Search Results for author:
Found 43 papers, 12 papers with code
LiftPool: Lifting-based Graph Pooling for Hierarchical Graph Representation Learning
Subsequently, this local information is aligned and propagated to the preserved nodes to alleviate information loss in graph coarsening.
Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks
This framework is general to endow arbitrary DNNs for solving linear inverse problems with convergence guarantees.
All-optical graph representation learning using integrated diffractive photonic computing units
Photonic neural networks perform brain-inspired computations using photons instead of electrons that can achieve substantially improved computing performance.
Hierarchical Graph Networks for 3D Human Pose Estimation
Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton.
Motion-aware Contrastive Video Representation Learning via Foreground-background Merging
To alleviate such bias, we propose \textbf{F}oreground-b\textbf{a}ckground \textbf{Me}rging (FAME) to deliberately compose the moving foreground region of the selected video onto the static background of others.
Graph Convolutional Networks via Adaptive Filter Banks
Graph convolutional networks have been a powerful tool in representation learning of networked data.
Variance Reduced Domain Randomization for Policy Gradient
In this paper, we theoretically derive a bias-free and state/environment-dependent optimal baseline for DR, and analytically show its ability to achieve further variance reduction over the standard constant and state-dependent baselines for DR. We further propose a variance reduced domain randomization (VRDR) approach for policy gradient methods, to strike a tradeoff between the variance reduction and computational complexity in practice.
Understanding Self-supervised Learning via Information Bottleneck Principle
To address this issue, we introduce the information bottleneck principle and propose the Self-supervised Variational Information Bottleneck (SVIB) learning framework.
Graph Neural Networks With Lifting-based Adaptive Graph Wavelets
To ensure that the learned graph representations are invariant to node permutations, a layer is employed at the input of the networks to reorder the nodes according to their local topology information.
Bag of Instances Aggregation Boosts Self-supervised Distillation
Here bag of instances indicates a set of similar samples constructed by the teacher and are grouped within a bag, and the goal of distillation is to aggregate compact representations over the student with respect to instances in a bag.
Message Passing in Graph Convolution Networks via Adaptive Filter Banks
Furthermore, each filter in the spectral domain corresponds to a message passing scheme, and diverse schemes are implemented via the filter bank.
Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets regardless of their taxonomy labels, and followed by fine-tuning the pretrained model over specific dataset as usual.
Light Field Reconstruction via Attention-Guided Deep Fusion of Hybrid Lenses
Besides, to promote the effectiveness of our method trained with simulated hybrid data on real hybrid data captured by a hybrid LF imaging system, we carefully design the network architecture and the training strategy.
Monotonic Robust Policy Optimization with Model Discrepancy
To mitigate the model discrepancy between training and target (testing) environments, domain randomization (DR) can generate plenty of environments with a sufficient diversity by randomly sampling environment parameters in simulator.
Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization
Existing differentiable neural architecture search approaches simply assume the architectural distribution on each edge is independent of each other, which conflicts with the intrinsic properties of architecture.
VEM-GCN: Topology Optimization with Variational EM for Graph Convolutional Networks
In the variational E-step, graph topology is optimized by approximating the posterior probability distribution of the latent adjacency matrix with a neural network learned from node embeddings.
PAC-Bayesian Randomized Value Function with Informative Prior
To address this, in this paper, we propose a Bayesian linear regression with informative prior (IP-BLR) operator to leverage the data-dependent prior in the learning process of randomized value function, which can leverage the statistics of training results from previous iterations.
NCGNN: Node-level Capsule Graph Neural Network
However, most existing works naively sum or average all the neighboring features to update node representations, which suffers from the following limitations: (1) lack of interpretability to identify crucial node features for GNN's prediction; (2) over-smoothing issue where repeated averaging aggregates excessive noise, making features of nodes in different classes over-mixed and thus indistinguishable.
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning
In this paper, we propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to \textbf{Cross-samples and Multi-level} representation, and models the invariance to semantically similar images in a hierarchical way.
Ranked #37 on
Self-Supervised Image Classification
on ImageNet
Batch Normalization with Enhanced Linear Transformation
Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions.
Center-wise Local Image Mixture For Contrastive Representation Learning
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples.
MimicNorm: Weight Mean and Last BN Layer Mimic the Dynamic of Batch Normalization
We leverage the neural tangent kernel (NTK) theory to prove that our weight mean operation whitens activations and transits network into the chaotic regime like BN layer, and consequently, leads to an enhanced convergence.
K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
In this paper, we propose the $K$-Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances.
Distilling Object Detectors with Task Adaptive Regularization
Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization.
Graph Pooling with Node Proximity for Hierarchical Representation Learning
In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology.
Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
We demonstrate that the proposed method is able to boost the performance of existing pose estimation pipelines on our HiEve dataset.
TRP: Trained Rank Pruning for Efficient Deep Neural Networks
The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss, thus eliminating the fine-tuning process after low rank decomposition.
Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
In this paper, we propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples.
Ranked #11 on
Fine-Grained Image Classification
on CUB-200-2011
Latency-Aware Differentiable Neural Architecture Search
However, these methods suffer the difficulty in optimizing network, so that the searched network is often unfriendly to hardware.
Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
In this paper, we propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) that leverages dynamical directed spatial dependencies and long-range temporal dependencies to improve the accuracy of long-term traffic forecasting.
FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
To this end, we present a novel regularization mechanism by learning the change of feature representations induced by a distribution of transformations without using the labels of data examples.
AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups
For this reason, we should use the geodesic to characterize how an image transform along the manifold of a transformation group, and adopt its length to measure the deviation between transformations.
Trained Rank Pruning for Efficient Deep Neural Networks
To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations.
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal architecture.
Ranked #15 on
Neural Architecture Search
on CIFAR-10
iPool -- Information-based Pooling in Hierarchical Graph Neural Networks
In this paper, we propose a parameter-free pooling operator, called iPool, that permits to retain the most informative features in arbitrary graphs.
Group Re-Identification with Multi-grained Matching and Integration
The task of re-identifying groups of people underdifferent camera views is an important yet less-studied problem. Group re-identification (Re-ID) is a very challenging task sinceit is not only adversely affected by common issues in traditionalsingle object Re-ID problems such as viewpoint and human posevariations, but it also suffers from changes in group layout andgroup membership.
Trained Rank Pruning for Efficient Deep Neural Networks
We propose Trained Rank Pruning (TRP), which iterates low rank approximation and training.
DNQ: Dynamic Network Quantization
Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices.
Zigzag Learning for Weakly Supervised Object Detection
Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds.
Ranked #13 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Deep Neural Network Compression with Single and Multiple Level Quantization
In this paper, we propose two novel network quantization approaches, single-level network quantization (SLQ) for high-bit quantization and multi-level network quantization (MLQ) for extremely low-bit quantization (ternary). We are the first to consider the network quantization from both width and depth level.
Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams.
Ensemble of Part Detectors for Simultaneous Classification and Localization
Part-based representation has been proven to be effective for a variety of visual applications.
Picking Deep Filter Responses for Fine-Grained Image Recognition
Recognizing fine-grained sub-categories such as birds and dogs is extremely challenging due to the highly localized and subtle differences in some specific parts.
