Search Results for author:
Found 87 papers, 20 papers with code
Boosting Deep Neural Network Efficiency with Dual-Module Inference
Using Deep Neural Networks (DNNs) in machine learning tasks is promising in delivering high-quality results but challenging to meet stringent latency requirements and energy constraints because of the memory-bound and the compute-bound execution pattern of DNNs.
Deep Streaming Label Learning
In order to fill in these research gaps, we propose a novel deep neural network (DNN) based framework, Deep Streaming Label Learning (DSLL), to classify instances with newly emerged labels effectively.
One-shot neural band selection for spectral recovery
To solve this ill-posed inverse problem, most band selection methods adopt hand-crafted priors or exploit clustering or sparse regularization constraints to find most prominent bands.
Reweighted Mixup for Subpopulation Shift
Subpopulation shift exists widely in many real-world applications, which refers to the training and test distributions that contain the same subpopulation groups but with different subpopulation proportions.
Deploying Offline Reinforcement Learning with Human Feedback
To address this issue, we propose an alternative framework that involves a human supervising the RL models and providing additional feedback in the online deployment phase.
CyberLoc: Towards Accurate Long-term Visual Localization
Second, a single-image-based localization pipeline (retrieval--matching--PnP) is performed to estimate 6-DoF camera poses for each query image, one for each 3D map.
Event Camera Data Pre-training
Our model is a self-supervised learning framework, and uses paired event camera data and natural RGB images for training.
K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring
It estimates a disparity feature map, which is used to query a trainable kernel set to estimate a blur kernel that best describes the spatially-varying blur.
ISG: I can See Your Gene Expression
Instead, we present ISG framework that harnesses interactions among discriminative features from texture-abundant regions by three new modules: 1) a Shannon Selection module, based on the Shannon information content and Solomonoff's theory, to filter out textureless image regions; 2) a Feature Extraction network to extract expressive low-dimensional feature representations for efficient region interactions among a high-resolution image; 3) a Dual Attention network attends to regions with desired gene expression features and aggregates them for the prediction task.
Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation
A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL.
UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup
Importance reweighting is a normal way to handle the subpopulation shift issue by imposing constant or adaptive sampling weights on each sample in the training dataset.
Balancing Stability and Plasticity through Advanced Null Space in Continual Learning
Continual learning is a learning paradigm that learns tasks sequentially with resources constraints, in which the key challenge is stability-plasticity dilemma, i. e., it is uneasy to simultaneously have the stability to prevent catastrophic forgetting of old tasks and the plasticity to learn new tasks well.
Online Continual Learning with Contrastive Vision Transformer
Based on the learnable focuses, we design a focal contrastive loss to rebalance contrastive learning between new and past classes and consolidate previously learned representations.
Learning Object Placement via Dual-path Graph Completion
Object placement aims to place a foreground object over a background image with a suitable location and size.
OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction
We start to collect 1, 800 common household objects and annotate their affordances to construct the first knowledge base: Oak.
Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
We address the problem of ground-to-satellite image geo-localization, that is, estimating the camera latitude, longitude and orientation (azimuth angle) by matching a query image captured at the ground level against a large-scale database with geotagged satellite images.
Exploring High-Order Structure for Robust Graph Structure Learning
In this paper, we analyze the adversarial attack on graphs from the perspective of feature smoothness which further contributes to an efficient new adversarial defensive algorithm for GNNs.
Escaping from the Barren Plateau via Gaussian Initializations in Deep Variational Quantum Circuits
Experimental results verify our theoretical findings in the quantum simulation and quantum chemistry.
Dynamic N:M Fine-grained Structured Sparse Attention Mechanism
We evaluate the 1:2 and 2:4 sparsity under different configurations and achieve 1. 27~ 1. 89x speedups over the full-attention mechanism.
AKB-48: A Real-World Articulated Object Knowledge Base
To bridge the gap, we present AKB-48: a large-scale Articulated object Knowledge Base which consists of 2, 037 real-world 3D articulated object models of 48 categories.
Robust Imitation Learning from Corrupted Demonstrations
We consider offline Imitation Learning from corrupted demonstrations where a constant fraction of data can be noise or even arbitrary outliers.
Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation
To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation.
Continual Learning With Lifelong Vision Transformer
Continual learning methods aim at training a neural network from sequential data with streaming labels, relieving catastrophic forgetting.
Text-to-Image Synthesis Based on Object-Guided Joint-Decoding Transformer
Object-guided text-to-image synthesis aims to generate images from natural language descriptions built by two-step frameworks, i. e., the model generates the layout and then synthesizes images from the layout and captions.
iSeg3D: An Interactive 3D Shape Segmentation Tool
It can obtain a satisfied segmentation result with minimal human clicks (< 10).
SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks
In this paper, we conduct theoretical and experimental analysis to explore the fundamental causes of performance degradation in deep GCNs: over-smoothing and gradient vanishing have a mutually reinforcing effect that causes the performance to deteriorate more quickly in deep GCNs.
Transcribing Natural Languages for The Deaf via Neural Editing Programs
This work studies the task of glossification, of which the aim is to em transcribe natural spoken language sentences for the Deaf (hard-of-hearing) community to ordered sign language glosses.
OMAD: Object Model with Articulated Deformations for Pose Estimation and Retrieval
With the full representation of the object shape and joint states, we can address several tasks including category-level object pose estimation and the articulated object retrieval.
Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels
Essentially, our CGPN can enhance the learning performance of GNNs under extremely limited labels by contrastively propagating the limited labels to the entire graph.
Transformer Acceleration with Dynamic Sparse Attention
We demonstrate that the sparse patterns are dynamic, depending on input sequences.
DFSSATTEN: Dynamic Fine-grained Structured Sparse Attention Mechanism
Transformers are becoming mainstream solutions for various tasks like NLP and Computer vision.
On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
Graph pooling is essential in learning effective graph-level representations.
Lagrangian Generative Adversarial Imitation Learning with Safety
Imitation Learning (IL) merely concentrates on reproducing expert behaviors and could take dangerous actions, which is unbearable in safety-critical scenarios.
Multi-modal Affect Analysis using standardized data within subjects in the Wild
Therefore, after learning the common features for each frame, we constructed a facial expression estimation model and valence-arousal model using time-series data after combining the common features and the standardized features for each video.
OPA: Object Placement Assessment Dataset
Image composition aims to generate realistic composite image by inserting an object from one image into another background image, where the placement (e. g., location, size, occlusion) of inserted object may be unreasonable, which would significantly degrade the quality of the composite image.
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
We also point out the limitations of existing methods in each sub-task and the problem of the whole image composition task.
PluckerNet: Learn To Register 3D Line Reconstructions
Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve line correspondences and relative pose between reconstructions.
Towards Real-World Category-level Articulation Pose Estimation
This setting allows varied kinematic structures within a semantic category, and multiple instances to co-exist in an observation of real world.
A deep neural network approach on solving the linear transport model under diffusive scaling
In our framework, the solution is approximated by a neural network that satisfies both the governing equation and other constraints.
Numerical Analysis Numerical Analysis
Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation
Spatial and channel attentions, modelling the semantic interdependencies in spatial and channel dimensions respectively, have recently been widely used for semantic segmentation.
Ranked #9 on
Semantic Segmentation
on COCO-Stuff test
Semantic Inference Network for Few-shot Streaming Label Learning
In this work, we formulate and study few-shot streaming label learning (FSLL), which models emerging new labels with only a few annotated examples by utilizing the knowledge learned from past labels.
Adaptive Curriculum Learning
Therefore, in contrast to recent works using a fixed curriculum, we devise a new curriculum learning method, Adaptive Curriculum Learning (Adaptive CL), adapting the difficulty of examples to the current state of the model.
PlueckerNet: Learn to Register 3D Line Reconstructions
Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve correspondences and relative pose between line reconstructions.
On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration
By contrast, this paper proves that LfO is almost equivalent to LfD in the deterministic robot environment, and more generally even in the robot environment with bounded randomness.
HiCOMEX: Facial Action Unit Recognition Based on Hierarchy Intensity Distribution and COMEX Relation Learning
The features are input to a bidirectional long short-term memory (BiLSTM) layer for learning the intensity distribution.
Weak-shot Fine-grained Classification via Similarity Transfer
In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories.
Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization
We instead propose the first fully end-to-end trainable network for solving the blind PnP problem efficiently and globally, that is, without the need for pose priors.
Robust Structured Statistical Estimation via Conditional Gradient Type Methods
However, the existing CG type methods are not robust to data corruption.
Robust Compressed Sensing using Generative Models
In analogy to classical compressed sensing, here we assume a generative model as a prior, that is, we assume the vector is represented by a deep generative model $G: \mathbb{R}^k \rightarrow \mathbb{R}^n$.
Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution
Second, we propose a new framework for real-world DSR, which consists of four modules : 1) An iterative residual learning module with deep supervision to learn effective high-frequency components of depth maps in a coarse-to-fine manner; 2) A channel attention strategy to enhance channels with abundant high-frequency components; 3) A multi-stage fusion module to effectively re-exploit the results in the coarse-to-fine process; and 4) A depth refinement module to improve the depth map by TGV regularization and input loss.
Computation on Sparse Neural Networks: an Inspiration for Future Hardware
We show that for practically complicated problems, it is more beneficial to search large and sparse models in the weight dominated region.
Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem
Conventional absolute camera pose via a Perspective-n-Point (PnP) solver often assumes that the correspondences between 2D image pixels and 3D points are given.
Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization
The first step is to apply a regular polar transform to warp an aerial image such that its domain is closer to that of a ground-view panorama.
DoveNet: Deep Image Harmonization via Domain Verification
Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image.
Ranked #5 on
Image Harmonization
on HAdobe5k(1024$\times$1024)
Stochastically Controlled Compositional Gradient for the Composition problem
The strategy is also accompanied by a mini-batch version of the proposed method that improves query complexity with respect to the size of the mini-batch.
Quantum algorithm for finding the negative curvature direction
Moreover, we propose an efficient algorithm to achieve the classical read-out of the target state.
Dual-module Inference for Efficient Recurrent Neural Networks
Using Recurrent Neural Networks (RNNs) in sequence modeling tasks is promising in delivering high-quality results but challenging to meet stringent latency requirements because of the memory-bound execution pattern of RNNs.
Encoding Selection for Solving Hamiltonian Cycle Problems with ASP
It is common for search and optimization problems to have alternative equivalent encodings in ASP.
Quantum algorithm for finding the negative curvature direction in non-convex optimization
Moreover, we propose an efficient quantum algorithm to achieve the classical read-out of the target state.
NODE: Extreme Low Light Raw Image Denoising using a Noise Decomposition Network
In this paper, we propose a multi-task deep neural network called Noise Decomposition (NODE) that explicitly and separately estimates defective pixel noise, in conjunction with Gaussian and Poisson noise, to denoise an extreme low light image.
Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night
Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image.
Optimal Feature Transport for Cross-View Image Geo-Localization
This paper proposes a novel Cross-View Feature Transport (CVFT) technique to explicitly establish cross-view domain transfer that facilitates feature alignment between ground and aerial images.
Lending Orientation to Neural Networks for Cross-view Geo-localization
The goal is to predict the spatial location of a ground-level query image by matching it to a large geotagged aerial image database (e. g., satellite imagery).
FurcaNeXt: End-to-end monaural speech separation with dynamic gated dilated temporal convolutional networks
Deep dilated temporal convolutional networks (TCN) have been proved to be very effective in sequence modeling.
Sound Audio and Speech Processing
High Dimensional Robust $M$-Estimation: Arbitrary Corruption and Heavy Tails
We define a natural condition we call the Robust Descent Condition (RDC), and show that if a gradient estimator satisfies the RDC, then Robust Hard Thresholding (IHT using this gradient estimator), is guaranteed to obtain good statistical rates.
Dynamic Sparse Graph for Efficient Deep Learning
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference.
Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient
Trust region and cubic regularization methods have demonstrated good performance in small scale non-convex optimization, showing the ability to escape from saddle points.
Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem
In this paper, we consider the convex and non-convex composition problem with the structure $\frac{1}{n}\sum\nolimits_{i = 1}^n {{F_i}( {G( x )} )}$, where $G( x )=\frac{1}{n}\sum\nolimits_{j = 1}^n {{G_j}( x )} $ is the inner function, and $F_i(\cdot)$ is the outer function.
Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization
This paper tackles the problem of large-scale image-based localization (IBL) where the spatial location of a query image is determined by finding out the most similar reference images in a large database.
Stochastic Zeroth-order Optimization via Variance Reduction method
However, due to the variance in the search direction, the convergence rates and query complexities of existing methods suffer from a factor of $d$, where $d$ is the problem dimension.
High Dimensional Robust Sparse Regression
Our algorithm recovers the true sparse parameters with sub-linear sample complexity, in the presence of a constant fraction of arbitrary corruptions.
Approximate Newton-based statistical inference using only stochastic gradients
We present a novel statistical inference framework for convex empirical risk minimization, using approximate stochastic Newton steps.
Discriminative Cross-View Binary Representation Learning
Learning compact representation is vital and challenging for large scale multimedia data.
L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
Batch Normalization (BN) has been proven to be quite effective at accelerating and improving the training of deep neural networks (DNNs).
Variance Reduced methods for Non-convex Composition Optimization
In this paper, we apply the variance-reduced technique to derive two variance reduced algorithms that significantly improve the query complexity if the number of inner component functions is large.
Duality-free Methods for Stochastic Composition Optimization
We consider the composition optimization with two expected-value functions in the form of $\frac{1}{n}\sum\nolimits_{i = 1}^n F_i(\frac{1}{m}\sum\nolimits_{j = 1}^m G_j(x))+R(x)$, { which formulates many important problems in statistical learning and machine learning such as solving Bellman equations in reinforcement learning and nonlinear embedding}.
Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map
In this paper, we introduce a global method which harnesses global contextual information exhibited both within the query image and among all the 3D points in the map.
Person Re-identification Using Visual Attention
Despite recent attempts for solving the person re-identification problem, it remains a challenging task since a person's appearance can vary significantly when large variations in view angle, human pose, and illumination are involved.
Multi-View Task-Driven Recognition in Visual Sensor Networks
Nowadays, distributed smart cameras are deployed for a wide set of tasks in several application scenarios, ranging from object recognition, image retrieval, and forensic applications.
Addressing Ambiguity in Multi-target Tracking by Hierarchical Strategy
We use a network flow approach to link detections in low-level and tracklets in high-level.
Statistical inference using SGD
We present a novel method for frequentist statistical inference in $M$-estimation problems, based on stochastic gradient descent (SGD) with a fixed step size: we demonstrate that the average of such SGD sequences can be used for statistical inference, after proper scaling.
Multi-view (Joint) Probability Linear Discrimination Analysis for Multi-view Feature Verification
However, in practical use, when using multi-task learned network as feature extractor, the extracted feature are always attached to several labels.
End-to-end Binary Representation Learning via Direct Binary Embedding
Furthermore, in the effort of handling multilabel images, we design a joint cross entropy loss that includes both softmax cross entropy and weighted binary cross entropy in consideration of the correlation and independence of labels, respectively.
CNNLab: a Novel Parallel Framework for Neural Networks using GPU and FPGA-a Practical Study with Trade-off Analysis
To improve the performance and maintain the scalability, we present CNNLab, a novel deep learning framework using GPU and FPGA-based accelerators.
Robust and Efficient Relative Pose with a Multi-camera System for Autonomous Vehicle in Highly Dynamic Environments
When the solver is used in combination with RANSAC, we are able to quickly prune unpromising hypotheses, significantly improve the chance of finding inliers.
Compressing Deep Convolutional Networks using Vector Quantization
In this paper, we tackle this model storage issue by investigating information theoretical vector quantization methods for compressing the parameters of CNNs.
Efficient Relational Learning with Hidden Variable Detection
Markov networks (MNs) can incorporate arbitrarily complex features in modeling relational data.
