Search Results for author:
Found 43 papers, 20 papers with code
DSOD: Learning Deeply Supervised Object Detectors from Scratch
State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets like ImageNet, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks.
Object Detection from Scratch with Deep Supervision
Thus, a better solution to handle these critical problems is to train object detectors from scratch, which motivates our proposed method.
RON: Reverse Connection with Objectness Prior Networks for Object Detection
To address (a), we design the reverse connection, which enables the network to detect objects on multi-levels of CNNs.
Learning Two-View Correspondences and Geometry Using Order-Aware Network
First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix.
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
The weights in the other group are responsible to compensate for the accuracy loss from the quantization, thus they are the ones to be re-trained.
Dynamic Network Surgery for Efficient DNNs
In this paper, we propose a novel network compression method called dynamic network surgery, which can remarkably reduce the network complexity by making on-the-fly connection pruning.
From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds
But adapting this scheme to the state-of-the-art (SOTA) solution for PC-based layout estimation is not straightforward.
Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
Internet video delivery has undergone a tremendous explosion of growth over the past few years.
Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization
This procedure can greatly compensate the quantization error and thus yield better accuracy for low-bit DNNs.
Efficient Semantic Scene Completion Network with Spatial Group Convolution
We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks.
Ranked #9 on
3D Semantic Scene Completion
on SemanticKITTI
A Closed-form Solution to Universal Style Transfer
Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing.
Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
This paper presents Ske2Grid, a new representation learning framework for improved skeleton-based action recognition.
ECT: Fine-grained Edge Detection with Learned Cause Tokens
To address these three issues, we propose a two-stage transformer-based network sequentially predicting generic edges and fine-grained edges, which has a global receptive field thanks to the attention mechanism.
Towards to Robust and Generalized Medical Image Segmentation Framework
In this paper, we address the challenge from the transfer learning point of view.
P-WAE: Generalized Patch-Wasserstein Autoencoder for Anomaly Screening
Anomaly detection plays a pivotal role in numerous real-world scenarios, such as industrial automation and manufacturing intelligence.
Network Decoupling: From Regular to Depthwise Separable Convolutions
Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available.
Efficient Meta-Tuning for Content-aware Neural Video Delivery
Our method significantly reduces the computational cost and achieves even better performance, paving the way for applying neural video delivery techniques to practical applications.
Dynamic Normalization and Relay for Video Action Recognition
In this paper, we present Dynamic Normalization and Relay (DNR), an improved normalization design, to augment the spatial-temporal representation learning of any deep action recognition model, adapting to small batch size training settings.
A Scalable Neural Network for DSIC Affine Maximizer Auction Design
AMenuNet is always DSIC and individually rational (IR) due to the properties of AMAs, and it enhances scalability by generating candidate allocations through a neural network.
Learning Visual Knowledge Memory Networks for Visual Question Answering
Second is the mechanism for handling multiple knowledge facts expanding from question and answer pairs.
Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation
In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes.
Network Sketching: Exploiting Binary Structure in Deep CNNs
Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks.
Weakly Supervised Dense Video Captioning
This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences.
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances.
Deep Attributes from Context-Aware Regional Neural Codes
Results show that deep attribute approaches achieve state-of-the-art results, and outperforms existing peer methods with a significant margin, even though some benchmarks have little overlap of concepts with the pre-trained CNN models.
Large-scale Supervised Hierarchical Feature Learning for Face Recognition
Second, the face image is further represented by patches of picked channels, and we search from the over-complete patch pool to activate only those most discriminant patches.
Sparse DNNs with Improved Adversarial Robustness
Deep neural networks (DNNs) are computationally/memory-intensive and vulnerable to adversarial attacks, making them prohibitive in some real-world applications.
Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks
Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective.
Decoder Network Over Lightweight Reconstructed Feature for Fast Semantic Style Transfer
Our method decomposes the semantic style transfer problem into feature reconstruction part and feature decoder part.
Deep Likelihood Network for Image Restoration with Multiple Degradation Levels
Convolutional neural networks have been proven effective in a variety of image restoration tasks.
Adversarial Attack on Hierarchical Graph Pooling Neural Networks
However, most of the existing work in this area focus on the GNNs for node-level tasks, while little work has been done to study the robustness of the GNNs for the graph classification task.
On Connections between Regularizations for Improving DNN Robustness
This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view.
CASNet: Common Attribute Support Network for image instance and panoptic segmentation
Given the insight that pixels belonging to one instance have one or more common attributes of current instance, we bring up an one-stage instance segmentation network named Common Attribute Support Network (CASNet), which realizes instance segmentation by predicting and clustering common attributes.
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
SnapQuant: A Probabilistic and Nested Parameterization for Binary Networks
During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.
Transferable End-to-end Room Layout Estimation via Implicit Encoding
Here we propose an end-to-end method that directly predicts parametric layouts from an input panorama image.
Projected Sliced Wasserstein Autoencoder-based Hyperspectral Images Anomaly Detection
In this case, the Wasserstein distance can be calculated with the closed-form, even the prior distribution is not Gaussian.
On the Convergence of Fictitious Play: A Decomposition Approach
Fictitious play (FP) is one of the most fundamental game-theoretical learning frameworks for computing Nash equilibrium in $n$-player games, which builds the foundation for modern multi-agent learning algorithms.
Optimal Private Payoff Manipulation against Commitment in Extensive-form Games
For all the settings considered in this paper, we characterize all the possible game outcomes that can be induced successfully.
Learning to Manipulate a Commitment Optimizer
We consider the scenario where the follower is not given any information about the leader's payoffs to begin with but has to learn to manipulate by interacting with the leader.
Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets
To the best of our knowledge, we are the first to consider bidder coordination in online repeated auctions with constraints.
Are Bounded Contracts Learnable and Approximately Optimal?
This paper considers the hidden-action model of the principal-agent problem, in which a principal incentivizes an agent to work on a project using a contract.
