Search Results for author:
Found 77 papers, 39 papers with code
Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning
Ultimately, our work bridges cognitive science and computer vision by analyzing the internal representations of a computational model trained on an infant's visual and linguistic inputs.
ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation
Instance segmentation algorithms in remote sensing are typically based on conventional methods, limiting their application to seen scenarios and closed-set predictions.
Video Set Distillation: Information Diversification and Temporal Densification
Video \textbf{sets} have two dimensions of redundancies: within-sample and inter-sample redundancies.
Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers
Recent advancements in deep learning have shown impressive results in image and video denoising, leveraging extensive pairs of noisy and noise-free data for supervision.
SoftShadow: Leveraging Penumbra-Aware Soft Masks for Shadow Removal
In view of this, inspired by the physical model of shadow formation, we introduce novel soft shadow masks specifically designed for shadow removal.
Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography
The integration of miniaturized spectrometers into mobile devices offers new avenues for image quality enhancement and facilitates novel downstream tasks.
SegPoint: Segment Any Point Cloud via Large Language Model
Despite significant progress in 3D point cloud segmentation, existing methods primarily address specific tasks and depend on explicit instructions to identify targets, lacking the capability to infer and understand implicit user intentions in a unified framework.
Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey
In this paper, we are the first to provide a comprehensive survey to cover various aspects ranging from technical details to applications.
Integrating Clinical Knowledge into Concept Bottleneck Models
Concept bottleneck models (CBMs), which predict human-interpretable concepts (e. g., nucleus shapes in cell images) before predicting the final output (e. g., cell type), provide insights into the decision-making processes of the model.
From Chaos to Clarity: 3DGS in the Dark
Our study reveals that 3D Gaussian Splatting (3DGS) is particularly susceptible to this noise, leading to numerous elongated Gaussian shapes that overfit the noise, thereby significantly degrading reconstruction quality and reducing inference speed, especially in scenarios with limited views.
ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Model
Recently, 3D Gaussian Splatting (3DGS) has become a promising framework for novel view synthesis, offering fast rendering speeds and high fidelity.
DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild
To our knowledge, DP-IQA is the first method to apply pre-trained diffusion priors in blind IQA.
Evolving Storytelling: Benchmarks and Methods for New Character Customization with Diffusion Models
Additionally, to mitigate the character confusion of generated results, we propose EpicEvo, a method that customizes a diffusion-based visual story generation model with a single story featuring the new characters seamlessly integrating them into established character dynamics.
EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model
In contrast, long sequential videos can reveal authentic emotions; 2) Previous studies commonly utilize various signals such as facial, speech, and even sensitive biological signals (e. g., electrocardiogram).
Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI
Starting from decomposing the original maximum-a-posteriori problem of accelerated MRI, we present a rigorous derivation of the proposed PDAC framework, which could be further unfolded into an end-to-end trainable network.
Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks
This is primarily due to the unique characteristic of spatially varying illumination within shadow images.
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
Diffusion models have proven to be highly effective in image and video generation; however, they still face composition challenges when generating images of varying sizes due to single-scale training data.
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection
To address these issues we propose a simple yet effective Category-aware Knowledge Distillation and Pruning (CaKDP) framework for compressing 3D detectors.
SinSR: Diffusion-Based Image Super-Resolution in a Single Step
Extensive experiments conducted on synthetic and real-world datasets demonstrate that the proposed method can achieve comparable or even superior performance compared to both previous SOTA methods and the teacher model, in just one sampling step, resulting in a remarkable up to x10 speedup for inference.
Spectral Convergence of Complexon Shift Operators
We recall the notion of a complexon as the limit of a simplicial complex sequence [1].
ExposureDiffusion: Learning to Expose for Low-light Image Enhancement
Different from a vanilla diffusion model that has to perform Gaussian denoising, with the injected physics-based exposure model, our restoration process can directly start from a noisy image instead of pure noise.
Ranked #1 on
Image Denoising
on Image Denoising on SID x300
Enhancing Low-Light Images Using Infrared-Encoded Images
In this work, we propose a novel approach to increase the visibility of images captured under low-light environments by removing the in-camera infrared (IR) cut-off filter, which allows for the capture of more photons and results in improved signal-to-noise ratio due to the inclusion of information from the IR spectrum.
WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes
We then annotated ten thousand WBC images with these attributes.
Beyond Learned Metadata-based Raw Image Reconstruction
Besides, we propose a novel design of the context model, which can better predict the order masks of encoding/decoding based on both the sRGB image and the masks of already processed features.
Denoising Diffusion Models for Plug-and-Play Image Restoration
Although diffusion models have shown impressive performance for high-quality image synthesis, their potential to serve as a generative denoiser prior to the plug-and-play IR methods remains to be further explored.
Towards Adversarially Robust Continual Learning
Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real world.
Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation
The second module compares the outputs of augmented data from the current model to the outputs of weakly augmented data from the source model, forming a novel consistency regularization on the model to alleviate the accumulation of prediction errors.
Unsupervised Deep Digital Staining For Microscopic Cell Images Via Knowledge Distillation
In this work, we propose a novel unsupervised deep learning framework for the digital staining of cell images using knowledge distillation and generative adversarial networks (GANs).
Benchmarking White Blood Cell Classification Under Domain Shift
Recognizing the types of white blood cells (WBCs) in microscopic images of human blood smears is a fundamental task in the fields of pathology and hematology.
Raw Image Reconstruction with Learned Compact Metadata
While raw images exhibit advantages over sRGB images (e. g., linearity and fine-grained quantization level), they are not widely used by common users due to the large storage requirements.
Removing Image Artifacts From Scratched Lens Protectors
Removing image artifacts from the scratched lens protector is inherently challenging due to the occasional flare artifacts and the co-occurring interference within mixed artifacts.
ShadowFormer: Global Context Helps Image Shadow Removal
It is still challenging for the deep shadow removal model to exploit the global contextual correlation between shadow and non-shadow regions.
Ranked #1 on
Shadow Removal
on ISTD
Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal
Recent deep learning methods have achieved superior results in shadow removal.
Frequency Guidance Matters in Few-Shot Learning
Few-shot classification aims to learn a discriminative feature representation to recognize unseen classes with few labeled support samples.
sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model
Modeling and synthesizing real noise in the standard RGB (sRGB) domain is challenging due to the complicated noise distribution.
Temporal Output Discrepancy for Loss Estimation-based Active Learning
Inspired by the fact that the samples with higher loss are usually more informative to the model than the samples with lower loss, in this paper we present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss.
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
Recent deep learning methods have achieved promising results in image shadow removal.
Ranked #10 on
Shadow Removal
on ISTD+
Making Your First Choice: To Address Cold Start Problem in Vision Active Learning
However, we uncover a striking contradiction to this promise: active learning fails to select data as efficiently as random selection at the first few choices.
Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning
We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections.
REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration
To this end, we propose a novel deep reinforcement learning (DRL) based PnP framework, dubbed RePNP, by leveraging a light-weight DRL-based denoiser for robust image restoration tasks.
ABCDE: An Agent-Based Cognitive Development Environment
How can the most common 1, 000 concepts (89\% of everyday use) be learnt in a naturalistic children's setting?
Learning Nonlocal Sparse and Low-Rank Models for Image Compressive Sensing
Furthermore, we present a unified framework for incorporating various GSR and LR models and discuss the relationship between GSR and LR models.
Enhancing Low-Light Images in Real World via Cross-Image Disentanglement
Images captured in the low-light condition suffer from low visibility and various imaging artifacts, e. g., real noise.
FINO: Flow-based Joint Image and Noise Model
One of the fundamental challenges in image restoration is denoising, where the objective is to estimate the clean image from its noisy measurements.
Adversarial Purification through Representation Disentanglement
Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment.
Disentangled Feature Representation for Few-shot Image Classification
In this work, we propose a novel Disentangled Feature Representation framework, dubbed DFR, for few-shot learning applications.
Variational Disentanglement for Domain Generalization
Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain.
PIP: Physical Interaction Prediction via Mental Simulation with Span Selection
However, there is a lack of intuitive physics models that are tested on long physical interaction sequences with multiple interactions among different objects.
Ranked #1 on
Semantic Object Interaction Classification
on SPACE
ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
Low-light image enhancement (LLIE) is a pervasive yet challenging problem, since: 1) low-light measurements may vary due to different imaging conditions in practice; 2) images can be enlightened subjectively according to diverse preferences by each individual.
R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery
To benchmark the effectiveness of reinforcement learning in R3L, we train a recurrent neural network with the same architecture for residual recovery using the deterministic loss, thus to analyze how the two different training strategies affect the denoising performance.
Ranked #1 on
Image Denoising
on BSD68 sigma30
Reconciliation of Statistical and Spatial Sparsity For Robust Image and Image-Set Classification
Recent image classification algorithms, by learning deep features from large-scale datasets, have achieved significantly better results comparing to the classic feature-based approaches.
Systematic Analysis and Removal of Circular Artifacts for StyleGAN
StyleGAN is one of the state-of-the-art image generators which is well-known for synthesizing high-resolution and hyper-realistic face images.
Recent Advances in Adversarial Training for Adversarial Robustness
Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models.
Joint Dimensionality Reduction for Separable Embedding Estimation
In this paper, we propose a supervised dimensionality reduction method that learns linear embeddings jointly for two feature vectors representing data of different modalities or data from distinct types of entities.
Feature Distillation With Guided Adversarial Contrastive Learning
In this paper, we propose a novel approach called Guided Adversarial Contrastive Distillation (GACD), to effectively transfer adversarial robustness from teacher to student with features.
Removing Backdoor-Based Watermarks in Neural Networks with Limited Data
In this paper, we benchmark the robustness of watermarking, and propose a novel backdoor-based watermark removal framework using limited data, dubbed WILD.
Generating Person Images with Appearance-aware Pose Stylizer
Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e. g., appearance, pose, foreground, background, local details, global structures, etc.
Attentive Graph Neural Networks for Few-Shot Learning
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks.
Exploiting Non-Local Priors via Self-Convolution For Highly-Efficient Image Restoration
Experimental results demonstrate that (1) Self-Convolution can significantly speed up most of the popular non-local image restoration algorithms, with two-fold to nine-fold faster block matching, and (2) the proposed multi-modality image restoration scheme achieves superior denoising results in both efficiency and effectiveness on RGB-NIR images.
Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling On-the-Fly for Moving Object Detection
Robust Principal Component Analysis (RPCA), as one of the most popular moving object modelling methods, aims to separate the temporally varying (i. e., moving) foreground objects from the static background in video, assuming the background frames to be low-rank while the foreground to be spatially sparse.
The Power of Triply Complementary Priors for Image Compressive Sensing
In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely \textit{external} and \textit{internal}, \textit{deep} and \textit{shallow}, and \textit{local} and \textit{non-local} priors.
A Set-Theoretic Study of the Relationships of Image Models and Priors for Restoration Problems
Furthermore, we relate the denoising performance improvement by combining multiple models, to the image model relationships.
Parameter-Free Style Projection for Arbitrary Style Transfer
This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs.
Segmentation-Aware Image Denoising without Knowing True Segmentation
Several recent works discussed application-driven image restoration neural networks, which are capable of not only removing noise in images but also preserving their semantic-aware details, making them suitable for various high-level computer vision tasks as the pre-processing step.
Transform Learning for Magnetic Resonance Image Reconstruction: From Model-based Learning to Building Neural Networks
The model could be pre-learned from datasets, or learned simultaneously with the reconstruction, i. e., blind CS (BCS).
Connecting Image Denoising and High-Level Vision Tasks via Deep Learning
Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation.
The Power of Complementary Regularizers: Image Recovery via Transform Learning and Low-Rank Modeling
Recent works on adaptive sparse and on low-rank signal modeling have demonstrated their usefulness in various image / video processing applications.
From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image Restoration
Towards this end, we first obtain a good reference of the original image groups by using the image NSS prior, and then the rank residual of the image groups between this reference and the degraded image is minimized to achieve a better estimate to the desired image.
Non-Local Recurrent Network for Image Restoration
The main contributions of this work are: (1) Unlike existing methods that measure self-similarity in an isolated manner, the proposed non-local module can be flexibly integrated into existing deep networks for end-to-end training to capture deep feature correlation between each location and its neighborhood.
Ranked #1 on
Grayscale Image Denoising
on Set12 sigma30
VIDOSAT: High-dimensional Sparsifying Transform Learning for Online Video Denoising
Transform learning methods involve cheap computations and have been demonstrated to perform well in applications such as image denoising and medical image reconstruction.
Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising
In this work, we propose a novel video denoising method, based on an online tensor reconstruction scheme with a joint adaptive sparse and low-rank model, dubbed SALT.
A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization
Sparse coding has achieved a great success in various image processing tasks.
When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
Conventionally, image denoising and high-level vision tasks are handled separately in computer vision.
A Comparative Study for the Nuclear Norms Minimization Methods
Inspired by enhancing sparsity of the weighted L1-norm minimization in comparison with L1-norm minimization in sparse representation, we thus explain that WNNM is more effective than NMM.
Machine Learning Techniques and Applications For Ground-based Image Analysis
Ground-based whole sky cameras have opened up new opportunities for monitoring the earth's atmosphere.
Robust Single Image Super-Resolution via Deep Networks With Sparse Prior
We demonstrate that a sparse coding model particularly designed for SR can be incarnated as a neural network with the merit of end-to-end optimization over training data.
FRIST - Flipping and Rotation Invariant Sparsifying Transform Learning and Applications
Features based on sparse representation, especially using the synthesis dictionary model, have been heavily exploited in signal processing and computer vision.
