Search Results for author:
Found 82 papers, 36 papers with code
ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos
Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines.
Ranked #3 on
Human-Object Interaction Anticipation
on VidHOI
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot
In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods and surprisingly find that: (1) A set of methods which aims to find good subnetworks of the randomly-initialized network (which we call "initial tickets"), hardly exploits any information from the training data; (2) For the pruned networks obtained by these methods, randomly changing the preserved weights in each layer, while keeping the total number of preserved weights unchanged per layer, does not affect the final performance.
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
We provide an explanation by showing that InstanceNorm serves as a preconditioner for GNNs, but such preconditioning effect is weaker with BatchNorm due to the heavy batch noise in graph datasets.
Ranked #25 on
Graph Property Prediction
on ogbg-molhiv
Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL
The regret of FMDP-BF is shown to be exponentially smaller than that of optimal algorithms designed for non-factored MDPs, and improves on the best previous result for FMDPs~\citep{osband2014near} by a factored of $\sqrt{H|\mathcal{S}_i|}$, where $|\mathcal{S}_i|$ is the cardinality of the factored state subspace and $H$ is the planning horizon.
Improving One-stage Visual Grounding by Recursive Sub-query Construction
We improve one-stage visual grounding by addressing current limitations on grounding long and complex queries.
RANDOM MASK: Towards Robust Convolutional Neural Networks
We next investigate the adversarial examples which 'fool' a CNN with Random Mask.
Transferred Discrepancy: Quantifying the Difference Between Representations
Our experiments show that TD can provide fine-grained information for varied downstream tasks, and for the models trained from different initializations, the learned features are not the same in terms of downstream-task predictions.
Comprehensive Image Captioning via Scene Graph Decomposition
We address the challenging problem of image captioning by revisiting the representation of image scene graph.
RepPoints V2: Verification Meets Regression for Object Detection
Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement.
Ranked #27 on
Object Detection
on COCO-O
MC-BERT: Efficient Language Pre-Training via a Meta Controller
Pre-trained contextual representations (e. g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks.
Multi-modal Feature Fusion with Feature Attention for VATEX Captioning Challenge 2020
This report describes our model for VATEX Captioning Challenge 2020.
(Locally) Differentially Private Combinatorial Semi-Bandits
In this paper, we study Combinatorial Semi-Bandits (CSB) that is an extension of classic Multi-Armed Bandits (MAB) under Differential Privacy (DP) and stronger Local Differential Privacy (LDP) setting.
Locally Differentially Private (Contextual) Bandits Learning
We study locally differentially private (LDP) bandits learning in this paper.
METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
In answer, we posit that a smaller yet diverse set of unit cells leads to scalable search and unbiased learning.
Boosting Few-Shot Learning With Adaptive Margin Loss
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples.
Ranked #1 on
Few-Shot Image Classification
on ImageNet (1-shot)
Improve bone age assessment by learning from anatomical local regions
In the clinical practice, Tanner and Whitehouse (TW2) method is a widely-used method for radiologists to perform BAA.
MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning
Generating multi-sentence descriptions for videos is one of the most challenging captioning tasks due to its high requirements for not only visual relevance but also discourse-based coherence across the sentences in the paragraph.
Ranked #5 on
Video Captioning
on ActivityNet Captions
Memory Enhanced Global-Local Aggregation for Video Object Detection
We argue that there are two important cues for humans to recognize objects in videos: the global semantic information and the local localization information.
Ranked #14 on
Video Object Detection
on ImageNet VID
FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
Applying artificial intelligence techniques in medical imaging is one of the most promising areas in medicine.
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories
We address the problem of discovering 3D parts for objects in unseen categories.
On Layer Normalization in the Transformer Architecture
This motivates us to remove the warm-up stage for the training of Pre-LN Transformers.
Combinatorial Semi-Bandit in the Non-Stationary Environment
In a special case where the reward function is linear and we have an exact oracle, we design a parameter-free algorithm that achieves nearly optimal regret both in the switching case and in the dynamic case without knowing the parameters in advance.
MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius
Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly.
Dense RepPoints: Representing Visual Objects with Dense Point Sets
We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level.
Defective Convolutional Networks
Robustness of convolutional neural networks (CNNs) has gained in importance on account of adversarial examples, i. e., inputs added as well-designed perturbations that are imperceptible to humans but can cause the model to predict incorrectly.
Clinical Concept Extraction: a Methodology Review
Background Concept extraction, a subdomain of natural language processing (NLP) with a focus on extracting concepts of interest, has been adopted to computationally extract clinical information from text for a wide range of applications ranging from clinical decision support to care quality improvement.
On the Anomalous Generalization of GANs
Motivated by this observation, we discover two specific problems of GANs leading to anomalous generalization behaviour, which we refer to as the sample insufficiency and the pixel-wise combination.
Robust Local Features for Improving the Generalization of Adversarial Training
We continue to propose a new approach called Robust Local Features for Adversarial Training (RLFAT), which first learns the robust local features by adversarial training on the RBS-transformed adversarial examples, and then transfers the robust local features into the training of normal adversarial examples.
Hint-Based Training for Non-Autoregressive Machine Translation
Due to the unparallelizable nature of the autoregressive factorization, AutoRegressive Translation (ART) models have to generate tokens sequentially during decoding and thus suffer from high inference latency.
McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds
We demonstrate that for many types of dependent data, the forest complexity is small and thus implies good concentration.
A Fast and Accurate One-Stage Approach to Visual Grounding
We propose a simple, fast, and accurate one-stage approach to visual grounding, inspired by the following insight.
Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks
While SIM is based on our discovery on the scale-invariant property of deep learning models, for which we leverage to optimize the adversarial perturbations over the scale copies of the input images so as to avoid "overfitting" on the white-box model being attacked and generate more transferable adversarial examples.
Few-Shot Learning with Global Class Representations
In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples.
Representation Degeneration Problem in Training Natural Language Generation Models
We study an interesting problem in training neural network-based models for natural language generation tasks, which we call the \emph{representation degeneration problem}.
Cross-lingual Data Transformation and Combination for Text Classification
In order to train a generalizable model, a large volume of text must be collected.
Convergence of Adversarial Training in Overparametrized Neural Networks
Neural networks are vulnerable to adversarial examples, i. e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network.
Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
In this paper, we provide a novel perspective towards understanding the architecture: we show that the Transformer can be mathematically interpreted as a numerical Ordinary Differential Equation (ODE) solver for a convection-diffusion equation in a multi-particle dynamic system.
Adversarially Robust Generalization Just Requires More Unlabeled Data
Neural network robustness has recently been highlighted by the existence of adversarial examples.
Equipping Experts/Bandits with Long-term Memory
We propose the first reduction-based approach to obtaining long-term memory guarantees for online learning in the sense of Bousquet and Warmuth, 2002, by reducing the problem to achieving typical switching regret.
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems
First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks.
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs.
Hint-based Training for Non-Autoregressive Translation
To improve the accuracy of NART models, in this paper, we propose to leverage the hints from a well-trained ART model to train the NART model.
RepPoints: Point Set Representation for Object Detection
They furthermore do not require the use of anchors to sample a space of bounding boxes.
Ranked #100 on
Object Detection
on COCO minival
AT-GAN: An Adversarial Generator Model for Non-constrained Adversarial Examples
In this way, AT-GAN can learn the distribution of adversarial examples that is very close to the distribution of real data.
Distributed Bandit Learning: Near-Optimal Regret with Efficient Communication
We study the problem of regret minimization for distributed bandits learning, in which $M$ agents work collaboratively to minimize their total regret under the coordination of a central server.
Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing
We present a method for compositing virtual objects into a photograph such that the object colors appear to have been processed by the photo's camera imaging pipeline.
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP
A fundamental question in reinforcement learning is whether model-free algorithms are sample efficient.
Gradient Descent Finds Global Minima of Deep Neural Networks
Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex.
Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning
Inspired by the fact that an unseen class is not exactly `unseen' if it belongs to the same superclass as a seen class, we propose a novel inductive ZSL model that leverages superclasses as the bridge between seen and unseen classes to narrow the domain gap.
Improving the Generalization of Adversarial Training with Domain Adaptation
Our intuition is to regard the adversarial training on FGSM adversary as a domain adaption task with limited number of target domain samples.
FRAGE: Frequency-Agnostic Word Representation
Continuous word representation (aka word embedding) is a basic building block in many neural network-based models used in natural language processing tasks.
Ranked #3 on
Machine Translation
on IWSLT2015 German-English
Learning to Navigate for Fine-grained Classification
In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher.
Ranked #45 on
Fine-Grained Image Classification
on FGVC Aircraft
MedSTS: A Resource for Clinical Semantic Textual Similarity
A subset of MedSTS (MedSTS_ann) containing 1, 068 sentence pairs was annotated by two medical experts with semantic similarity scores of 0-5 (low to high similarity).
Dropout Training, Data-dependent Regularization, and Generalization Bounds
We study the problem of generalization guarantees for dropout training.
Towards Binary-Valued Gates for Robust LSTM Training
Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling.
Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech
We achieve the trifecta: (1) High accuracy for the diverse captions as evaluated by standard captioning metrics and user studies; (2) Faster computation of diverse captions compared to beam search and diverse beam search; and (3) High diversity as evaluated by counting novel sentences, distinct n-grams and mutual overlap (i. e., mBleu-4) scores.
Learning Region Features for Object Detection
While most steps in the modern object detection methods are learnable, the region feature extraction step remains largely hand-crafted, featured by RoI pooling methods.
A Comparison of Word Embeddings for the Biomedical Natural Language Processing
First, the word embeddings trained on clinical notes and biomedical publications can capture the semantics of medical terms better, and find more relevant similar medical terms, and are closer to human experts' judgments, compared to these trained on Wikipedia and news.
Information Retrieval
Decoding with Value Networks for Neural Machine Translation
Inspired by the success and methodology of AlphaGo, in this paper we propose using a prediction network to improve beam search, which takes the source sentence $x$, the currently available decoding output $y_1,\cdots, y_{t-1}$ and a candidate word $w$ at step $t$ as inputs and predicts the long-term value (e. g., BLEU score) of the partial target sentence if it is completed by the NMT model.
The Expressive Power of Neural Networks: A View from the Width
That is, there are classes of deep networks which cannot be realized by any shallow network whose size is no more than an exponential bound.
Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints
This is the first algorithm-dependent result with reasonable dependence on aggregated step sizes for non-convex learning, and has important implications to statistical learning aspects of stochastic gradient methods in complicated models such as deep learning.
Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics
In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i. e. zero-shot fine-grained classification.
Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks
Early detection of pulmonary cancer is the most promising way to enhance a patient's chance for survival.
Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible
For learning with smooth generalized linear losses, we propose an approximate stochastic gradient oracle estimated from non-interactive LDP channel, using Chebyshev expansion.
Randomness in Deconvolutional Networks for Visual Representation
Toward a deeper understanding on the inner work of deep neural networks, we investigate CNN (convolutional neural network) using DCN (deconvolutional network) and randomization technique, and gain new insights for the intrinsic property of this network architecture.
Efficient Private ERM for Smooth Objectives
For strongly convex and smooth objectives, we prove that gradient descent with output perturbation not only achieves nearly optimal utility, but also significantly improves the running time of previous state-of-the-art private optimization algorithms, for both $\epsilon$-DP and $(\epsilon, \delta)$-DP.
Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes
The RTD of a concept class $\mathcal C \subseteq \{0, 1\}^n$, introduced by Zilles et al. (2011), is a combinatorial complexity measure characterized by the worst-case number of examples necessary to identify a concept in $\mathcal C$ according to the recursive teaching model.
Stable Memory Allocation in the Hippocampus: Fundamental Limits and Neural Realization
In Valiant's neuroidal model, the hippocampus was described as a randomly connected graph, the computation on which maps input to a set of activated neuroids with stable size.
Dual Learning for Machine Translation
Based on the feedback signals generated during this process (e. g., the language-model likelihood of the output of a model, and the reconstruction error of the original sentence after the primal and dual translations), we can iteratively update the two models until convergence (e. g., using the policy gradient methods).
On the Depth of Deep Neural Networks: A Theoretical View
First, we derive an upper bound for RA of DNN, and show that it increases with increasing depth.
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models
The Flickr30k dataset has become a standard benchmark for sentence-based image description.
Ranked #15 on
Phrase Grounding
on Flickr30k Entities Test
Image classification by visual bag-of-words refinement and reduction
This paper presents a new framework for visual bag-of-words (BOW) refinement and reduction to overcome the drawbacks associated with the visual BOW model which has been widely used for image classification.
Pairwise Constraint Propagation on Multi-View Data
This paper presents a graph-based learning approach to pairwise constraint propagation on multi-view data.
A Game-theoretic Machine Learning Approach for Revenue Maximization in Sponsored Search
Sponsored search is an important monetization channel for search engines, in which an auction mechanism is used to select the ads shown to users and determine the prices charged from advertisers.
Can Image-Level Labels Replace Pixel-Level Labels for Image Parsing
By oversegmenting all the images into regions, we formulate noisily tagged image parsing as a weakly supervised sparse learning problem over all the regions, where the initial labels of each region are inferred from image-level labels.
Multi-scale Orderless Pooling of Deep Convolutional Activation Features
Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition.
Differentially Private Data Releasing for Smooth Queries with Synthetic Database Output
We develop an $\epsilon$-differentially private mechanism for the class of $K$-smooth queries.
Efficient Algorithm for Privately Releasing Smooth Queries
Outputting the summary runs in time $O(n^{1+\frac{d}{2d+K}})$, and the evaluation algorithm for answering a query runs in time $\tilde O (n^{\frac{d+2+\frac{2d}{K}}{2d+K}} )$.
A Theoretical Analysis of NDCG Type Ranking Measures
We show that NDCG with logarithmic discount has consistent distinguishability although it converges to the same limit for all ranking functions.
Dimensionality Dependent PAC-Bayes Margin Bound
We show that our bound is strictly sharper than a previously well-known PAC-Bayes margin bound if the feature space is of finite dimension; and the two bounds tend to be equivalent as the dimension goes to infinity.
