a cognitive embedding, which not only activates prior information from large text-to-image diffusion models but also facilitates the generation of high-quality reference images to optimize the SR process.
GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning
To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis.
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification
The conventional few-shot classification aims at learning a model on a large labeled base dataset and rapidly adapting to a target dataset that is from the same distribution as the base dataset.
IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts
Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to guide 3D object generation.
Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network
We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks, which enables the correction factor gamma to be learned in a coarse to elaborate manner via adaptively perceiving the deviated illumination.
Generalizing Event-Based Motion Deblurring in Real-World Scenarios
Event-based motion deblurring has shown promising results by exploiting low-latency events.
MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation
To address this issue, we propose MixReorg, a novel and straightforward pre-training paradigm for semantic segmentation that enhances a model's ability to reorganize patches mixed across images, exploring both local visual relevance and global semantic coherence.
Video Frame Interpolation with Stereo Event and Intensity Camera
The stereo event-intensity camera setup is widely applied to leverage the advantages of both event cameras with low latency and intensity cameras that capture accurate brightness and texture information.
WaveDM: Wavelet-Based Diffusion Models for Image Restoration
Latest diffusion-based methods for many image restoration tasks outperform traditional models, but they encounter the long-time inference problem.
AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning
Text consists of a category name and a fixed number of learnable parameters which are selected from our designed attribute word bank and serve as attributes.
Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment
However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant information in images, and (2) the alignment between the visual and language feature distributions is difficult.
Controllable Mind Visual Diffusion Model
Brain signal visualization has emerged as an active research area, serving as a critical interface between the human visual system and computer vision models.
AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions
In recent years, videos and images in 720p (HD), 1080p (FHD) and 4K (UHD) resolution have become more popular for display devices such as TVs, mobile phones and VR.
Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
In MOTOR, we combine two kinds of basic medical knowledge, i. e., general and specific knowledge, in a complementary manner to boost the general pretraining process.
Face Animation with an Attribute-Guided Diffusion Model
Face animation has achieved much progress in computer vision.
Recovering Continuous Scene Dynamics from A Single Blurry Image with Events
This paper aims at demystifying a single motion-blurred image with events and revealing temporally continuous scene dynamics encrypted behind motion blurs.
Implicit Diffusion Models for Continuous Super-Resolution
IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework, where the implicit neural representation is adopted in the decoding process to learn continuous-resolution representation.
Ranked #1 on
Image Super-Resolution
on CelebA-HQ 128x128
Learning to Super-Resolve Blurry Images with Events
Super-Resolution from a single motion Blurred image (SRB) is a severely ill-posed problem due to the joint degradation of motion blurs and low spatial resolution.
Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation
Vision-Language Navigation (VLN) is a challenging task which requires an agent to align complex visual observations to language instructions to reach the goal position.
ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency
Specifically, we first propose text-to-views consistency modeling to learn correspondence for multiple views of the same input image.
SmartAssign: Learning a Smart Knowledge Assignment Strategy for Deraining and Desnowing
Extensive experiments on seven benchmark datasets verify that proposed SmartAssign explores effective connection between rain and snow, and improves the performances of both deraining and desnowing apparently.
PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval
The parallel isomeric attention module is used as the video encoder, which consists of two parallel branches modeling the spatial-temporal information of videos from both patch and frame levels.
Ranked #3 on
Video Retrieval
on MSR-VTT-1kA
HiVLP: Hierarchical Interactive Video-Language Pre-Training
However, compared to image-language pre-training, VLP has lagged far behind due to the lack of large amounts of video-text pairs.
CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval
Pre-training a vison-language model and then fine-tuning it on downstream tasks have become a popular paradigm.
Feature Calibration Network for Occluded Pedestrian Detection
FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection, and is implemented as a self-paced feature learning framework with a self-activation (SA) module and a feature calibration (FC) module.
CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation
Then in the Sentence-Mask Alignment (SMA) module, the masks are weighted by the sentence embedding to localize the referred object, and finally projected back to aggregate the pixels for the target.
FNeVR: Neural Volume Rendering for Face Animation
In FNeVR, we design a 3D Face Volume Rendering (FVR) module to enhance the facial details for image rendering.
Structure-Preserving Graph Representation Learning
To this end, we propose a novel Structure-Preserving Graph Representation Learning (SPGRL) method, to fully capture the structure information of graphs.
Removing Rain Streaks via Task Transfer Learning
Inspired by our studies, we propose to remove rain by learning favorable deraining representations from other connected tasks.
Anti-Retroactive Interference for Lifelong Learning
Second, according to the similarity between incremental knowledge and base knowledge, we design an adaptive fusion of incremental knowledge, which helps the model allocate capacity to the knowledge of different difficulties.
Low-Light Video Enhancement with Synthetic Event Guidance
Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving.
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation
Top-down methods dominate the field of 3D human pose and shape estimation, because they are decoupled from human detection and allow researchers to focus on the core problem.
Ranked #1 on
Unsupervised 3D Human Pose Estimation
on Human3.6M
(PA-MPJPE metric)
Self-Supervision Can Be a Good Few-Shot Learner
Specifically, we maximize the mutual information (MI) of instances and their representations with a low-bias MI estimator to perform self-supervised pre-training.
cross-domain few-shot learning
Unsupervised Few-Shot Image Classification
+1
ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
Vision-Language Navigation (VLN) is a challenging task that requires an embodied agent to perform action-level modality alignment, i. e., make instruction-asked actions sequentially in complex visual environments.
Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection
To tackle this problem, we propose a depth solving system that fully explores the visual clues from the subtasks in M3OD and generates multiple estimations for the depth of each target.
Prompt Distribution Learning
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks.
Learning Enriched Illuminants for Cross and Single Sensor Color Constancy
Color constancy aims to restore the constant colors of a scene under different illuminants.
Neural Architecture Search With Representation Mutual Information
Building upon RMI, we further propose a new search algorithm termed RMI-NAS, facilitating with a theorem to guarantee the global optimal of the searched architecture.
SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers
For zero-shot image restoration, we design a novel model, termed SiamTrans, which is constructed by Siamese transformers, encoders, and decoders.
IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase.
Motion Deblurring with Real Events
In this paper, we propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the performance degradation caused by data inconsistency.
Wavelet-Based Network For High Dynamic Range Imaging
The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details.
Multi-Target Domain Adaptation with Collaborative Consistency Learning
To obtain a single model that works across multiple target domains, we propose to simultaneously learn a student model which is trained to not only imitate the output of each expert on the corresponding target domain, but also to pull different expert close to each other with regularization on their weights.
Ranked #4 on
Domain Adaptation
on GTAV to Cityscapes+Mapillary
Uformer: A General U-Shaped Transformer for Image Restoration
Powered by these two designs, Uformer enjoys a high capability for capturing both local and global dependencies for image restoration.
Ranked #3 on
Deblurring
on RSBlur
Towards Compact CNNs via Collaborative Compression
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression.
Multiple instance active learning for object detection
Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection.
Ranked #1 on
Active Object Detection
on MS COCO
ReCU: Reviving the Dead Weights in Binary Neural Networks
We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error.
Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain.
Ranked #1 on
Domain Adaptation
on GTA5+Synscapes to Cityscapes
Multi-Source Unsupervised Domain Adaptation
Semantic Segmentation
+1
Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
To address the task of SSDA, a novel framework based on dual-level domain mixing is proposed.
Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images.
TRAR: Routing the Attention Spans in Transformer for Visual Question Answering
Due to the superior ability of global dependency modeling, Transformer and its variants have become the primary choice of many vision-and-language tasks.
Active Learning for Lane Detection: A Knowledge Distillation Approach
The experiments show that our method achieves new state-of-the-art on the lane detection benchmarks.
Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-ID
To avoid such problematic models in occluded person ReID, we propose the Occlusion-Aware Mask Network (OAMN).
Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs
In this paper, we propose a self-adaptive learning method for demoiréing a high-frequency image, with the help of an additional defocused moiré-free blur image.
Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs
In this paper, we propose a self-adaptive learning method for demoireing a high-frequency image, with the help of an additional defocused moire-free blur image.
Binarized Neural Architecture Search for Efficient Object Recognition
In this paper, binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing.
Light Field View Synthesis via Aperture Disparity and Warping Confidence Map
This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images.
Dual Distribution Alignment Network for Generalizable Person Re-Identification
Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without model updating.
Domain Generalization
Generalizable Person Re-identification
Wavelet-Based Dual-Branch Network for Image Demoireing
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality.
Projection & Probability-Driven Black-Box Attack
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
High-Order Residual Network for Light Field Super-Resolution
In this paper, we propose a novel high-order residual network to learn the geometric features hierarchically from the LF for reconstruction.
Context-Transformer: Tackling Object Confusion for Few-Shot Detection
Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors.
SketchyCOCO: Image Generation from Freehand Scene Sketches
We introduce the first method for automatic image generation from scene-level freehand sketches.
Ranked #2 on
Sketch-to-Image Translation
on SketchyCOCO
Filter Sketch for Network Pruning
Our approach, referred to as FilterSketch, encodes the second-order information of pre-trained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure.
Multiple Anchor Learning for Visual Object Detection
In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector.
Ranked #117 on
Object Detection
on COCO test-dev
GBCNs: Genetic Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs
The BGA method is proposed to modify the binary process of GBCNs to alleviate the local minima problem, which can significantly improve the performance of 1-bit DCNNs.
Binarized Neural Architecture Search
A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models.
An End-to-End Foreground-Aware Network for Person Re-Identification
By presenting a target attention loss, the pedestrian features extracted from the foreground branch become more insensitive to the backgrounds, which greatly reduces the negative impacts of changing backgrounds on matching an identical across different camera views.
Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation
The CiFs can be easily incorporated into existing deep convolutional neural networks (DCNNs), which leads to new Circulant Binary Convolutional Networks (CBCNs).
Unsupervised Image Super-Resolution with an Indirect Supervised Path
The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image.
RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs
Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications.
Bayesian Optimized 1-Bit CNNs
Deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models.
Multinomial Distribution Learning for Effective Neural Architecture Search
Therefore, NAS can be transformed to a multinomial distribution learning problem, i. e., the distribution is optimized to have a high expectation of the performance.
Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression
The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression.
Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation
The advancement of deep convolutional neural networks (DCNNs) has driven significant improvement in the accuracy of recognition systems for many computer vision tasks.
Modulated Convolutional Networks
In this paper, we propose new Modulated Convolutional Networks (MCNs) to improve the portability of CNNs via binarized filters.
Memory Attention Networks for Skeleton-based Action Recognition
Specifically, the TARM is deployed in a residual learning module that employs a novel attention learning network to recalibrate the temporal attention of frames in a skeleton sequence.
Ranked #95 on
Skeleton Based Action Recognition
on NTU RGB+D
One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
Compression artifacts reduction (CAR) is a challenging problem in the field of remote sensing.
Gabor Convolutional Networks
Steerable properties dominate the design of traditional filters, e. g., Gabor filters, and endow features the capability of dealing with spatial transformations.
A Maximum Entropy Feature Descriptor for Age Invariant Face Recognition
In this paper, we propose a new approach to overcome the representation and matching problems in age invariant face recognition.
Separation of Line Drawings Based on Split Faces for 3D Object Reconstruction
Reconstructing 3D objects from single line drawings is often desirable in computer vision and graphics applications.
Transitive Distance Clustering with K-Means Duality
We propose a very intuitive and simple approximation for the conventional spectral clustering methods.
The BeiHang Keystroke Dynamics Authentication System
Keystroke Dynamics is an important biometric solution for person authentication.
