37 citations · 209 across the 24 of their papers we have counts for
24 papers
Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning
Vinay K Verma, Nikhil Mehta, Kevin J Liang +2
Zero-shot learning (ZSL) is a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges remain. Recently, metho…
Pseudo-label Correction and Learning For Semi-Supervised Object Detection
Yulin He, Wei Chen, Ke Liang +3
Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly de…
EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset
Hao Tang, Kevin Liang, Matt Feiszli +1
Visual object tracking is a key component to many egocentric vision problems. However, the full spectrum of challenges of egocentric tracking faced by an embodied AI is underrepres…
Task Grouping for Multilingual Text Recognition
Jing Huang, Kevin J Liang, Rama Kovvuri +1
Most existing OCR methods focus on alphanumeric characters due to the popularity of English and numbers, as well as their corresponding datasets. On extending the characters to mor…
GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction
Samrudhdhi B Rangrej, Kevin J Liang, Tal Hassner +1
Many online action prediction models observe complete frames to locate and attend to informative subregions in the frames called glimpses and recognize an ongoing action based on g…
Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection
Li Yin, Juan M Perez-Rua, Kevin J Liang
We study the challenging incremental few-shot object detection (iFSD) setting. Recently, hypernetwork-based approaches have been studied in the context of continuous and finetune-f…
Few-shot Learning with Noisy Labels
Kevin J Liang, Samrudhdhi B. Rangrej, Vladan Petrovic +1
Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: suppor…
Extending One-Stage Detection with Open-World Proposals
Sachin Konan, Kevin J Liang, Li Yin
In many applications, such as autonomous driving, hand manipulation, or robot navigation, object detection methods must be able to detect objects unseen in the training set. Open W…
An extended Krylov subspace method for decoding edge-based compressed images by homogeneous diffusion
Volker Grimm, Kevin Liang
The heat equation is often used in order to inpaint dropped data in inpainting-based lossy compression schemes. We propose an alternative way to numerically solve the heat equation…
Towards Fair Federated Learning with Zero-Shot Data Augmentation
Weituo Hao, Mostafa El-Khamy, Jungwon Lee +4
Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the…
A Multiplexed Network for End-to-End, Multilingual OCR
Jing Huang, Guan Pang, Rama Kovvuri +5
Recent advances in OCR have shown that an end-to-end (E2E) training pipeline that includes both detection and recognition leads to the best results. However, many existing methods…
Efficient Feature Transformations for Discriminative and Generative Continual Learning
Vinay Kumar Verma, Kevin J Liang, Nikhil Mehta +2
As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critica…
Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?
Nathan Inkawhich, Kevin J Liang, Jingyang Zhang +3
We design blackbox transfer-based targeted adversarial attacks for an environment where the attacker's source model and the target blackbox model may have disjoint label spaces and…
Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
Vinay Kumar Verma, Kevin Liang, Nikhil Mehta +1
Zero-shot learning (ZSL) has been shown to be a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges still…
MixKD: Towards Efficient Distillation of Large-scale Language Models
Kevin J Liang, Weituo Hao, Dinghan Shen +4
Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power c…
Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images
John B. Sigman, Gregory P. Spell, Kevin J Liang +1
Recently, progress has been made in the supervised training of Convolutional Object Detectors (e.g. Faster R-CNN) for threat recognition in carry-on luggage using X-ray images. Thi…
WAFFLe: Weight Anonymized Factorization for Federated Learning
Weituo Hao, Nikhil Mehta, Kevin J Liang +3
In domains where data are sensitive or private, there is great value in methods that can learn in a distributed manner without the data ever leaving the local devices. In light of…
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
Nathan Inkawhich, Kevin J Liang, Binghui Wang +3
We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers. Rather than focusing on crossing decis…
Transferable Perturbations of Deep Feature Distributions
Nathan Inkawhich, Kevin J Liang, Lawrence Carin +1
Almost all current adversarial attacks of CNN classifiers rely on information derived from the output layer of the network. This work presents a new adversarial attack based on the…
Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors
Nikhil Mehta, Kevin J Liang, Vinay K Verma +1
Naively trained neural networks tend to experience catastrophic forgetting in sequential task settings, where data from previous tasks are unavailable. A number of methods, using v…
Object Detection as a Positive-Unlabeled Problem
Yuewei Yang, Kevin J Liang, Lawrence Carin
As with other deep learning methods, label quality is important for learning modern convolutional object detectors. However, the potentially large number and wide diversity of obje…
Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detection
Kevin J Liang, John B. Sigman, Gregory P. Spell +5
For the safety of the traveling public, the Transportation Security Administration (TSA) operates security checkpoints at airports in the United States, seeking to keep dangerous i…
Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods
Kevin J Liang, Guoyin Wang, Yitong Li +2
We investigate time-dependent data analysis from the perspective of recurrent kernel machines, from which models with hidden units and gated memory cells arise naturally. By consid…
Generative Adversarial Network Training is a Continual Learning Problem
Kevin J Liang, Chunyuan Li, Guoyin Wang +1
Generative Adversarial Networks (GANs) have proven to be a powerful framework for learning to draw samples from complex distributions. However, GANs are also notoriously difficult…