Search Results for author:
Found 178 papers, 86 papers with code
Multiple Class Novelty Detection Under Data Distribution Shift
To this end, we consider the problem of multiple class novelty detection under dataset distribution shift to improve the novelty detection performance.
Utilizing Patch-level Category Activation Patterns for Multiple Class Novelty Detection
For any recognition system, the ability to identify novel class samples during inference is an important aspect of the system’s robustness.
Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers
As these parameters are independent, a single diffusion model with these task-specific parameters can be used to perform multiple tasks simultaneously.
Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency.
Frame by Familiar Frame: Understanding Replication in Video Diffusion Models
In our paper, we present a systematic investigation into the phenomenon of sample replication in video diffusion models.
View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network
Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5. 0%/2. 7% on CARGO and 3. 7%/5. 2% on AG-ReID, keeping the same magnitude of computational complexity.
Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditions
To address these issues, we present Thermal-NeRF, which takes thermal and visible raw images as inputs, considering the thermal camera is robust to the illumination variation and raw images preserve any possible clues in the dark, to accomplish visible and thermal view synthesis simultaneously.
FaceXFormer: A Unified Transformer for Facial Analysis
Unlike these conventional methods, our FaceXformer leverages a transformer-based encoder-decoder architecture where each task is treated as a learnable token, enabling the integration of multiple tasks within a single framework.
Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image
At the core of portrait photography is the search for ideal lighting and viewpoint.
Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal Modeling
This approach greatly reduces the number of learnable parameters compared to full tuning.
Deployment Prior Injection for Run-time Calibratable Object Detection
With a strong alignment between the training and test distributions, object relation as a context prior facilitates object detection.
MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers
Adversarial robustness often comes at the cost of degraded accuracy, impeding the real-life application of robust classification models.
Entropic Open-set Active Learning
Active Learning (AL) aims to enhance the performance of deep models by selecting the most informative samples for annotation from a pool of unlabeled data.
Guarding Barlow Twins Against Overfitting with Mixed Samples
Self-supervised Learning (SSL) aims to learn transferable feature representations for downstream applications without relying on labeled data.
Ranked #1 on
Self-Supervised Learning
on STL-10
Latent Feature-Guided Diffusion Models for Shadow Removal
Recovering textures under shadows has remained a challenging problem due to the difficulty of inferring shadow-free scenes from shadow images.
CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation
Our conditional-task learning and distillation approach outperforms previous distillation methods, achieving a new state-of-the-art in producing high-quality images with very few steps (e. g., 1-4) across multiple tasks, including super-resolution, text-guided image editing, and depth-to-image generation.
Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
To this end, and capitalizing on the powerful fine-grained generative control offered by the recent diffusion-based generative models, we introduce Steered Diffusion, a generalized framework for photorealistic zero-shot conditional image generation using a diffusion model trained for unconditional generation.
Towards Federated Learning Under Resource Constraints via Layer-wise Training and Depth Dropout
To mitigate this issue and facilitate training of large models on edge devices, we introduce a simple yet effective strategy, Federated Layer-wise Learning, to simultaneously reduce per-client memory, computation, and communication costs.
AdaptiveSAM: Towards Efficient Tuning of SAM for Surgical Scene Segmentation
However, SAM does not generalize well to the medical domain as is without utilizing a large amount of compute resources for fine-tuning and using task-specific prompts.
Cross-Dataset Adaptation for Instrument Classification in Cataract Surgery Videos
In this paper, we highlight this domain shift in the commonly performed cataract surgery and propose a novel end-to-end Unsupervised Domain Adaptation (UDA) method called the Barlow Adaptor that addresses the problem of distribution shift without requiring any labels from another domain.
Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training
We curate a large-scale dataset to enable pre-training of 3D medical radiology images (MRI and CT).
GLSFormer : Gated - Long, Short Sequence Transformer for Step Recognition in Surgical Videos
These results validate the suitability of our proposed approach for automated surgical step recognition.
Self-Supervised MRI Reconstruction with Unrolled Diffusion Models
Magnetic Resonance Imaging (MRI) produces excellent soft tissue contrast, albeit it is an inherently slow imaging modality.
Securing Deep Generative Models with Universal Adversarial Signature
Prior research attempted to mitigate these threats by detecting generated images, but the varying traces left by different generative models make it challenging to create a universal detector capable of generalizing to new, unseen generative models.
T1: Scaling Diffusion Probabilistic Fields to High-Resolution on Unified Visual Modalities
The model can be scaled to generate high-resolution data while unifying multiple modalities.
Analyzing Bias in Diffusion-based Face Generation Models
Diffusion models are becoming increasingly popular in synthetic data generation and image editing applications.
Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations
In summary, an OV method learns task-specific information using strong supervision from base annotations and novel category information using weak supervision from image-captions pairs.
Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation
Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers labeled source knowledge to an unlabeled target domain by relying on accessing both the source and target data.
ReBotNet: Fast Real-time Video Enhancement
The first branch learns spatio-temporal features by tokenizing the input frames along the spatial and temporal dimensions using a ConvNext-based encoder and processing these abstract tokens using a bottleneck mixer.
LightPainter: Interactive Portrait Relighting with Freehand Scribble
Recent portrait relighting methods have achieved realistic results of portrait lighting effects given a desired lighting representation such as an environment map.
$CrowdDiff$: Multi-hypothesis Crowd Density Estimation using Diffusion Models
Furthermore, as the intermediate time steps of the diffusion process are noisy, we incorporate a regression branch for direct crowd estimation only during training to improve the feature learning.
CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
Attempting to train the visual and text encoder to account for this shift results in catastrophic forgetting and a notable decrease in performance.
Deep Metric Learning for Unsupervised Remote Sensing Change Detection
This loss is motivated by the principle of metric learning where we simultaneously maximize the distance between change pair-wise pixels while minimizing the distance between no-change pair-wise pixels in bi-temporal image domain and their deep feature domain.
Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey
Deep learning has been highly successful in computer vision with large amounts of labeled data, but struggles with limited labeled training data.
Bi-Noising Diffusion: Towards Conditional Diffusion Models with Generative Restoration Priors
The improvements obtained by our method suggest that the priors can be incorporated as a general plugin for improving conditional diffusion models.
Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models
We also introduce a novel reliability parameter that allows using different off-the-shelf diffusion models trained across various datasets during sampling time alone to guide it to the desired outcome satisfying multiple constraints.
Ranked #1 on
Face Sketch Synthesis
on Multi-Modal CelebA-HQ
VIDM: Video Implicit Diffusion Models
Diffusion models have emerged as a powerful generative method for synthesizing high-quality and diverse set of images.
Ranked #11 on
Video Generation
on UCF-101
SceneComposer: Any-Level Semantic Image Synthesis
We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes.
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
Our adaptive masking strategy samples visible tokens based on the semantic context using an auxiliary sampling network.
Ranked #1 on
Action Classification
on Something-Something V2
Open-Set Automatic Target Recognition
Automatic Target Recognition (ATR) is a category of computer vision algorithms which attempts to recognize targets on data obtained from different sensors.
NBD-GAP: Non-Blind Image Deblurring Without Clean Target Images
This results in a pair of images with colored noise.
T2V-DDPM: Thermal to Visible Face Translation using Denoising Diffusion Probabilistic Models
In this paper, we propose a Denoising Diffusion Probabilistic Model (DDPM) based solution for T2V translation specifically for facial images.
AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic Models
In recent years, various deep learning-based single image atmospheric turbulence mitigation methods, including CNN-based and GAN inversion-based, have been proposed in the literature which attempt to remove the distortion in the image.
Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation
In this paper, we propose a novel UDA method for MDE, referred to as Learning Feature Decomposition for Adaptation (LFDA), which learns to decompose the feature space into content and style components.
Deep Semantic Statistics Matching (D2SM) Denoising Network
The ultimate aim of image restoration like denoising is to find an exact correlation between the noisy and clear image domains.
Learning to restore images degraded by atmospheric turbulence using uncertainty
Atmospheric turbulence can significantly degrade the quality of images acquired by long-range imaging systems by causing spatially and temporally random fluctuations in the index of refraction of the atmosphere.
DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change Detection
However, in this work, our focus is not on image synthesis but on utilizing it as a pre-trained feature extractor for the downstream application of change detection.
Ranked #1 on
Change Detection
on WHU-CD
SAR Despeckling using a Denoising Diffusion Probabilistic Model
The despeckled image is recovered by a reverse process which iteratively predicts the added noise using a noise predictor which is conditioned on the speckled image.
SAR Despeckling Using Overcomplete Convolutional Networks
We show that the proposed network improves despeckling performance compared to recent despeckling methods on synthetic and real SAR images.
On Trace of PGD-Like Adversarial Attacks
Adversarial attacks pose safety and security concerns to deep learning applications, but their characteristics are under-explored.
Deep-learning-enabled Brain Hemodynamic Mapping Using Resting-state fMRI
Deep-learning resting-state vascular imaging has the potential to become a useful tool in clinical cerebrovascular imaging.
Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN
Existing approaches for restoring weather-degraded images follow a fully-supervised paradigm and they require paired data for training.
A comparison of different atmospheric turbulence simulation methods for image restoration
In this paper, we systematically evaluate the effectiveness of various turbulence simulation methods on image restoration.
Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images
The performance of existing deep supervised CD methods is attributed to the large amounts of annotated data used to train the networks.
Shape-guided Object Inpainting
Therefore, we propose a new data preparation method and a novel Contextual Object Generator (CogNet) for the object inpainting task.
Towards Online Domain Adaptive Object Detection
To the best of our knowledge, this is the first work to address online and offline adaptation settings for object detection.
Thermal to Visible Image Synthesis under Atmospheric Turbulence
In this paper, we first investigate the problem with a turbulence simulation method on real-world thermal images.
Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination
In Heterogeneous Face Recognition (HFR), the objective is to match faces across two different domains such as visible and thermal.
Target and Task specific Source-Free Domain Adaptive Image Segmentation
In task-specific adaptation, we exploit the enhanced pseudo-labels using a student-teacher framework to effectively learn segmentation on the target domain.
Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection
The Source-Free Domain Adaptation (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
Interactive Portrait Harmonization
To enable flexible interaction between user and harmonization, we introduce interactive harmonization, a new setting where the harmonization is performed with respect to a selected \emph{region} in the reference image instead of the entire background.
Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation
Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing.
On-the-Fly Test-time Adaptation for Medical Image Segmentation
During test-time, the model takes in just the new test image and generates a domain code to adapt the features of source model according to the test data.
UNeXt: MLP-based Rapid Medical Image Segmentation Network
Using tokenized MLPs in latent space reduces the number of parameters and computational complexity while being able to result in a better representation to help segmentation.
Ranked #3 on
Medical Image Segmentation
on ISIC 2018
HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening
Existing pansharpening approaches neglect using an attention mechanism to transfer HR texture features from PAN to LR-HSI features, resulting in spatial and spectral distortions.
Enhancing Adversarial Robustness for Deep Metric Learning
Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved.
Exploring Adversarially Robust Training for Unsupervised Domain Adaptation
Adversarial Training (AT) has been considered to be the most successful adversarial defense approach.
Open-set Adversarial Defense with Clean-Adversarial Mutual Learning
This paper proposes an Open-Set Defense Network with Clean-Adversarial Mutual Learning (OSDN-CAML) as a solution to the OSAD problem.
ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer
Accelerating magnetic resonance image (MRI) reconstruction process is a challenging ill-posed inverse problem due to the excessive under-sampling operation in k-space.
Transformer-based SAR Image Despeckling
Synthetic Aperture Radar (SAR) images are usually degraded by a multiplicative noise known as speckle which makes processing and interpretation of SAR images difficult.
A Transformer-Based Siamese Network for Change Detection
This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images.
Ranked #14 on
Change Detection
on LEVIR-CD
LTT-GAN: Looking Through Turbulence by Inverting GANs
To mitigate the turbulence effect, in this paper, we propose the first turbulence mitigation method that makes use of visual priors encapsulated by a well-trained GAN.
Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection
We demonstrate our approach on two recent object detectors and achieve results that out-perform the other domain adaptation works.
SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
Our model can be trained in a self-supervised fashion by learning the reconstruction of an image region from the style vector and sketch.
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions
We also introduce a transformer decoder with learnable weather type embeddings to adjust to the weather degradation at hand.
Ranked #1 on
Single Image Deraining
on Raindrop
Reference-based Magnetic Resonance Image Reconstruction Using Texture Transformer
Deep Learning (DL) based methods for magnetic resonance (MR) image reconstruction have been shown to produce superior performance in recent years.
Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation
The generalization ability of face presentation attack detection models to unseen attacks has become a key issue for real-world deployment, which can be improved when models are trained with face images from different input distributions and different types of spoof attacks.
Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection
Multimodal learning is an emerging yet challenging research area.
Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning
Though thermal cameras are widely used for military applications and increasingly for commercial applications, there is a lack of robust algorithms to robustly exploit the thermal imagery due to the limited availability of labeled thermal data.
Fine-Context Shadow Detection using Shadow Removal
First, we propose a Fine Context-aware Shadow Detection Network (FCSD-Net), where we constraint the receptive field size and focus on low-level features to learn fine context features better.
SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving
Using just convolution neural networks (ConvNets) for this problem is not effective as it is inefficient at capturing distant dependencies between road segments in the image which is essential to extract road connectivity.
Ranked #1 on
Road Segmentation
on DeepGlobe
Adversarially Robust One-class Novelty Detection
To this end, we propose a defense strategy that manipulates the latent space of novelty detectors to improve the robustness against adversarial examples.
A Synthesis-Based Approach for Thermal-to-Visible Face Verification
Lastly, we show that our end-to-end thermal-to-visible face verification system provides strong performance on the MILAB-VTF(B) dataset.
Image Fusion Transformer
Furthermore, we show the effectiveness of the proposed ST fusion strategy with an ablation analysis.
Heterogeneous Face Frontalization via Domain Agnostic Learning
We propose a domain agnostic learning-based generative adversarial network (DAL-GAN) which can synthesize frontal views in the visible domain from thermal faces with pose variations.
Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection
Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars.
Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
To estimate the PAN image of the up-sampled HSI, we also propose a learnable spectral response function (SRF).
Ranked #1 on
Image Super-Resolution
on Chikusei Dataset
Over-and-Under Complete Convolutional RNN for MRI Reconstruction
Reconstructing magnetic resonance (MR) images from undersampled data is a challenging problem due to various artifacts introduced by the under-sampling operation.
Unsupervised Domain Adaptation of Object Detectors: A Survey
Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection.
Federated Generalized Face Presentation Attack Detection
A face presentation attack detection model with good generalization can be obtained when it is trained with face images from different input distributions and different types of spoof attacks.
Federated Learning-based Active Authentication on Mobile Devices
Using FL/SL frameworks, we can alleviate the lack of negative data problem by training a user authentication model over multiple user data distributed across devices.
Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN
Existing thermal-to-visible face verification approaches expect the thermal and visible face images to be of similar resolution.
Multimodal Face Synthesis from Visual Attributes
Extensive experiments and comparisons with several state-of-the-art methods are performed to verify the effectiveness of the proposed attribute-based multimodal synthesis method.
MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
Existing approaches for unsupervised domain adaptive object detection perform feature alignment via adversarial training.
Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning
However, the generalizability of models trained with the FL setting can still be suboptimal due to domain shift, which results from the data collected at multiple institutions with different sensors, disease types, and acquisition protocols, etc.
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation
The proposed Medical Transformer (MedT) is evaluated on three different medical image segmentation datasets and it is shown that it achieves better performance than the convolutional and other related transformer-based architectures.
Ranked #1 on
Medical Image Segmentation
on Brain US
Error Diffusion Halftoning Against Adversarial Examples
In this paper, we propose a new image transformation defense based on error diffusion halftoning, and combine it with adversarial training to defend against adversarial examples.
One-Class Classification: A Survey
One-Class Classification (OCC) is a special case of multi-class classification, where data observed during training is from a single positive class.
A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset
Thermal face imagery, which captures the naturally emitted heat from the face, is limited in availability compared to face imagery in the visible spectrum.
CR-Fill: Generative Image Inpainting With Auxiliary Contextual Reconstruction
The auxiliary branch (i. e. CR loss) is required only during training, and only the inpainting generator is required during the inference.
Ranked #8 on
Image Inpainting
on Places2
Overcomplete Representations Against Adversarial Videos
Adversarial robustness of deep neural networks is an extensively studied problem in the literature and various methods have been proposed to defend against adversarial images.
CR-Fill: Generative Image Inpainting with Auxiliary Contexutal Reconstruction
Due to the lack of supervision signals for the correspondence between missing regions and known regions, it may fail to find proper reference features, which often leads to artifacts in the results.
Overcomplete Deep Subspace Clustering Networks
This method uses undercomplete representations of the input data which makes it not so robust and more dependent on pre-training.
Deep Image Compositing
In this paper, we propose a new method which can automatically generate high-quality image compositing without any user input.
Exploring Overcomplete Representations for Single Image Deraining using CNNs
Removal of rain streaks from a single image is an extremely challenging problem since the rainy images often contain rain streaks of different size, shape, direction and density.
KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
To overcome this issue, we propose using an overcomplete convolutional architecture where we project our input image into a higher dimension such that we constrain the receptive field from increasing in the deep layers of the network.
Ranked #1 on
Medical Image Segmentation
on RITE
MultAV: Multiplicative Adversarial Videos
In this paper, we propose a novel attack method against video recognition models, Multiplicative Adversarial Videos (MultAV), which imposes perturbation on video data by multiplication.
Completely Self-Supervised Crowd Counting via Distribution Matching
Dense crowd counting is a challenging task that demands millions of head annotations for training models.
Defending Against Multiple and Unforeseen Adversarial Videos
With a multiple BN structure, each BN brach is responsible for learning the distribution of a single perturbation type and thus provides more precise distribution estimations.
Open-set Adversarial Defense
In this paper, we show that open-set recognition systems are vulnerable to adversarial attacks.
Confidence-guided Lesion Mask-based Simultaneous Synthesis of Anatomic and Molecular MR Images in Patients with Post-treatment Malignant Gliomas
Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas in neuro-oncology, especially with the help of standard anatomic and advanced molecular MR images.
Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs
Atmospheric turbulence significantly affects imaging systems which use light that has propagated through long atmospheric paths.
Anomaly Detection-Based Unknown Face Presentation Attack Detection
Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users.
Learning to Count in the Crowd from Limited Labeled Data
In this work, we focus on reducing the annotation efforts by learning to count in the crowd from limited number of labeled samples while leveraging a large pool of unlabeled data.
Lesion Mask-based Simultaneous Synthesis of Anatomic and MolecularMR Images using a GAN
Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas for patients with malignant gliomas in neuro-oncology with the help of conventional and advanced molecular MR images.
Quickest Intruder Detection for Multiple User Active Authentication
In this paper, we investigate how to detect intruders with low latency for Active Authentication (AA) systems with multiple-users.
KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations
Due to its excellent performance, U-Net is the most widely used backbone architecture for biomedical image segmentation in the recent years.
Federated Face Presentation Attack Detection
A face presentation attack detection model with good generalization can be obtained when it is trained with face images from different input distributions and different types of spoof attacks.
Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis
Finally, a pre-trained VGG-Face network is leveraged to extract features from the synthesized image and the input visible image for verification.
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
The proposed Confidence Guided Deep Residual Counting Network (CG-DRCN) is evaluated on recent complex datasets, and it achieves significant improvements in errors.
Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data
We show that our method can synthesize high-quality US images for every manipulated segmentation label with qualitative and quantitative improvements over the recent state-of-the-art synthesis methods.
Facial Synthesis from Visual Attributes via Sketch using Multi-Scale Generators
In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem.
Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions
Adverse weather conditions such as haze and rain corrupt the quality of captured images, which cause detection networks trained on clean images to perform poorly on these images.
Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method
The proposed Confidence Guided Deep Residual Counting Network (CG-DRCN) is evaluated on recent complex datasets, and it achieves significant improvements in errors.
Confidence Measure Guided Single Image De-raining
Single image de-raining is an extremely challenging problem since the rainy images contain rain streaks which often vary in size, direction and density.
Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting
These issues are further exacerbated in highly congested scenes.
Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks
We propose a novel multi-stream architecture and training methodology that exploits semantic labels for facial image deblurring.
HA-CCN: Hierarchical Attention-based Crowd Counting Network
The proposed method, which is based on the VGG16 network, consists of a spatial attention module (SAM) and a set of global attention modules (GAM).
Inverse Attention Guided Deep Crowd Counting Network
In this paper, we address the challenging problem of crowd counting in congested scenes.
Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining
Previous approaches have attempted to address this problem by leveraging some prior information to remove rain streaks from a single image.
Ranked #8 on
Single Image Deraining
on Test2800
Deep Sparse Representation-based Classification
The proposed network consists of a convolutional autoencoder along with a fully-connected layer.
Ranked #1 on
Sparse Representation-based Classification
on SVHN
Polarimetric Thermal to Visible Face Verification via Self-Attention Guided Synthesis
Polarimetric thermal to visible face verification entails matching two images that contain significant domain differences.
C2AE: Class Conditioned Auto-Encoder for Open-set Recognition
It refers to the problem of identifying the unknown classes during testing, while maintaining performance on the known classes.
Deep CNN-based Multi-task Learning for Open-Set Recognition
We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition.
Deep Transfer Learning for Multiple Class Novelty Detection
We show that thresholding the maximal activation of the proposed network can be used to identify novel objects effectively.
Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier
Generally, an active authentication problem is modelled as a one class classification problem due to the unavailability of data from the impostor users.
One-Class Convolutional Neural Network
We present a novel Convolutional Neural Network (CNN) based approach for one class classification.
DAFE-FD: Density Aware Feature Enrichment for Face Detection
In this work, we approach the problem of small face detection with the motivation of enriching the feature maps using a density map estimation module.
Polarimetric Thermal to Visible Face Verification via Attribute Preserved Synthesis
A pre-trained VGG-Face network is used to extract the attributes from the visible image.
Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training
We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition.
Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
Previous approaches utilize either a two-step procedure (visible feature estimation and visible image reconstruction) or an input-level fusion technique, where different Stokes images are concatenated and used as a multi-channel input to synthesize the visible image given the corresponding polarimetric signatures.
Disentangled Variational Representation for Heterogeneous Face Recognition
Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms.
Ranked #2 on
Face Verification
on BUAA-VisNir
Simultaneous Segmentation and Classification of Bone Surfaces from Ultrasound Using a Multi-feature Guided CNN
Various imaging artifacts, low signal-to-noise ratio, and bone surfaces appearing several millimeters in thickness have hindered the success of ultrasound (US) guided computer assisted orthopedic surgery procedures.
Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results
In this work, we identify the next set of challenges that requires attention from the research community and collect a new dataset of face images that involve these issues such as weather-based degradations, motion blur, focus blur and several others.
Deep Multimodal Subspace Clustering Networks
In addition to various spatial fusion-based methods, an affinity fusion-based network is also proposed in which the self-expressive layer corresponding to different modalities is enforced to be the same.
Ranked #1 on
Image Clustering
on Extended Yale-B
Densely Connected Pyramid Dehazing Network
We propose a new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazing all together.
Ranked #6 on
Image Dehazing
on RESIDE-6K
Generating High Quality Visible Images from SAR Images Using CNNs
We propose a novel approach for generating high quality visible-like images from Synthetic Aperture Radar (SAR) images using Deep Convolutional Generative Adversarial Network (GAN) architectures.
Density-aware Single Image De-raining using a Multi-stream Dense Network
In addition, an ablation study is performed to demonstrate the improvements obtained by different modules in the proposed method.
Ranked #6 on
Single Image Deraining
on RainCityscapes
Learning Deep Features for One-Class Classification
We propose a deep learning-based solution for the problem of feature learning in one-class classification.
Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem.
In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks
In unsupervised image-to-image translation, the goal is to learn the mapping between an input image and an output image using a set of unpaired training images.
Generative Adversarial Network
Multimodal Unsupervised Image-To-Image Translation
+2
High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
To this end, we propose a novel synthesis framework called Photo-Sketch Synthesis using Multi-Adversarial Networks, (PS2-MAN) that iteratively generates low resolution to high resolution images in an adversarial way.
Ranked #2 on
Face Sketch Synthesis
on CUHK
GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks
The primary aim of this work is to demonstrate that information preserved by landmarks (gender in particular) can be further accentuated by leveraging generative models to synthesize corresponding faces.
Generative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faces
Previous approaches utilize a two-step procedure (visible feature estimation and visible image reconstruction) to synthesize the visible image given the corresponding polarimetric thermal image.
Joint Transmission Map Estimation and Dehazing using Deep Networks
Single image haze removal is an extremely challenging problem due to its inherent ill-posed nature.
Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs
DME is a multi-column architecture-based CNN that aims to generate high-dimensional feature maps from the input image which are fused with the contextual information estimated by GCE and LCE using F-CNN.
Ranked #8 on
Crowd Counting
on WorldExpo’10
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations.
Ranked #16 on
Crowd Counting
on UCF-QNRF
Synthesis-based Robust Low Resolution Face Recognition
Recognition of low resolution face images is a challenging problem in many practical face recognition systems.
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation
Nevertheless, over the last few years, crowd count analysis has evolved from earlier methods that are often limited to small variations in crowd density and scales to the current state-of-the-art methods that have developed the ability to perform successfully on a wide range of scenarios.
Hierarchical Multimodal Metric Learning for Multimodal Classification
The learned metrics can improve multimodal classification accuracy and experimental results on four datasets show that the proposed algorithm outperforms existing learning algorithms based on multiple metrics as well as other approaches tested on these datasets.
SAR Image Despeckling Using a Convolutional Neural Network
Synthetic Aperture Radar (SAR) images are often contaminated by a multiplicative noise known as speckle.
Sparse Representation-based Open Set Recognition
We propose a generalized Sparse Representation- based Classification (SRC) algorithm for open set recognition where not all classes presented during testing are known during training.
Learning from Ambiguously Labeled Face Images
To prevent the majority labels from dominating the result of MCar, we generalize MCar to a weighted MCar (WMCar) that handles label imbalance.
Image De-raining Using a Conditional Generative Adversarial Network
Hence, it is important to solve the problem of single image de-raining/de-snowing.
Active User Authentication for Smartphones: A Challenge Data Set and Benchmark Results
In this paper, automated user verification techniques for smartphones are investigated.
Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks
Over the last five years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems.
Partial Face Detection for Continuous Authentication
In this paper, a part-based technique for real time detection of users' faces on mobile devices is proposed.
HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition
We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN).
Ranked #2 on
Face Detection
on Annotated Faces in the Wild
Deep Feature-based Face Detection on Mobile Devices
We propose a deep feature-based face detector for mobile devices to detect user's face acquired by the front facing camera.
Optimized Kernel-based Projection Space of Riemannian Manifolds
Recently, it was shown that embedding such manifolds into a Random Projection Spaces (RPS), rather than RKHS or tangent space, leads to higher classification and clustering performance.
Towards the Design of an End-to-End Automated System for Image and Video-based Recognition
In this paper, we present a brief history of developments in computer vision and artificial neural networks over the last forty years for the problem of image-based recognition.
Sequential Score Adaptation with Extreme Value Theory for Robust Railway Track Inspection
Periodic inspections are necessary to keep railroad tracks in state of good repair and prevent train accidents.
Deep Multi-task Learning for Railway Track Inspection
Railroad tracks need to be periodically inspected and monitored to ensure safe transportation.
A Deep Pyramid Deformable Part Model for Face Detection
We present a face detection algorithm based on Deformable Part Models and deep pyramidal features.
Unconstrained Face Verification using Deep CNN Features
In this paper, we present an algorithm for unconstrained face verification based on deep convolutional features and evaluate it on the newly released IARPA Janus Benchmark A (IJB-A) dataset.
Ranked #13 on
Face Verification
on IJB-A
Generalized Domain-Adaptive Dictionaries
Data-driven dictionaries have produced state-of-the-art results in various classification tasks.
Dictionary Learning from Ambiguously Labeled Data
We propose a novel dictionary-based learning method for ambiguously labeled multiclass classification, where each training sample has multiple labels and only one of them is the correct label.
