Search Results for author:
Found 103 papers, 23 papers with code
On Modulating the Gradient for Meta-Learning
Inspired by optimization techniques, we propose a novel meta-learning algorithm with gradient modulation to encourage fast-adaptation of neural networks in the absence of abundant data.
Backpropagation-free Network for 3D Test-time Adaptation
Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data.
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression
3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity.
Text-Enhanced Data-free Approach for Federated Class-Incremental Learning
In this field, Data-Free Knowledge Transfer (DFKT) plays a crucial role in addressing catastrophic forgetting and data privacy problems.
EraseDiff: Erasing Data Influence in Diffusion Models
In this work, we introduce an unlearning algorithm for diffusion models.
Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks
Machine unlearning has become a pivotal task to erase the influence of data from a trained model.
LaViP:Language-Grounded Visual Prompts
We introduce a language-grounded visual prompting method to adapt the visual encoder of vision-language models for downstream tasks.
Real-time Neonatal Chest Sound Separation using Deep Learning
Inspired by the Conv-TasNet model, the proposed model has an encoder, decoder, and mask generator.
Continual Test-time Domain Adaptation via Dynamic Sample Selection
DSS consists of dynamic thresholding, positive learning, and negative learning processes.
NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
In this paper, we propose a novel Noisy Layer Generation method (NAYER) which relocates the random source from the input to a noisy layer and utilizes the meaningful constant label-text embedding (LTE) as the input.
RSAM: Learning on manifolds with Riemannian Sharpness-aware Minimization
Motivated by this analysis, we introduce our algorithm, Riemannian Sharpness-Aware Minimization (RSAM).
Hyperbolic Audio-visual Zero-shot Learning
Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training.
Ranked #2 on
GZSL Video Classification
on ActivityNet-GZSL (cls)
Subspace Distillation for Continual Learning
To mitigate forgetting prior knowledge, we propose a novel knowledge distillation technique that takes into the account the manifold structure of the latent/output space of a neural network in learning novel tasks.
L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space
To address the problem, we propose a distillation strategy named L3DMC that operates on mixed-curvature spaces to preserve the already-learned knowledge by modeling and maintaining complex geometrical structures.
EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos
We constrain the learned shape by tailoring multiple regularization strategies and disentangling geometry and appearance.
Contrastive Learning MRI Reconstruction
We show that this latent space can be utilized for accelerated MR image reconstruction.
Hyperbolic Geometry in Computer Vision: A Survey
Hyperbolic geometry, a Riemannian manifold endowed with constant sectional negative curvature, has been considered an alternative embedding space in many learning scenarios, \eg, natural language processing, graph learning, \etc, as a result of its intriguing property of encoding the data's hierarchical structure (like irregular graph or tree-likeness data).
Exploring Data Geometry for Continual Learning
Our method dynamically expands the geometry of the underlying space to match growing geometric structures induced by new data, and prevents forgetting by keeping geometric structures of old data into account.
Vector Quantized Wasserstein Auto-Encoder
Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks.
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.
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partial known data.
Multimorbidity Content-Based Medical Image Retrieval Using Proxies
Medical imaging data, such as radiology images, are often multimorbidity; a single sample may have more than one pathology present.
LAVA: Label-efficient Visual Learning and Adaptation
We present LAVA, a simple yet effective method for multi-domain visual transfer learning with limited data.
A Differentiable Distance Approximation for Fairer Image Classification
We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios, whilst still maintaining a high level of classification accuracy.
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.
Learning Deep Optimal Embeddings with Sinkhorn Divergences
Deep Metric Learning algorithms aim to learn an efficient embedding space to preserve the similarity relationships among the input data.
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.
Curved Geometric Networks for Visual Anomaly Recognition
Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature.
Deep Laparoscopic Stereo Matching with Transformers
The self-attention mechanism, successfully employed with the transformer structure is shown promise in many computer vision tasks including image recognition, and object detection.
Multi-branch Cascaded Swin Transformers with Attention to k-space Sampling Pattern for Accelerated MRI Reconstruction
Convolutional neural network (CNN) models are widely utilized for accelerated MRI reconstruction, but those models are limited in capturing global correlations due to the intrinsic locality of the convolution operation.
Rethinking Generalization in Few-Shot Classification
Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted.
On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation
Inspired by the concept of preconditioning, we propose a novel method to increase adaptation speed for gradient-based meta-learning methods without incurring extra parameters.
GOSS: Towards Generalized Open-set Semantic Segmentation
In this paper, we present and study a new image segmentation task, called Generalized Open-set Semantic Segmentation (GOSS).
Implicit Motion Handling for Video Camouflaged Object Detection
We propose a new video camouflaged object detection (VCOD) framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames.
Ranked #2 on
Camouflaged Object Segmentation
on Camouflaged Animal Dataset
(using extra training data)
On Generalizing Beyond Domains in Cross-Domain Continual Learning
Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.
Reciprocal Adversarial Learning for Brain Tumor Segmentation: A Solution to BraTS Challenge 2021 Segmentation Task
In this concept, the 3D segmentation network learns from dual reciprocal adversarial learning approaches.
Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning
A principle way of achieving few-shot learning is to realize a model that can rapidly adapt to the context of a given task.
Adaptive Poincaré Point to Set Distance for Few-Shot Classification
To this end, we formulate the metric as a weighted sum on the tangent bundle of the hyperbolic space and develop a mechanism to obtain the weights adaptively and based on the constellation of the points.
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.
Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
Uncertainty estimation has been extensively studied in recent literature, which can usually be classified as aleatoric uncertainty and epistemic uncertainty.
Learning Online for Unified Segmentation and Tracking Models
A segmentation model cannot easily learn from prior information given in the visual tracking scenario.
Meta-Learning for Multi-Label Few-Shot Classification
Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address.
Towards a Robust Differentiable Architecture Search under Label Noise
Our empirical evaluations show that the noise injecting operation does not degrade the performance of the NAS algorithm if the data is indeed clean.
Dense Uncertainty Estimation
Deep neural networks can be roughly divided into deterministic neural networks and stochastic neural networks. The former is usually trained to achieve a mapping from input space to output space via maximum likelihood estimation for the weights, which leads to deterministic predictions during testing.
Designing Less Forgetful Networks for Continual Learning
Neural networks usually excel in learning a single task.
IDENTIFYING CONCEALED OBJECTS FROM VIDEOS
The proposed SLT-Net leverages on both short-term dynamics and long-term temporal consistency to detect concealed objects in continuous video frames.
Feature Correlation Aggregation: on the Path to Better Graph Neural Networks
The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbors.
Duo-SegNet: Adversarial Dual-Views for Semi-Supervised Medical Image Segmentation
Segmentation of images is a long-standing challenge in medical AI.
Semi-Supervised Metric Learning: A Deep Resurrection
In this paper, we address the problem of Semi-Supervised DML (SSDML) that tries to learn a metric using a few labeled examples, and abundantly available unlabeled examples.
Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.
On Learning the Geodesic Path for Incremental Learning
This in practice is done by minimizing the dissimilarity between current and previous responses of the network one way or another.
Learning Log-Determinant Divergences for Positive Definite Matrices
There exist several similarity measures for comparing SPD matrices with documented benefits.
Reinforced Attention for Few-Shot Learning and Beyond
Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images.
Learning to Continually Learn Rapidly from Few and Noisy Data
Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution.
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner.
Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record.
Curvature Generation in Curved Spaces for Few-Shot Learning
Few-shot learning describes the challenging problem of recognizing samples from unseen classes given very few labeled examples.
Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces
In this paper, we propose addressing this problem using a mixture of subspaces.
Kernel Methods in Hyperbolic Spaces
However, working in hyperbolic spaces is not without difficulties as a result of its curved geometry (e. g., computing the Frechet mean of a set of points requires an iterative algorithm).
Highway-Connection Classifier Networks for Plastic yet Stable Continual Learning
Catastrophic forgetting occurs when a neural network is trained sequentially on multiple tasks – its weights will be continuously modified and as a result, the network will lose its ability in solving a previous task.
Uncertainty-Aware Deep Calibrated Salient Object Detection
Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy.
Set Augmented Triplet Loss for Video Person Re-Identification
Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss.
Hierarchical Neural Architecture Search for Deep Stereo Matching
To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classification and semantic segmentation.
Ranked #2 on
Stereo Disparity Estimation
on Scene Flow
Channel Recurrent Attention Networks for Video Pedestrian Retrieval
Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks.
Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss
As obtaining class labels in all applications is not feasible, we propose an unsupervised approach that learns a metric without making use of class labels.
MTL2L: A Context Aware Neural Optimiser
Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner.
Cross-Correlated Attention Networks for Person Re-Identification
Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered.
Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
We design a regularisation technique to regulate the domain adaptation.
Affinity guided Geometric Semi-Supervised Metric Learning
In this paper, we revamp the forgotten classical Semi-Supervised Distance Metric Learning (SSDML) problem from a Riemannian geometric lens, to leverage stochastic optimization within a end-to-end deep framework.
A Probabilistic approach for Learning Embeddings without Supervision
This restricts their applicability for large datasets in new applications where obtaining labels require extensive manual efforts and domain knowledge.
Projective Subspace Networks For Few-Shot Learning
Generalization from limited examples, usually studied under the umbrella of meta-learning, equips learning techniques with the ability to adapt quickly in dynamical environments and proves to be an essential aspect of lifelong learning.
Neural Collaborative Subspace Clustering
We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces.
Scalable Deep $k$-Subspace Clustering
In this paper, we introduce a method that simultaneously learns an embedding space along subspaces within it to minimize a notion of reconstruction error, thus addressing the problem of subspace clustering in an end-to-end learning paradigm.
Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond
To achieve robust baselines, we build on a recent approach that aligns per-class scatter matrices of the source and target CNN streams.
Geometry Aware Constrained Optimization Techniques for Deep Learning
In this paper, we extend some popular optimization algorithm to the Riemannian (constrained) setting.
Block Mean Approximation for Efficient Second Order Optimization
Advanced optimization algorithms such as Newton method and AdaGrad benefit from second order derivative or second order statistics to achieve better descent directions and faster convergence rates.
Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
Such supervision, while labor-intensive and not always possible, tends to hinder the generalization ability of the learned models.
Devon: Deformable Volume Network for Learning Optical Flow
State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions.
Museum Exhibit Identification Challenge for Domain Adaptation and Beyond
To achieve robust baselines, we build on a recent approach that aligns per-class scatter matrices of the source and target CNN streams [15].
Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding
Linear Dynamical Systems (LDSs) are fundamental tools for modeling spatio-temporal data in various disciplines.
Learning Discriminative ab-Divergences for Positive Definite Matrices
Symmetric positive definite (SPD) matrices are useful for capturing second-order statistics of visual data.
Learning Discriminative Alpha-Beta-divergence for Positive Definite Matrices (Extended Version)
Symmetric positive definite (SPD) matrices are useful for capturing second-order statistics of visual data.
Joint Dimensionality Reduction and Metric Learning: A Geometric Take
To be tractable and robust to data noise, existing metric learning algorithms commonly rely on PCA as a pre-processing step.
Generalized Rank Pooling for Activity Recognition
Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity.
Learning an Invariant Hilbert Space for Domain Adaptation
This paper introduces a learning scheme to construct a Hilbert space (i. e., a vector space along its inner product) to address both unsupervised and semi-supervised domain adaptation problems.
Generalized BackPropagation, Étude De Cas: Orthogonality
This paper introduces an extension of the backpropagation algorithm that enables us to have layers with constrained weights in a deep network.
Dimensionality Reduction
Fine-Grained Image Classification
+1
Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning
We then devise efficient algorithms to perform sparse coding and dictionary learning on the space of infinite-dimensional subspaces.
Sparse Coding and Dictionary Learning With Linear Dynamical Systems
To enhance the performance of LDSs, in this paper, we address the challenging issue of performing sparse coding on the space of LDSs, where both data and dictionary atoms are LDSs.
Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods
This lets us formulate dimensionality reduction as the problem of finding a projection that yields a low-dimensional manifold either with maximum discriminative power in the supervised scenario, or with maximum variance of the data in the unsupervised one.
Going Deeper into Action Recognition: A Survey
Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation.
Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs
State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution.
When VLAD met Hilbert
Vectors of Locally Aggregated Descriptors (VLAD) have emerged as powerful image/video representations that compete with or even outperform state-of-the-art approaches on many challenging visual recognition tasks.
Riemannian Coding and Dictionary Learning: Kernels to the Rescue
While sparse coding on non-flat Riemannian manifolds has recently become increasingly popular, existing solutions either are dedicated to specific manifolds, or rely on optimization problems that are difficult to solve, especially when it comes to dictionary learning.
Optimizing Over Radial Kernels on Compact Manifolds
We tackle the problem of optimizing over all possible positive definite radial kernels on Riemannian manifolds for classification.
A Framework for Shape Analysis via Hilbert Space Embedding
We propose a framework for 2D shape analysis using positive definite kernels defined on Kendall's shape manifold.
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
To encode the geometry of the manifold in the mapping, we introduce a family of provably positive definite kernels on the Riemannian manifold of SPD matrices.
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
We then use the proposed framework to identify positive definite kernels on two specific manifolds commonly encountered in computer vision: the Riemannian manifold of symmetric positive definite matrices and the Grassmann manifold, i. e., the Riemannian manifold of linear subspaces of a Euclidean space.
Kernel Coding: General Formulation and Special Cases
In contrast, here, we study the problem of performing coding in a high-dimensional Hilbert space, where the classes are expected to be more easily separable.
Sparse Coding on Symmetric Positive Definite Manifolds using Bregman Divergences
This paper introduces sparse coding and dictionary learning for Symmetric Positive Definite (SPD) matrices, which are often used in machine learning, computer vision and related areas.
Bregman Divergences for Infinite Dimensional Covariance Matrices
We introduce an approach to computing and comparing Covariance Descriptors (CovDs) in infinite-dimensional spaces.
Multi-Shot Person Re-Identification via Relational Stein Divergence
The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately.
Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds
With the aim of building a bridge between the two realms, we address the problem of sparse coding and dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds.
Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution
Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry.
