Search Results for author:
Found 243 papers, 155 papers with code
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity.
Ranked #735 on
Image Classification
on ImageNet
Localization Distillation for Dense Object Detection
Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of mimicking classification logit due to its inefficiency in distilling localization information and trivial improvement.
Deep Concept-wise Temporal Convolutional Networks for Action Localization
In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution.
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.
Blind Face Restoration via Deep Multi-scale Component Dictionaries
Next, with the degraded input, we match and select the most similar component features from their corresponding dictionaries and transfer the high-quality details to the input via the proposed dictionary feature transfer (DFT) block.
Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels
In this paper, we propose a principled formulation and framework by extending bicubic degradation based deep SISR with the help of plug-and-play framework to handle LR images with arbitrary blur kernels.
Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\leftrightarrow$Preserving Image Content
First, a semantic layout generation module utilizes semantic segmentation of the reference image to progressively predict the desired semantic layout after try-on.
Ranked #4 on
Virtual Try-on
on VITON
(IS metric)
ControlVideo: Training-free Controllable Text-to-Video Generation
Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling.
Plug-and-Play Image Restoration with Deep Denoiser Prior
Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems.
AttGAN: Facial Attribute Editing by Only Changing What You Want
Based on the encoder-decoder architecture, facial attribute editing is achieved by decoding the latent representation of the given face conditioned on the desired attributes.
Learning Deep CNN Denoiser Prior for Image Restoration
Recent works have revealed that, with the aid of variable splitting techniques, denoiser prior can be plugged in as a modular part of model-based optimization methods to solve other inverse problems (e. g., deblurring).
Ranked #1 on
Color Image Denoising
on BSD68 sigma5
Toward Convolutional Blind Denoising of Real Photographs
While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs.
Ranked #4 on
Denoising
on Darmstadt Noise Dataset
ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation
In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation.
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising.
Ranked #1 on
Grayscale Image Denoising
on BSD68 sigma75
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks.
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR).
A Comprehensive Survey on 3D Content Generation
Recent years have witnessed remarkable advances in artificial intelligence generated content(AIGC), with diverse input modalities, e. g., text, image, video, audio and 3D.
Shift-Net: Image Inpainting via Deep Feature Rearrangement
To this end, the encoder feature of the known region is shifted to serve as an estimation of the missing parts.
Localization Distillation for Object Detection
Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years.
Neural Blind Deconvolution Using Deep Priors
To connect MAP and deep models, we in this paper present two generative networks for respectively modeling the deep priors of clean image and blur kernel, and propose an unconstrained neural optimization solution to blind deconvolution.
Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency.
Cross-Scale Internal Graph Neural Network for Image Super-Resolution
Specifically, we dynamically construct a cross-scale graph by searching k-nearest neighboring patches in the downsampled LR image for each query patch in the LR image.
Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
The proposed methods are highly modular, readily plugged into existing deep CNNs.
Ranked #1 on
Image Classification
on iNaturalist
(Top 3 Error metric)
Multi-level Wavelet Convolutional Neural Networks
Specifically, MWCNN for image restoration is based on U-Net architecture, and inverse wavelet transform (IWT) is deployed to reconstruct the high resolution (HR) feature maps.
Progressive Image Deraining Networks: A Better and Simpler Baseline
To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions.
Ranked #1 on
Single Image Deraining
on Rain1400
Multi-level Wavelet-CNN for Image Restoration
With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork.
Ranked #2 on
Grayscale Image Denoising
on Set12 sigma25
Lightweight image super-resolution with enhanced CNN
Finally, the IRB uses coarse high-frequency features from the RB to learn more accurate SR features and construct a SR image.
Ranked #45 on
Image Super-Resolution
on Set14 - 4x upscaling
Blind Super-Resolution With Iterative Kernel Correction
In this paper, we propose an Iterative Kernel Correction (IKC) method for blur kernel estimation in blind SR problem, where the blur kernels are unknown.
Ranked #2 on
Blind Super-Resolution
on Set5 - 3x upscaling
Component Divide-and-Conquer for Real-World Image Super-Resolution
Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures.
Learning Generative Structure Prior for Blind Text Image Super-resolution
To restrict the generative space of StyleGAN so that it obeys the structure of characters yet remains flexible in handling different font styles, we store the discrete features for each character in a codebook.
Spatio-Temporal Filter Adaptive Network for Video Deblurring
To overcome the limitation of separate optical flow estimation, we propose a Spatio-Temporal Filter Adaptive Network (STFAN) for the alignment and deblurring in a unified framework.
Ranked #3 on
Deblurring
on DVD
(using extra training data)
TBSN: Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising
For channel self-attention, we observe that it may leak the blind-spot information when the channel number is greater than spatial size in the deep layers of multi-scale architectures.
Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
Compared with SRDCF, STRCF with hand-crafted features provides a 5 times speedup and achieves a gain of 5. 4% and 3. 6% AUC score on OTB-2015 and Temple-Color, respectively.
Ranked #9 on
Visual Object Tracking
on VOT2017/18
DAVANet: Stereo Deblurring with View Aggregation
Nowadays stereo cameras are more commonly adopted in emerging devices such as dual-lens smartphones and unmanned aerial vehicles.
Improving Adversarial Transferability via Intermediate-level Perturbation Decay
In particular, the proposed method, named intermediate-level perturbation decay (ILPD), encourages the intermediate-level perturbation to be in an effective adversarial direction and to possess a great magnitude simultaneously.
Unpaired Learning of Deep Image Denoising
As for knowledge distillation, we first apply the learned noise models to clean images to synthesize a paired set of training images, and use the real noisy images and the corresponding denoising results in the first stage to form another paired set.
Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision
Despite recent advances in deep learning-based face frontalization methods, photo-realistic and illumination preserving frontal face synthesis is still challenging due to large pose and illumination discrepancy during training.
VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models
Different from conventional T2V sampling (i. e., temporal and spatial modeling), VideoElevator explicitly decomposes each sampling step into temporal motion refining and spatial quality elevating.
Learning Dual Memory Dictionaries for Blind Face Restoration
Generally, it is a challenging and intractable task to improve the photo-realistic performance of blind restoration and adaptively handle the generic and specific restoration scenarios with a single unified model.
Learning Warped Guidance for Blind Face Restoration
For better recovery of fine facial details, we modify the problem setting by taking both the degraded observation and a high-quality guided image of the same identity as input to our guided face restoration network (GFRNet).
Ranked #1 on
Image Super-Resolution
on WebFace - 8x upscaling
Multi-scale Location-aware Kernel Representation for Object Detection
Our MLKP can be efficiently computed on a modified multi-scale feature map using a low-dimensional polynomial kernel approximation. Moreover, different from existing orderless global representations based on high-order statistics, our proposed MLKP is location retentive and sensitive so that it can be flexibly adopted to object detection.
From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution
Notably, LQ face images, which may have the same degradation process as natural images, can be robustly restored with photo-realistic textures by exploiting their strong structural priors.
Deep Adaptive Inference Networks for Single Image Super-Resolution
Nonetheless, content and resource adaptive model is more preferred, and it is encouraging to apply simpler and efficient networks to the easier regions with less details and the scenarios with restricted efficiency constraints.
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
To address this issue, we propose CLIP2Point, an image-depth pre-training method by contrastive learning to transfer CLIP to the 3D domain, and adapt it to point cloud classification.
Ranked #3 on
Training-free 3D Point Cloud Classification
on ScanObjectNN
(using extra training data)
Asymmetric CNN for image super-resolution
In this paper, we propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a memory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution.
Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
For guiding our IS to obtain better object performance, we explore issues of instance imbalance and class importance in datasets, which frequently occur and bring adverse effect on detection performance.
Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision
To diminish the effect of color inconsistency in image alignment, we introduce to use a global color mapping (GCM) module to generate an initial sRGB image given the input raw image, which can keep the spatial location of the pixels unchanged, and the target sRGB image is utilized to guide GCM for converting the color towards it.
Texts as Images in Prompt Tuning for Multi-Label Image Recognition
Nonetheless, visual data (e. g., images) is by default prerequisite for learning prompts in existing methods.
Contrastive Learning
Multi-label Image Recognition with Partial Labels
HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping
We blend the semantic layouts of source head and source body, and then inpaint the transition region by the semantic layout generator, achieving a coarse-grained head swapping.
Is Second-order Information Helpful for Large-scale Visual Recognition?
The main challenges involved are robust covariance estimation given a small sample of large-dimensional features and usage of the manifold structure of covariance matrices.
Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising
And we extend the blind-spot network to a blind-neighborhood network (BNN) for providing supervision on flat areas.
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
It simply encourages the variation of output caused by perturbations on different latent dimensions to be orthogonal, and the Jacobian with respect to the input is calculated to represent this variation.
Image Super-resolution with An Enhanced Group Convolutional Neural Network
In this paper, we present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture by fully fusing deep and wide channel features to extract more accurate low-frequency information in terms of correlations of different channels in single image super-resolution (SISR).
Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks
In this work, aiming at a general and comprehensive way for neural network acceleration, we develop a Wavelet-like Auto-Encoder (WAE) that decomposes the original input image into two low-resolution channels (sub-images) and incorporate the WAE into the classification neural networks for joint training.
Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations
For this purpose, we take the telephoto image instead of an additional high-resolution image as the supervision information and select a center patch from it as the reference to super-resolve the corresponding short-focus image patch.
Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser
To begin with, the pre-trained denoiser is used to generate the pseudo clean images for the test images.
Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time
Moreover, on the seemingly implausible x16 interpolation task, our method outperforms existing methods by more than 1. 5 dB in terms of PSNR.
SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions
The key idea of our SmartControl is to relax the visual condition on the areas that are conflicted with text prompts.
Multi-stage image denoising with the wavelet transform
In this paper, we propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i. e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and a residual block (RB).
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces
To evaluate our proposed MetaF2N, we have collected a real-world low-quality dataset with one or multiple faces in each image, and our MetaF2N achieves superior performance on both synthetic and real-world datasets.
Designing and Training of A Dual CNN for Image Denoising
The enhancement block gathers and fuses the global and local features to provide complementary information for the latter network.
Learning Semantic Person Image Generation by Region-Adaptive Normalization
In the first stage, we predict the target semantic parsing maps to eliminate the difficulties of pose transfer and further benefit the latter translation of per-region appearance style.
Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning
In this paper, we focus on a particular setting of learning adaptive prompts on the fly for each test sample from an unseen new domain, which is known as test-time prompt tuning (TPT).
LPT: Long-tailed Prompt Tuning for Image Classification
For better effectiveness, we divide prompts into two groups: 1) a shared prompt for the whole long-tailed dataset to learn general features and to adapt a pretrained model into target domain; and 2) group-specific prompts to gather group-specific features for the samples which have similar features and also to empower the pretrained model with discrimination ability.
Ranked #1 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
(using extra training data)
DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior
The priors are then regarded as input conditions to maintain reasonable geometries, in which conditional LoRA and weighted score are further proposed to optimize detailed textures.
Improving Image Restoration through Removing Degradations in Textual Representations
To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing the degradations, and then convert the restored textual representations into a guidance image for assisting image restoration.
SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety measures is paramount.
Self-Promoted Supervision for Few-Shot Transformer
The few-shot learning ability of vision transformers (ViTs) is rarely investigated though heavily desired.
Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks
In this paper, we present a novel one-shot generative domain adaption method, i. e., DiFa, for diverse generation and faithful adaptation.
Perspective-Guided Convolution Networks for Crowd Counting
In this paper, we propose a novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i. e. PGCNet), which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect.
Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
Specifically, we introduce class-specific auxiliary weights into the original MMD for exploiting the class prior probability on source and target domains, whose challenge lies in the fact that the class label in target domain is unavailable.
Learning Symmetry Consistent Deep CNNs for Face Completion
As for missing pixels on both of half-faces, we present a generative reconstruction subnet together with a perceptual symmetry loss to enforce symmetry consistency of recovered structures.
Ranked #1 on
Facial Inpainting
on VggFace2
A cross Transformer for image denoising
To avoid loss of key information, PB uses three heterogeneous networks to implement multiple interactions of multi-level features to broadly search for extra information for improving the adaptability of an obtained denoiser for complex scenes.
Exposure Bracketing is All You Need for Unifying Image Restoration and Enhancement Tasks
It is highly desired but challenging to acquire high-quality photos with clear content in low-light environments.
Sentence-level Prompts Benefit Composed Image Retrieval
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption.
Ranked #1 on
Image Retrieval
on CIRR
Self-Supervised Image Restoration with Blurry and Noisy Pairs
By learning in a collaborative manner, the deblurring and denoising tasks in our method can benefit each other.
Learning Federated Visual Prompt in Null Space for MRI Reconstruction
Federated Magnetic Resonance Imaging (MRI) reconstruction enables multiple hospitals to collaborate distributedly without aggregating local data, thereby protecting patient privacy.
Simultaneous Fidelity and Regularization Learning for Image Restoration
For blind deconvolution, as estimation error of blur kernel is usually introduced, the subsequent non-blind deconvolution process does not restore the latent image well.
Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance
To be specific, the reflection layer is firstly estimated due to that it generally is much simpler and is relatively easier to estimate.
RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution
The main challenge of BurstSR is to effectively combine the complementary information from input frames, while existing methods still struggle with it.
Bringing Events Into Video Deblurring With Non-Consecutively Blurry Frames
EFM can also be easily incorporated into existing deblurring networks, making event-driven deblurring task benefit from state-of-the-art deblurring methods.
UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving
The extension makes it possible to back-project the informative features, obtained by fusing features from both modalities, into their native modalities to reconstruct the multiple masked inputs.
Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis
Obviously, a fine-grained part-level semantic layout will benefit object details generation, and it can be roughly inferred from an object's shape.
A heterogeneous group CNN for image super-resolution
To prevent loss of original information, a multi-level enhancement mechanism guides a CNN to achieve a symmetric architecture for promoting expressive ability of HGSRCNN.
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization
In this paper, we propose a VQGAN-based framework (i. e., VQ-Font) to enhance glyph fidelity through token prior refinement and structure-aware enhancement.
Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes
The color component is estimated from aligned multi-exposure images, while the structure one is generated through a structure-focused network that is supervised by the color component and an input reference (\eg, medium-exposure) image.
Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
Motivated by the theoretical results in \cite{mansour2009domain}, the target distribution can be represented as the weighted combination of source distributions, and, the multi-source unsupervised domain adaptation via DCTN is then performed as two alternating steps: i) It deploys multi-way adversarial learning to minimize the discrepancy between the target and each of the multiple source domains, which also obtains the source-specific perplexity scores to denote the possibilities that a target sample belongs to different source domains.
Multi-Source Unsupervised Domain Adaptation
Unsupervised Domain Adaptation
W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection
Generally, with given pseudo ground-truths generated from the well-trained WSOD network, we propose a two-module iterative training algorithm to refine pseudo labels and supervise better object detector progressively.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective
Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task.
Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Ones
However, BiRNN is intrinsically offline because it uses backward recurrent modules to propagate from the last to current frames, which causes high latency and large memory consumption.
Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition
In this paper, we circumvent this issue by presenting a joint framework for both unbounded recommendation of camera view and image composition (i. e., UNIC).
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
This challenge includes three tracks.
Learning Convolutional Networks for Content-weighted Image Compression
Therefore, the encoder, decoder, binarizer and importance map can be jointly optimized in an end-to-end manner by using a subset of the ImageNet database.
Image Inpainting with Edge-guided Learnable Bidirectional Attention Maps
In this paper, we present an edge-guided learnable bidirectional attention map (Edge-LBAM) for improving image inpainting of irregular holes with several distinct merits.
Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
Semantic image synthesis is a challenging task with many practical applications.
ImaginaryNet: Learning Object Detectors without Real Images and Annotations
Given a class label, the language model is used to generate a full description of a scene with a target object, and the text-to-image model deployed to generate a photo-realistic image.
Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization Perspective
Meanwhile, diverse testing sets are also provided with different types of reflection and scenes.
Symmetry-Aware Transformer-based Mirror Detection
Mirror detection aims to identify the mirror regions in the given input image.
Adversarial Contrastive Learning via Asymmetric InfoNCE
Contrastive learning (CL) has recently been applied to adversarial learning tasks.
Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters
In this paper, we defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset.
Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc.
Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution
On the other hand, alignment algorithms in existing VSR methods perform poorly for real-world videos, leading to unsatisfactory results.
Integrating Boundary and Center Correlation Filters for Visual Tracking with Aspect Ratio Variation
The aspect ratio variation frequently appears in visual tracking and has a severe influence on performance.
Dark and Bright Channel Prior Embedded Network for Dynamic Scene Deblurring
In this work, we propose a Dark and Bright Channel Priors embedded Network (DBCPeNet) to plug the channel priors into a neural network for effective dynamic scene deblurring.
Ranked #32 on
Image Deblurring
on GoPro
(using extra training data)
Global Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural Networks
However, both GAP and existing HOP methods assume unimodal distributions, which cannot fully capture statistics of convolutional activations, limiting representation ability of deep CNNs, especially for samples with complex contents.
Image Inpainting with Learnable Bidirectional Attention Maps
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on
Image Inpainting
on Paris StreetView
Local Patch Network with Global Attention for Infrared Small Target Detection
A local patch network (LPNet) with global attention is proposed in this paper to detect small targets by jointly considering the global and local properties of infrared small target images.
A self-supervised CNN for image watermark removal
Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal.
Flexible Image Denoising with Multi-layer Conditional Feature Modulation
For flexible non-blind image denoising, existing deep networks usually take both noisy image and noise level map as the input to handle various noise levels with a single model.
Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking
Existing visual object tracking usually learns a bounding-box based template to match the targets across frames, which cannot accurately learn a pixel-wise representation, thereby being limited in handling severe appearance variations.
Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples
In this paper, by contrast, we opt for the diversity in substitute models and advocate to attack a Bayesian model for achieving desirable transferability.
Learning Content-Weighted Deep Image Compression
Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance.
Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
For learning pseudo mask generator from the auxiliary dataset, we present a bi-level optimization formulation.
A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration
Generative adversarial networks (GANs) have drawn enormous attention due to the simple yet effective training mechanism and superior image generation quality.
Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis
Despite the progress in semantic image synthesis, it remains a challenging problem to generate photo-realistic parts from input semantic map.
PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis
Extensive experiments demonstrate that our approach performs favorably in terms of visual quality, semantic consistency, and layout alignment.
Self-Supervised Video Desmoking for Laparoscopic Surgery
On the other hand, in order to enhance the desmoking performance, we further feed the valuable information from PS frame into models, where a masking strategy and a regularization term are presented to avoid trivial solutions.
MC$^2$: Multi-concept Guidance for Customized Multi-concept Generation
Customized text-to-image generation aims to synthesize instantiations of user-specified concepts and has achieved unprecedented progress in handling individual concept.
Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning
When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge while retaining old knowledge.
A Heterogeneous Dynamic Convolutional Neural Network for Image Super-resolution
The lower network utilizes a symmetric architecture to enhance relations of different layers to mine more structural information, which is complementary with a upper network for image super-resolution.
Remove Cosine Window from Correlation Filter-based Visual Trackers: When and How
Therefore, we in this paper investigate the feasibility to remove cosine window from CF trackers with spatial regularization.
Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression
For the former, we directly apply a CCN to the binarized representation of an image to compute the Bernoulli distribution of each code for entropy estimation.
Learning Single Image Defocus Deblurring with Misaligned Training Pairs
First, in the deblurring module, a bi-directional optical flow-based deformation is introduced to tolerate spatial misalignment between deblurred and ground-truth images.
Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive
In this paper, we propose a Self-supervised learning framework for Dual reversed RS distortions Correction (SelfDRSC), where a DRSC network can be learned to generate a high framerate GS video only based on dual RS images with reversed distortions.
Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising
To cope with this issue, this paper presents a multi-level wavelet residual network (MWRN) architecture as well as a progressive training (PTMWRN) scheme to improve image denoising performance.
Learning Dual-Pixel Alignment for Defocus Deblurring
Generally, DPANet is an encoder-decoder with skip-connections, where two branches with shared parameters in the encoder are employed to extract and align deep features from left and right views, and one decoder is adopted to fuse aligned features for predicting the sharp image.
Towards Instance-adaptive Inference for Federated Learning
However, the performance of the global model is often hampered by non-i. i. d.
Human Co-Parsing Guided Alignment for Occluded Person Re-identification
Most supervised methods propose to train an extra human parsing model aside from the ReID model with cross-domain human parts annotation, suffering from expensive annotation cost and domain gap; Unsupervised methods integrate a feature clustering-based human parsing process into the ReID model, but lacking supervision signals brings less satisfactory segmentation results.
Ranked #3 on
Person Re-Identification
on Occluded-DukeMTMC
Learning Diverse Tone Styles for Image Retouching
In particular, the style encoder predicts the target style representation of an input image, which serves as the conditional information in the RetouchNet for retouching, while the TSFlow maps the style representation vector into a Gaussian distribution in the forward pass.
Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation
The merits of the proposed MCTL are four-fold: 1) the concept of manifold criterion (MC) is first proposed as a measure validating the distribution matching across domains, and domain adaptation is achieved if the MC is satisfied; 2) the proposed MC can well guide the generation of the intermediate domain sharing similar distribution with the target domain, by minimizing the local domain discrepancy; 3) a global generative discrepancy metric (GGDM) is presented, such that both the global and local discrepancy can be effectively and positively reduced; 4) a simplified version of MCTL called MCTL-S is presented under a perfect domain generation assumption for more generic learning scenario.
Deepfake Forensics via An Adversarial Game
In this paper, we advocate adversarial training for improving the generalization ability to both unseen facial forgeries and unseen image/video qualities.
NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Dataset
Despite the significant progress in image denoising, it is still challenging to restore fine-scale details while removing noise, especially in extremely low-light environments.
Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images
Methods: In this paper, we propose a direct volumes prediction method based on the end-to-end deep convolutional neural networks (CNN).
Scaled Simplex Representation for Subspace Clustering
However, the negative entries in the coefficient matrix are forced to be positive when constructing the affinity matrix via exponentiation, absolute symmetrization, or squaring operations.
Crowd Counting via Perspective-Guided Fractional-Dilation Convolution
One of the main issues in this task is how to handle the dramatic scale variations of pedestrians caused by the perspective effect.
Robust Deep Ensemble Method for Real-world Image Denoising
In particular, we take well-trained CBDNet, NBNet, HINet, Uformer and GMSNet into denoiser pool, and a U-Net is adopted to predict pixel-wise weighting maps to fuse these denoisers.
Aggregating Long-term Sharp Features via Hybrid Transformers for Video Deblurring
To aggregate long-term sharp features from detected sharp frames, we utilize a global Transformer with multi-scale matching capability.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
An Intermediate-level Attack Framework on The Basis of Linear Regression
This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples.
Learning Hierarchical Dynamics with Spatial Adjacency for Image Enhancement
In various real-world image enhancement applications, the degradations are always non-uniform or non-homogeneous and diverse, which challenges most deep networks with fixed parameters during the inference phase.
Ranked #14 on
Image Dehazing
on SOTS Indoor
Learning Real-World Image De-Weathering with Imperfect Supervision
Real-world image de-weathering aims at removing various undesirable weather-related artifacts.
VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering
By feeding the retrieved image and question to the VQA model, one can find the images inconsistent with relative caption when the answer by VQA is inconsistent with the answer in the QA pair.
Decoupled Textual Embeddings for Customized Image Generation
To decouple irrelevant attributes (i. e., background and pose) from the subject embedding, we further present several attribute mappers that encode each image as several image-specific subject-unrelated embeddings.
Squeeze Training for Adversarial Robustness
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community.
An Improved Normed-Deformable Convolution for Crowd Counting
However, the heads are not uniformly covered by the sampling points in the deformable convolution, resulting in loss of head information.
FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models
Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.
Dimensionality Reduction
Few-Shot Class-Incremental Learning
+2
Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation
Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios.
Latent Code Augmentation Based on Stable Diffusion for Data-free Substitute Attacks
Specifically, we augment the latent codes of the inferred member data with LCA and use them as guidance for SD.
DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection
Most existing data augmentation methods tend to find a compromise in augmenting the data, \textit{i. e.}, increasing the amplitude of augmentation carefully to avoid degrading some data too much and doing harm to the model performance.
Responsible Visual Editing
To mitigate the negative implications of harmful images on research, we create a transparent and public dataset, AltBear, which expresses harmful information using teddy bears instead of humans.
Visual Tracking via Dynamic Graph Learning
First, the graph is initialized by assigning binary weights of some image patches to indicate the object and background patches according to the predicted bounding box.
PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
As a result, using partial data channels to build a full representation of multi-modalities is clearly desired.
VITAL: VIsual Tracking via Adversarial Learning
To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes.
Metric Learning with Dynamically Generated Pairwise Constraints for Ear Recognition
Ear recognition task is known as predicting whether two ear images belong to the same person or not.
Deep Structured Scene Parsing by Learning with Image Descriptions
This paper addresses a fundamental problem of scene understanding: How to parse the scene image into a structured configuration (i. e., a semantic object hierarchy with object interaction relations) that finely accords with human perception.
Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions
Rather than relying on elaborative annotations (e. g., manually labeled semantic maps and relations), we train our deep model in a weakly-supervised learning manner by leveraging the descriptive sentences of the training images.
Enlarging Context with Low Cost: Efficient Arithmetic Coding with Trimmed Convolution
One key issue of arithmetic encoding method is to predict the probability of the current coding symbol from its context, i. e., the preceding encoded symbols, which usually can be executed by building a look-up table (LUT).
Active Self-Paced Learning for Cost-Effective and Progressive Face Identification
By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert re-certification.
Robust Online Matrix Factorization for Dynamic Background Subtraction
We propose an effective online background subtraction method, which can be robustly applied to practical videos that have variations in both foreground and background.
Deep Identity-aware Transfer of Facial Attributes
In general, our model consists of a mask network and an attribute transform network which work in synergy to generate a photo-realistic facial image with the reference attribute.
Ranked #2 on
Image-to-Image Translation
on RaFD
Convolutional Network for Attribute-driven and Identity-preserving Human Face Generation
Here we address this problem from the view of optimization, and suggest an optimization model to generate human face with the given attributes while keeping the identity of the reference image.
Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning
Cross-domain visual data matching is one of the fundamental problems in many real-world vision tasks, e. g., matching persons across ID photos and surveillance videos.
Learning Support Correlation Filters for Visual Tracking
Sampling and budgeting training examples are two essential factors in tracking algorithms based on support vector machines (SVMs) as a trade-off between accuracy and efficiency.
A Deep Structured Model with Radius-Margin Bound for 3D Human Activity Recognition
Understanding human activity is very challenging even with the recently developed 3D/depth sensors.
Weighted Schatten $p$-Norm Minimization for Image Denoising and Background Subtraction
However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications.
Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification
Furthermore, each bit of our hashing codes is unequally weighted so that we can manipulate the code lengths by truncating the insignificant bits.
Towards Effective Codebookless Model for Image Classification
The bag-of-features (BoF) model for image classification has been thoroughly studied over the last decade.
Detail-preserving and Content-aware Variational Multi-view Stereo Reconstruction
It is much more promising in suppressing noise while preserving sharp features than conventional isotropic mesh smoothing.
F-SVM: Combination of Feature Transformation and SVM Learning via Convex Relaxation
The generalization error bound of support vector machine (SVM) depends on the ratio of radius and margin, while standard SVM only considers the maximization of the margin but ignores the minimization of the radius.
Deep Joint Task Learning for Generic Object Extraction
We present a general joint task learning framework, in which each task (either object localization or object segmentation) is tackled via a multi-layer convolutional neural network, and the two networks work collaboratively to boost performance.
Iterated Support Vector Machines for Distance Metric Learning
Distance metric learning aims to learn from the given training data a valid distance metric, with which the similarity between data samples can be more effectively evaluated for classification.
3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks
Our model thus advances existing approaches in two aspects: (i) it acts directly on the raw inputs (grayscale-depth data) to conduct recognition instead of relying on hand-crafted features, and (ii) the model structure can be dynamically adjusted accounting for the temporal variations of human activities, i. e. the network configuration is allowed to be partially activated during inference.
On the Optimal Solution of Weighted Nuclear Norm Minimization
Nevertheless, so far the global optimal solution of WNNM problem is not completely solved yet due to its non-convexity in general cases.
A Kernel Classification Framework for Metric Learning
Learning a distance metric from the given training samples plays a crucial role in many machine learning tasks, and various models and optimization algorithms have been proposed in the past decade.
Image Set based Collaborative Representation for Face Recognition
One key issue of ISFR is how to effectively and efficiently represent the query face image set by using the gallery face image sets.
Identity Preserving Face Completion for Large Ocular Region Occlusion
Different from the state-of-the-art face inpainting methods that have no control over the synthesized content and can only handle frontal face pose, our approach can faithfully recover the missing content under various head poses while preserving the identity.
Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking
In existing off-line deep learning models for CF trackers, the model adaptation usually is either abandoned or has closed-form solution to make it feasible to learn deep representation in an end-to-end manner.
Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement
To address this issue, we propose an unsupervised DL method for LdCT enhancement that incorporates unlabeled LdCT sinograms directly into the network training.
Convolutional Neural Networks based Intra Prediction for HEVC
To overcome this problem, in this paper, an intra prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting the current block.
Model Inconsistent but Correlated Noise: Multi-view Subspace Learning with Regularized Mixture of Gaussians
Different from single view case, MSL should take both common and specific knowledge among different views into consideration.
Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation
In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework.
Projective dictionary pair learning for pattern classification
Discriminative dictionary learning (DL) has been widely studied in various pattern classification problems.
Generative Adversarial Learning Towards Fast Weakly Supervised Detection
Without the need of annotating bounding boxes, the existing methods usually follow a two/multi-stage pipeline with an online compulsive stage to extract object proposals, which is an order of magnitude slower than fast fully supervised object detectors such as SSD [31] and YOLO [34].
Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior
Video summarization is a challenging under-constrained problem because the underlying summary of a single video strongly depends on users' subjective understandings.
Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
In this paper, we propose a model-based deep learning approach for merging an HrMS and LrHS images to generate a high-resolution hyperspectral (HrHS) image.
Texture Enhanced Image Denoising via Gradient Histogram Preservation
Image denoising is a classical yet fundamental problem in low level vision, as well as an ideal test bed to evaluate various statistical image modeling methods.
Weighted Nuclear Norm Minimization with Application to Image Denoising
In this paper we study the weighted nuclear norm minimization (WNNM) problem, where the singular values are assigned different weights.
Discriminative Learning of Iteration-Wise Priors for Blind Deconvolution
The maximum a posterior (MAP)-based blind deconvolution framework generally involves two stages: blur kernel estimation and non-blind restoration.
SOLD: Sub-Optimal Low-rank Decomposition for Efficient Video Segmentation
In particular, the affinity matrix with the rank fixed can be decomposed into two sub-matrices of low rank, and then we iteratively optimize them with closed-form solutions.
Joint Learning of Single-Image and Cross-Image Representations for Person Re-Identification
Person re-identification has been usually solved as either the matching of single-image representation (SIR) or the classification of cross-image representation (CIR).
Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization
Multispectral images (MSI) can help deliver more faithful representation for real scenes than the traditional image system, and enhance the performance of many computer vision tasks.
Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection
Feature representation and object category classification are two key components of most object detection methods.
A Probabilistic Collaborative Representation Based Approach for Pattern Classification
Consequently, we present a probabilistic collaborative representation based classifier (ProCRC), which jointly maximizes the likelihood that a test sample belongs to each of the multiple classes.
The Solution Path Algorithm for Identity-Aware Multi-Object Tracking
The tracker is formulated as a quadratic optimization problem with L0 norm constraints, which we propose to solve with the solution path algorithm.
RAID-G: Robust Estimation of Approximate Infinite Dimensional Gaussian With Application to Material Recognition
Infinite dimensional covariance descriptors can provide richer and more discriminative information than their low dimensional counterparts.
Learning Dynamic Guidance for Depth Image Enhancement
To address these limitations, we propose a weighted analysis representation model for guided depth image enhancement, which advances the conventional methods in two aspects: (i) task driven learning and (ii) dynamic guidance.
Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising
PGs are extracted from training images by putting nonlocal similar patches into groups, and a PG based Gaussian Mixture Model (PG-GMM) learning algorithm is developed to learn the NSS prior.
