Search Results for author:
Found 70 papers, 43 papers with code
Learning Enriched Features for Real Image Restoration and Enhancement
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing.
Ranked #4 on
Image Denoising
on DND
CycleISP: Real Image Restoration via Improved Data Synthesis
This is mainly because the AWGN is not adequate for modeling the real camera noise which is signal-dependent and heavily transformed by the camera imaging pipeline.
Ranked #9 on
Image Denoising
on DND
(using extra training data)
Multi-Stage Progressive Image Restoration
At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features.
Ranked #3 on
Spectral Reconstruction
on ARAD-1K
Restormer: Efficient Transformer for High-Resolution Image Restoration
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks.
Ranked #1 on
Grayscale Image Denoising
on Urban100 sigma15
Transformers in Medical Imaging: A Survey
Following unprecedented success on the natural language tasks, Transformers have been successfully applied to several computer vision problems, achieving state-of-the-art results and prompting researchers to reconsider the supremacy of convolutional neural networks (CNNs) as {de facto} operators.
Learning Enriched Features for Fast Image Restoration and Enhancement
In the former case, spatial details are preserved but the contextual information cannot be precisely encoded.
A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation
We propose a Transformer architecture for volumetric segmentation, a challenging task that requires keeping a complex balance in encoding local and global spatial cues, and preserving information along all axes of the volume.
MARLIN: Masked Autoencoder for facial video Representation LearnINg
This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS).
Ranked #1 on
Emotion Classification
on CMU-MOSEI
Intriguing Properties of Vision Transformers
We show and analyze the following intriguing properties of ViT: (a) Transformers are highly robust to severe occlusions, perturbations and domain shifts, e. g., retain as high as 60% top-1 accuracy on ImageNet even after randomly occluding 80% of the image content.
Semantic-Aware Domain Generalized Segmentation
In this paper, we address domain generalized semantic segmentation, where a segmentation model is trained to be domain-invariant without using any target domain data.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Orthogonal Projection Loss
The CE loss encourages features of a class to have a higher projection score on the true class-vector compared to the negative classes.
Automatic Gaze Analysis: A Survey of Deep Learning based Approaches
Eye gaze analysis is an important research problem in the field of Computer Vision and Human-Computer Interaction.
iTAML: An Incremental Task-Agnostic Meta-learning Approach
In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks.
Self-supervised Knowledge Distillation for Few-shot Learning
Our experiments show that, even in the first stage, self-supervision can outperform current state-of-the-art methods, with further gains achieved by our second stage distillation process.
Ranked #12 on
Few-Shot Image Classification
on FC100 5-way (5-shot)
Image Super-Resolution as a Defense Against Adversarial Attacks
The proposed scheme is simple and has the following advantages: (1) it does not require any model training or parameter optimization, (2) it complements other existing defense mechanisms, (3) it is agnostic to the attacked model and attack type and (4) it provides superior performance across all popular attack algorithms.
A Self-supervised Approach for Adversarial Robustness
Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e. g., for classification, segmentation and object detection.
Towards Robust and Reproducible Active Learning Using Neural Networks
Finally, we conclude with a set of recommendations on how to assess the results using a new AL algorithm to ensure results are reproducible and robust under changes in experimental conditions.
Ranked #6 on
Active Learning
on CIFAR10 (10,000)
Max-margin Class Imbalanced Learning with Gaussian Affinity
Real-world object classes appear in imbalanced ratios.
CLIP model is an Efficient Continual Learner
In this work, we show that a frozen CLIP (Contrastive Language-Image Pretraining) model offers astounding continual learning performance without any fine-tuning (zero-shot evaluation).
Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks
Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images.
Ranked #7 on
Adversarial Defense
on CIFAR-10
Synthesizing the Unseen for Zero-shot Object Detection
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference.
Ranked #1 on
Zero-Shot Object Detection
on ImageNet Detection
On Generating Transferable Targeted Perturbations
To this end, we propose a new objective function that not only aligns the global distributions of source and target images, but also matches the local neighbourhood structure between the two domains.
An Adaptive Random Path Selection Approach for Incremental Learning
In a conventional supervised learning setting, a machine learning model has access to examples of all object classes that are desired to be recognized during the inference stage.
Random Path Selection for Continual Learning
In order to maintain an equilibrium between previous and newly acquired knowledge, we propose a simple controller to dynamically balance the model plasticity.
Ranked #7 on
Continual Learning
on F-CelebA (10 tasks)
Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization
Our baseline method for benchmarking the proposed dataset is a 3DCNN model, termed as Boundary Aware Temporal Forgery Detection (BA-TFD), which is guided via contrastive, boundary matching, and frame classification loss functions.
Ranked #1 on
DeepFake Detection
on LAV-DF
Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations.
Ranked #1 on
Temporal Forgery Localization
on ForgeryNet
AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
The comprehensive benchmark of the proposed dataset utilizing state-of-the-art deepfake detection and localization methods indicates a significant drop in performance compared to previous datasets.
Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
With that, we develop a large-scale synthetic scene flow dataset GTA-SF.
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training
The current approaches for 3D visual reasoning are task-specific, and lack pre-training methods to learn generic representations that can transfer across various tasks.
PosSAM: Panoptic Open-vocabulary Segment Anything
In this paper, we introduce an open-vocabulary panoptic segmentation model that effectively unifies the strengths of the Segment Anything Model (SAM) with the vision-language CLIP model in an end-to-end framework.
Ranked #1 on
Open Vocabulary Panoptic Segmentation
on ADE20K
Open Vocabulary Panoptic Segmentation
Open Vocabulary Semantic Segmentation
+2
Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation
Despite the significant recent progress made on 3D point cloud semantic segmentation, the current methods require training data for all classes at once, and are not suitable for real-life scenarios where new categories are being continuously discovered.
Stylized Adversarial Defense
In contrast to existing adversarial training methods that only use class-boundary information (e. g., using a cross-entropy loss), we propose to exploit additional information from the feature space to craft stronger adversaries that are in turn used to learn a robust model.
Hybrid Window Attention Based Transformer Architecture for Brain Tumor Segmentation
As intensities of MRI volumes are inconsistent across institutes, it is essential to extract universal features of multi-modal MRIs to precisely segment brain tumors.
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization.
Ranked #3 on
Weakly Supervised Action Localization
on THUMOS’14
Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis
Given only the class-level semantic information for unseen objects, we strive to enhance the correspondence, alignment and consistency between the visual and semantic spaces, to synthesise diverse, generic and transferable visual features.
Survey: Image Mixing and Deleting for Data Augmentation
One such method is augmentation which introduces different types of corruption in the data to prevent the model from overfitting and to memorize patterns present in the data.
LAVA: Label-efficient Visual Learning and Adaptation
We present LAVA, a simple yet effective method for multi-domain visual transfer learning with limited data.
Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation
Our model simultaneously learns to match the data, reconstruction loss and the latent distributions of real and fake images to improve the quality of generated samples.
Real-time Trajectory-based Social Group Detection
These results demonstrate that our proposed method is suitable for real-time robotic applications.
'Labelling the Gaps': A Weakly Supervised Automatic Eye Gaze Estimation
Our proposed method reduces the annotation effort to as low as 2. 67%, with minimal impact on performance; indicating the potential of our model enabling gaze estimation 'in-the-wild' setup.
Regularization of Deep Neural Networks with Spectral Dropout
We cast the proposed approach in the form of regular Convolutional Neural Network (CNN) weight layers using a decorrelation transform with fixed basis functions.
Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data
Class imbalance is a common problem in the case of real-world object detection and classification tasks.
A Spatial Layout and Scale Invariant Feature Representation for Indoor Scene Classification
This paper introduces a new learnable feature descriptor called "spatial layout and scale invariant convolutional activations" to deal with these challenges.
A Discriminative Representation of Convolutional Features for Indoor Scene Recognition
To this end, we introduce a new large-scale dataset of 1300 object categories which are commonly present in indoor scenes.
Striking the Right Balance with Uncertainty
Rare classes tend to get a concentrated representation in the classification space which hampers the generalization of learned boundaries to new test examples.
Learning Non-Linear Reconstruction Models for Image Set Classification
We propose a deep learning framework for image set classification with application to face recognition.
Joint Registration and Representation Learning for Unconstrained Face Identification
We validate the proposed scheme on template based unconstrained face identification.
Contractive Rectifier Networks for Nonlinear Maximum Margin Classification
The contractive constraints ensure that the achieved separating margin in the input space is larger than or equal to the separating margin in the output layer.
Scene Categorization With Spectral Features
To the best of our knowledge, this is the first attempt to use deep learning based spectral features explicitly for image classification task.
Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection
Our approach defines an inverse mapping between different geometric descriptors computed on the mesh surface or its down-sampled version, and the corresponding 2D texture image of the mesh, allowing the construction of fused geometrically augmented images (FGAI).
Unsupervised Primitive Discovery for Improved 3D Generative Modeling
Using the primitive parts for shapes as attributes, a parameterized 3D representation is modeled in the first stage.
Gaussian Affinity for Max-Margin Class Imbalanced Learning
Real-world object classes appear in imbalanced ratios.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
Meta-learning the Learning Trends Shared Across Tasks
This demonstrates their ability to acquire transferable knowledge, a capability that is central to human learning.
Transformers in Vision: A Survey
Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems.
Low Light Image Enhancement via Global and Local Context Modeling
These contexts can be crucial towards inferring several image enhancement tasks, e. g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent.
MTGLS: Multi-Task Gaze Estimation with Limited Supervision
Our proposed framework outperforms the unsupervised state-of-the-art on CAVE (by 6. 43%) and even supervised state-of-the-art methods on Gaze360 (by 6. 59%) datasets.
ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues
Firstly, we analyze CLIP for unsupervised open-category proposal generation and design an objectness score based on our empirical analysis on proposal selection.
Unpaired Referring Expression Grounding via Bidirectional Cross-Modal Matching
To avoid the laborious annotation in conventional referring grounding, unpaired referring grounding is introduced, where the training data only contains a number of images and queries without correspondences.
Transformer Scale Gate for Semantic Segmentation
Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation.
AV-Gaze: A Study on the Effectiveness of Audio Guided Visual Attention Estimation for Non-Profilic Faces
In challenging real-life conditions such as extreme head-pose, occlusions, and low-resolution images where the visual information fails to estimate visual attention/gaze direction, audio signals could provide important and complementary information.
Concealing Sensitive Samples against Gradient Leakage in Federated Learning
Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server.
ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning
Finally, ProtoCon addresses the poor training signal in the initial phase of training (due to fewer confident predictions) by introducing an auxiliary self-supervised loss.
Open-Vocabulary Object Detection via Scene Graph Discovery
However, they only use pairs of nouns and individual objects in VL data, while these data usually contain much more information, such as scene graphs, which are also crucial for OV detection.
Unified Open-Vocabulary Dense Visual Prediction
We present a UOVN training mechanism to reduce such gaps.
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation
EBL can be used to improve the instance selection for a self-training task on the unlabelled target domain, and 2. alignment and normalizing energy scores can learn domain-invariant representations.
DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition
The task of Visual Relationship Recognition (VRR) aims to identify relationships between two interacting objects in an image and is particularly challenging due to the widely-spread and highly imbalanced distribution of <subject, relation, object> triplets.
EraseDiff: Erasing Data Influence in Diffusion Models
In this work, we introduce an unlearning algorithm for diffusion models.
OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation
We propose OCAI, a method that supports robust frame interpolation by generating intermediate video frames alongside optical flows in between.
