Search Results for author:
Found 74 papers, 18 papers with code
Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps
As a result, such syntactic relationships can be overlooked in cross-attention module, leading to inaccurate image generation.
Learning to Customize Text-to-Image Diffusion In Diverse Context
This often results in the model becoming overfitted to these training images and unable to generalize to new contexts in future text prompts.
Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
We show that PSO can directly adapt distilled models to human-preferred generation with both offline and online-generated pairwise preference image data.
Posterior sampling via Langevin dynamics based on generative priors
Posterior sampling in high-dimensional spaces using generative models holds significant promise for various applications, including but not limited to inverse problems and guided generation tasks.
Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort
Enhancing model interpretability can address spurious correlations by revealing how models draw their predictions.
Model-Agnostic Human Preference Inversion in Diffusion Models
Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models.
Generative Quanta Color Imaging
In this paper, we explore the possibility of generating a color image from a single binary frame of a single-photon camera.
Large Convolutional Model Tuning via Filter Subspace
Furthermore, each filter atom can be recursively decomposed as a combination of another set of atoms, which naturally expands the number of tunable parameters in the filter subspace.
Training Bayesian Neural Networks with Sparse Subspace Variational Inference
Bayesian neural networks (BNNs) offer uncertainty quantification but come with the downside of substantially increased training and inference costs.
Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning
We also show the effectiveness of our RL fine-tuning framework on enhancing the diversity of image generation with different types of diffusion models including class-conditional models and text-conditional models e. g. StableDiffusion.
Dynamic Frequency Domain Graph Convolutional Network for Traffic Forecasting
Complex spatial dependencies in transportation networks make traffic prediction extremely challenging.
Binary Latent Diffusion
In this paper, we show that a binary latent space can be explored for compact yet expressive image representations.
Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation
To this end, at every generator update, we aim to maintain the student's performance on previously encountered examples while acquiring knowledge from samples of the current distribution.
Energy-Inspired Self-Supervised Pretraining for Vision Models
In the proposed framework, we model energy estimation and data restoration as the forward and backward passes of a single network without any auxiliary components, e. g., an extra decoder.
Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition
To this end, we propose a pseudo-label generation and an uncertainty-based data selection framework for semi-supervised text recognition.
Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?
In this paper, we question the rationale behind propagating large numbers of parameters through a distributed system during federated learning.
Learning to Learn Dense Gaussian Processes for Few-Shot Learning
In contrast to sparse Gaussian processes, we define a set of dense inducing variables to be of a much larger size than the support set in each task, which collects prior knowledge from experienced tasks.
Image Generation using Continuous Filter Atoms
In this paper, we model the subspace of convolutional filters with a neural ordinary differential equation (ODE) to enable gradual changes in generated images.
Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks
In this paper, we introduce spatiotemporal joint filter decomposition to decouple spatial and temporal learning, while preserving spatiotemporal dependency in a video.
TESSERACT: Gradient Flip Score to Secure Federated Learning Against Model Poisoning Attacks
The attack uses the intuition that simply by changing the sign of the gradient updates that the optimizer is computing, for a set of malicious clients, a model can be diverted from the optima to increase the test error rate.
Meta-OLE: Meta-learned Orthogonal Low-Rank Embedding
We introduce Meta-OLE, a new geometry-regularized method for fast adaptation to novel tasks in few-shot image classification.
Continual Learning with Filter Atom Swapping
In this paper, we first enforce a low-rank filter subspace by decomposing convolutional filters within each network layer over a small set of filter atoms.
A Joint Subspace View to Convolutional Neural Networks
In other words, a CNN is now reduced to layers of filter atoms, typically a few hundred of parameters per layer, with a common block of subspace coefficients shared across layers.
Adaptive Convolutions with Per-pixel Dynamic Filter Atom
Applying feature dependent network weights have been proved to be effective in many fields.
Cirrus: A Long-range Bi-pattern LiDAR Dataset
Point density varies significantly across such a long range, and different scanning patterns further diversify object representation in LiDAR.
Using Text to Teach Image Retrieval
Image retrieval relies heavily on the quality of the data modeling and the distance measurement in the feature space.
Learning to Learn Variational Semantic Memory
The variational semantic memory accrues and stores semantic information for the probabilistic inference of class prototypes in a hierarchical Bayesian framework.
ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution
We then explicitly regularize CNN kernels by enforcing decomposed coefficients to be shared across sub-structures, while leaving each sub-structure only its own dictionary atoms, a few hundreds of parameters typically, which leads to dramatic model reductions.
Graph Convolution with Low-rank Learnable Local Filters
Recent deep models using graph convolutions provide an appropriate framework to handle such non-Euclidean data, but many of them, particularly those based on global graph Laplacians, lack expressiveness to capture local features required for representation of signals lying on the non-Euclidean grid.
Learning to Learn with Variational Information Bottleneck for Domain Generalization
Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift.
Low to High Dimensional Modality Hallucination using Aggregated Fields of View
While hallucinating data from a modality with richer information, e. g., RGB to depth, has been researched extensively, we investigate the more challenging low-to-high modality hallucination with interesting use cases in robotics and autonomous systems.
Differential 3D Facial Recognition: Adding 3D to Your State-of-the-Art 2D Method
Active illumination is a prominent complement to enhance 2D face recognition and make it more robust, e. g., to spoofing attacks and low-light conditions.
SalGaze: Personalizing Gaze Estimation Using Visual Saliency
Traditional gaze estimation methods typically require explicit user calibration to achieve high accuracy.
Range Adaptation for 3D Object Detection in LiDAR
To the best of our knowledge, this paper is the first attempt to study cross-range LiDAR adaptation for object detection in point clouds.
Stochastic Conditional Generative Networks with Basis Decomposition
One of these questions is how to efficiently achieve proper diversity and sampling of the multi-mode data space.
Scale-Equivariant Neural Networks with Decomposed Convolutional Filters
Encoding the input scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many vision tasks especially when dealing with multiscale input signals.
A Dictionary Approach to Domain-Invariant Learning in Deep Networks
In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN).
Domain-invariant Learning using Adaptive Filter Decomposition
Domain shifts are frequently encountered in real-world scenarios.
Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters
Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when dealing with multiscale inputs.
Single-shot 3D shape reconstruction using deep convolutional neural networks
A robust single-shot 3D shape reconstruction technique integrating the fringe projection profilometry (FPP) technique with the deep convolutional neural networks (CNNs) is proposed in this letter.
Hubless Nearest Neighbor Search for Bilingual Lexicon Induction
Recent advances in BLI work by aligning the two word embedding spaces.
Learning data-derived privacy preserving representations from information metrics
We study space-preserving transformations where the utility provider can use the same algorithm on original and sanitized data, a critical and novel attribute to help service providers accommodate varying privacy requirements with a single set of utility algorithms.
In Defense of Single-column Networks for Crowd Counting
Crowd counting usually addressed by density estimation becomes an increasingly important topic in computer vision due to its widespread applications in video surveillance, urban planning, and intelligence gathering.
LaneNet: Real-Time Lane Detection Networks for Autonomous Driving
Lane detection is to detect lanes on the road and provide the accurate location and shape of each lane.
OLÃ: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep Learning
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification.
Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning
Deep neural networks (DNNs) typically have enough capacity to fit random data by brute force even when conventional data-dependent regularizations focusing on the geometry of the features are imposed.
Learning to Collaborate for User-Controlled Privacy
As such, users and utility providers should collaborate in data privacy, a paradigm that has not yet been developed in the privacy research community.
RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks
Explicit encoding of group actions in deep features makes it possible for convolutional neural networks (CNNs) to handle global deformations of images, which is critical to success in many vision tasks.
Liveness Detection Using Implicit 3D Features
Spoofing attacks are a threat to modern face recognition systems.
Weakly Supervised Instance Segmentation using Class Peak Response
Motivated by this, we first design a process to stimulate peaks to emerge from a class response map.
Ranked #13 on
Image-level Supervised Instance Segmentation
on PASCAL VOC 2012 val
(using extra training data)
General Classification
Image-level Supervised Instance Segmentation
+3
Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification
In this paper we introduce an ensemble method for convolutional neural network (CNN), called "virtual branching," which can be implemented with nearly no additional parameters and computation on top of standard CNNs.
DCFNet: Deep Neural Network with Decomposed Convolutional Filters
In this paper, we suggest to decompose convolutional filters in CNN as a truncated expansion with pre-fixed bases, namely the Decomposed Convolutional Filters network (DCFNet), where the expansion coefficients remain learned from data.
OLÉ: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification.
ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees.
LDMNet: Low Dimensional Manifold Regularized Neural Networks
To resolve this, we propose a new framework, the Low-Dimensional-Manifold-regularized neural Network (LDMNet), which incorporates a feature regularization method that focuses on the geometry of both the input data and the output features.
Soft Proposal Networks for Weakly Supervised Object Localization
Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training.
Ranked #2 on
Weakly Supervised Object Detection
on MS COCO
Learning to Succeed while Teaching to Fail: Privacy in Closed Machine Learning Systems
Confronted with this challenge, in this paper we open a new line of research, where the security, privacy, and fairness is learned and used in a closed environment.
Oriented Response Networks
DCNNs using ARFs, referred to as Oriented Response Networks (ORNs), can produce within-class rotation-invariant deep features while maintaining inter-class discrimination for classification tasks.
Ranked #82 on
Image Classification
on CIFAR-100
(using extra training data)
Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model
In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved.
Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-spectral Hallucination and Low-rank Embedding
We observe that it is often equally effective to perform hallucination to input NIR images or low-rank embedding to output deep features for a VIS deep model for cross-spectral recognition.
GraphConnect: A Regularization Framework for Neural Networks
The new method encourages the relationships between the learned decisions to resemble a graph representing the manifold structure.
Discriminative Robust Transformation Learning
This paper proposes a framework for learning features that are robust to data variation, which is particularly important when only a limited number of trainingsamples are available.
Geometry-aware Deep Transform
Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets.
The Role of Principal Angles in Subspace Classification
Subspace models play an important role in a wide range of signal processing tasks, and this paper explores how the pairwise geometry of subspaces influences the probability of misclassification.
Data Representation using the Weyl Transform
The Weyl transform is introduced as a rich framework for data representation.
Random Forests Can Hash
Traditional random forest fails to enforce the consistency of hashes generated from each tree for the same class data, i. e., to preserve the underlying similarity, and it also lacks a principled way for code aggregation across trees.
Learning Transformations for Classification Forests
This work introduces a transformation-based learner model for classification forests.
Learning Transformations for Clustering and Classification
A low-rank transformation learning framework for subspace clustering and classification is here proposed.
Compositional Dictionaries for Domain Adaptive Face Recognition
This approach has three advantages: first, the extracted sparse representation for a subject is consistent across domains and enables pose and illumination insensitive face recognition.
Domain-invariant Face Recognition using Learned Low-rank Transformation
We present a low-rank transformation approach to compensate for face variations due to changes in visual domains, such as pose and illumination.
Sparse Dictionary-based Attributes for Action Recognition and Summarization
We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes.
Learning Robust Subspace Clustering
This proposed learned robust subspace clustering framework significantly enhances the performance of existing subspace clustering methods.
Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation
Domain adaptation addresses the problem where data instances of a source domain have different distributions from that of a target domain, which occurs frequently in many real life scenarios.
