71 citations · 416 across the 50 of their papers we have counts for
38 papers · 1 filter
Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
Gaurav Patel, Jun Fang, Greg Ver Steeg +2
Text-to-image diffusion models are increasingly distilled into few-step variants and being deployed to enable fast inference. However, their ability to generate harmful or undesire…
Binary Latent Diffusion
Ze Wang, Jiang Wang, Zicheng Liu +1
In this paper, we show that a binary latent space can be explored for compact yet expressive image representations. We model the bi-directional mappings between an image and the co…
Energy-Inspired Self-Supervised Pretraining for Vision Models
Ze Wang, Jiang Wang, Zicheng Liu +1
Motivated by the fact that forward and backward passes of a deep network naturally form symmetric mappings between input and output representations, we introduce a simple yet effec…
Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition
Gaurav Patel, Jan Allebach, Qiang Qiu
This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to…
Adaptive Convolutions with Per-pixel Dynamic Filter Atom
Ze Wang, Zichen Miao, Jun Hu +1
Applying feature dependent network weights have been proved to be effective in many fields. However, in practice, restricted by the enormous size of model parameters and memory foo…
Cirrus: A Long-range Bi-pattern LiDAR Dataset
Ze Wang, Sihao Ding, Ying Li +7
In this paper, we introduce Cirrus, a new long-range bi-pattern LiDAR public dataset for autonomous driving tasks such as 3D object detection, critical to highway driving and timel…
ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution
Ze Wang, Xiuyuan Cheng, Guillermo Sapiro +1
Convolutional Neural Networks (CNNs) are known to be significantly over-parametrized, and difficult to interpret, train and adapt. In this paper, we introduce a structural regulari…
Learning to Learn with Variational Information Bottleneck for Domain Generalization
Yingjun Du, Jun Xu, Huan Xiong +4
Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift. In this paper, we address both problems. We…
Low to High Dimensional Modality Hallucination using Aggregated Fields of View
Kausic Gunasekar, Qiang Qiu, Yezhou Yang
Real-world robotics systems deal with data from a multitude of modalities, especially for tasks such as navigation and recognition. The performance of those systems can drastically…
Differential 3D Facial Recognition: Adding 3D to Your State-of-the-Art 2D Method
J. Matias Di Martino, Fernando Suzacq, Mauricio Delbracio +2
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. In the present work we sho…
SalGaze: Personalizing Gaze Estimation Using Visual Saliency
Zhuoqing Chang, Matias Di Martino, Qiang Qiu +2
Traditional gaze estimation methods typically require explicit user calibration to achieve high accuracy. This process is cumbersome and recalibration is often required when there…
Range Adaptation for 3D Object Detection in LiDAR
Ze Wang, Sihao Ding, Ying Li +5
LiDAR-based 3D object detection plays a crucial role in modern autonomous driving systems. LiDAR data often exhibit severe changes in properties across different observation ranges…
Stochastic Conditional Generative Networks with Basis Decomposition
Ze Wang, Xiuyuan Cheng, Guillermo Sapiro +1
While generative adversarial networks (GANs) have revolutionized machine learning, a number of open questions remain to fully understand them and exploit their power. One of these…
In Defense of Single-column Networks for Crowd Counting
Ze Wang, Zehao Xiao, Kai Xie +3
Crowd counting usually addressed by density estimation becomes an increasingly important topic in computer vision due to its widespread applications in video surveillance, urban pl…
LaneNet: Real-Time Lane Detection Networks for Autonomous Driving
Ze Wang, Weiqiang Ren, Qiang Qiu
Lane detection is to detect lanes on the road and provide the accurate location and shape of each lane. It severs as one of the key techniques to enable modern assisted and autonom…
RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks
Xiuyuan Cheng, Qiang Qiu, Robert Calderbank +1
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…
Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning
Wei Zhu, Qiang Qiu, Bao Wang +3
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 f…
Weakly Supervised Instance Segmentation using Class Peak Response
Yanzhao Zhou, Yi Zhu, Qixiang Ye +2
Weakly supervised instance segmentation with image-level labels, instead of expensive pixel-level masks, remains unexplored. In this paper, we tackle this challenging problem by ex…
Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification
Albert Gong, Qiang Qiu, Guillermo Sapiro
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…
OLÉ: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning
José Lezama, Qiang Qiu, Pablo Musé +1
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-c…
LDMNet: Low Dimensional Manifold Regularized Neural Networks
Wei Zhu, Qiang Qiu, Jiaji Huang +3
Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers f…
ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
Qiang Qiu, Jose Lezama, Alex Bronstein +1
Hash codes are efficient data representations for coping with the ever growing amounts of data. In this paper, we introduce a random forest semantic hashing scheme that embeds tiny…
Soft Proposal Networks for Weakly Supervised Object Localization
Yi Zhu, Yanzhao Zhou, Qixiang Ye +2
Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training. Object proposal is an effective componen…
Oriented Response Networks
Yanzhao Zhou, Qixiang Ye, Qiang Qiu +1
Deep Convolution Neural Networks (DCNNs) are capable of learning unprecedentedly effective image representations. However, their ability in handling significant local and global im…