Search Results for author:
Found 90 papers, 19 papers with code
ProgressFace: Scale-Aware Progressive Learning for Face Detection
In this work, we propose a novel scale-aware progressive training mechanism to address large scale variations across faces.
MEMO : Accelerating Transformers with Memoization on Big Memory Systems
However, the transformer is computation-intensive, causing a long inference time.
Transformer in Transformer as Backbone for Deep Reinforcement Learning
Recent methods combine the Transformer with these modules for better performance.
Generation-Augmented Query Expansion For Code Retrieval
Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet.
Towards Reliable Item Sampling for Recommendation Evaluation
Since Rendle and Krichene argued that commonly used sampling-based evaluation metrics are ``inconsistent'' with respect to the global metrics (even in expectation), there have been a few studies on the sampling-based recommender system evaluation.
State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning
The key idea of SA-PP is leveraging discounted stationary state distribution ratios between the learning policy and the offline dataset to modulate the degree of behavior regularization in a state-wise manner, so that pessimism can be implemented in a more appropriate way.
Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning
The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remains challenging.
Model-based Reinforcement Learning
reinforcement-learning
+1
PTDE: Personalized Training with Distillated Execution for Multi-Agent Reinforcement Learning
Centralized Training with Decentralized Execution (CTDE) has been a very popular paradigm for multi-agent reinforcement learning.
Linear Video Transformer with Feature Fixation
Therefore, we propose a feature fixation module to reweight the feature importance of the query and key before computing linear attention.
On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies
Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance.
Multi-Document Scientific Summarization from a Knowledge Graph-Centric View
Multi-Document Scientific Summarization (MDSS) aims to produce coherent and concise summaries for clusters of topic-relevant scientific papers.
Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation
More specifically, we propose a novel Coarse-to-fine Knowledge-enhanced Multi-interest Learning (CKML) framework to learn shared and behavior-specific interests for different behaviors.
Neural Architecture Search on Efficient Transformers and Beyond
To address this issue, we propose a new framework to find optimal architectures for efficient Transformers with the neural architecture search (NAS) technique.
HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection
Sample assignment plays a prominent part in modern object detection approaches.
Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture
To address the problem, an improved augmentation search strategy, named Augmented Density Matching, was proposed by randomly sampling policies from a prior distribution for training.
Pushing the Limit of Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless Systems by Exploiting Global Attention
However, most of existing works on IRS focus on how to compute the phase shift for performance enhancement, and the problem on how to obtain the computed phase shift at the IRS side is generally neglected.
SEREN: Knowing When to Explore and When to Exploit
Efficient reinforcement learning (RL) involves a trade-off between "exploitative" actions that maximise expected reward and "explorative'" ones that sample unvisited states.
Rethinking Reinforcement Learning based Logic Synthesis
Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process.
Dynamic Sparse R-CNN
Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features.
Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification
First, we propose global-local cross-attention (GLCA) to enhance the interactions between global images and local high-response regions, which can help reinforce the spatial-wise discriminative clues for recognition.
Ranked #4 on
Fine-Grained Image Classification
on CUB-200-2011
Fine-Grained Image Classification
Fine-Grained Visual Categorization
Revisiting Communication-Efficient Federated Learning with Balanced Global and Local Updates
local update) and that of aggregations (a. k. a.
Compare learning: bi-attention network for few-shot learning
Learning with few labeled data is a key challenge for visual recognition, as deep neural networks tend to overfit using a few samples only.
LHNN: Lattice Hypergraph Neural Network for VLSI Congestion Prediction
Precise congestion prediction from a placement solution plays a crucial role in circuit placement.
Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework
To break this curse, we propose a unified agent permutation framework that exploits the permutation invariance (PI) and permutation equivariance (PE) inductive biases to reduce the multiagent state space.
Who Should Review Your Proposal? Interdisciplinary Topic Path Detection for Research Proposals
After extracting the semantic and interdisciplinary knowledge, we design a level-wise prediction component to fuse the two types of knowledge representations and detect interdisciplinary topic paths for each proposal.
Representing Videos as Discriminative Sub-graphs for Action Recognition
For each action category, we execute online clustering to decompose the graph into sub-graphs on each scale through learning Gaussian Mixture Layer and select the discriminative sub-graphs as action prototypes for recognition.
Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning
Though other methods (particularly those based on Laplacian Smoothing) have reported better accuracy, a fundamental limitation of all the work is a lack of scalability.
Neuro-Symbolic Hierarchical Rule Induction
We propose an efficient interpretable neuro-symbolic model to solve Inductive Logic Programming (ILP) problems.
A Survey on Interpretable Reinforcement Learning
To that aim, we distinguish interpretability (as a property of a model) and explainability (as a post-hoc operation, with the intervention of a proxy) and discuss them in the context of RL with an emphasis on the former notion.
Adaptive Online Packing-guided Search for POMDPs
A belief is a distribution of states representing state uncertainty.
Learning State Representations via Retracing in Reinforcement Learning
We propose learning via retracing, a novel self-supervised approach for learning the state representation (and the associated dynamics model) for reinforcement learning tasks.
SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition
The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the complex \emph{ObtainDiamond} task with sparse rewards.
Generalizable Cross-Graph Embedding for GNN-based Congestion Prediction
To address this limitation, we propose a framework that can directly learn embeddings for the given netlist to enhance the quality of our node features.
Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless Systems
To this end, it is crucial to adjust the phases of reflecting elements of the IRS, and most of the research works focus on how to optimize/quantize the phase for different optimization objectives.
Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization
In this work, we propose a new algorithm for circuit routing, named Ranking Cost, which innovatively combines search-based methods (i. e., A* algorithm) and learning-based methods (i. e., Evolution Strategies) to form an efficient and trainable router.
Learning Explicit Credit Assignment for Multi-agent Joint Q-learning
In contrast, we formulate an \emph{explicit} credit assignment problem where each agent gives its suggestion about how to weight individual Q-values to explicitly maximize the joint Q-value, besides guaranteeing the Bellman optimality of the joint Q-value.
On the regularization landscape for the linear recommendation models
Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders several standard recommendation benchmarks.
Learning Pseudometric-based Action Representations for Offline Reinforcement Learning
Offline reinforcement learning is a promising approach for practical applications since it does not require interactions with real-world environments.
CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation
Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of the model and thus allowing fast adaptation to a specific task from limited data examples.
Towards Discriminative Representation Learning for Unsupervised Person Re-identification
We observe that these proposed schemes are capable of facilitating the learning of discriminative feature representations.
On Sampling Top-K Recommendation Evaluation
Recently, Rendle has warned that the use of sampling-based top-$k$ metrics might not suffice.
RankDetNet: Delving Into Ranking Constraints for Object Detection
To this end, we comprehensively investigate three types of ranking constraints, i. e., global ranking, class-specific ranking and IoU-guided ranking losses.
InfoBehavior: Self-supervised Representation Learning for Ultra-long Behavior Sequence via Hierarchical Grouping
Typically, the risk can be identified by jointly considering product content (e. g., title and image) and seller behavior.
Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment
In addition, we use a novel agent network named Population Invariant agent with Transformer (PIT) to realize the coordination transfer in more varieties of scenarios.
Towards a Better Understanding of Linear Models for Recommendation
Through the derivation and analysis of the closed-form solutions for two basic regression and matrix factorization approaches, we found these two approaches are indeed inherently related but also diverge in how they "scale-down" the singular values of the original user-item interaction matrix.
Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving
Our goal is to train a unified model for improving the performance in each dataset by leveraging information from all the datasets.
Learning Symbolic Rules for Interpretable Deep Reinforcement Learning
To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL.
Learning State Representations via Temporal Cycle-Consistency Constraint in Model-Based Reinforcement Learning
Representation learning is a popular approach for reinforcement learning (RL) tasks with partially observable Markov decision processes.
On Estimating Recommendation Evaluation Metrics under Sampling
The proposed approaches either are rather uninformative (linking sampling to metric evaluation) or can only work on simple metrics, such as Recall/Precision (Krichene and Rendle 2020; Li et al. 2020).
Excess-noise suppression for a squeezed state propagating through random amplifying media via wave-front shaping
After propagating through a random amplifying medium, a squeezed state commonly shows excess noise above the shot-noise level.
Quantum Physics
Diagnosing a Solar Flaring Core with Bidirectional Quasi-Periodic Fast Propagating Magnetoacoustic Waves
Quasi-periodic fast propagating (QFP) waves are often excited by solar flares, and could be trapped in the coronal structure with low Alfv\'en speed, so they could be used as a diagnosing tool for both the flaring core and magnetic waveguide.
Solar and Stellar Astrophysics
ZeRO-Offload: Democratizing Billion-Scale Model Training
By combining compute and memory efficiency with ease-of-use, ZeRO-Offload democratizes large-scale model training making it accessible to even data scientists with access to just a single GPU.
Interpretable Reinforcement Learning With Neural Symbolic Logic
Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
Robust Multi-Agent Reinforcement Learning Driven by Correlated Equilibrium
Therefore, to achieve robust CMARL, we introduce novel strategies to encourage agents to learn correlated equilibrium while maximally preserving the convenience of the decentralized execution.
Meta-Learning with Implicit Processes
This paper presents a novel implicit process-based meta-learning (IPML) algorithm that, in contrast to existing works, explicitly represents each task as a continuous latent vector and models its probabilistic belief within the highly expressive IP framework.
Approximating Pareto Frontier through Bayesian-optimization-directed Robust Multi-objective Reinforcement Learning
Thirdly, the agent’s learning process is regarded as a black-box, and the comprehensive metric we proposed is computed after each episode of training, then a Bayesian optimization (BO) algorithm is adopted to guide the agent to evolve towards improving the quality of the approximated Pareto frontier.
Ranking Cost: One-Stage Circuit Routing by Directly Optimizing Global Objective Function
In our method, we introduce a new set of variables called cost maps, which can help the A* router to find out proper paths to achieve the global object.
Improving Low-Precision Network Quantization via Bin Regularization
Such bin regularization (BR) mechanism encourages the weight distribution of each quantization bin to be sharp and approximate to a Dirac delta distribution ideally.
Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification
In this letter, we propose a conceptually simple and effective dual-granularity triplet loss for visible-thermal person re-identification (VT-ReID).
Ranked #2 on
Cross-Modal Person Re-Identification
on SYSU-MM01
Towards Better Object Detection in Scale Variation with Adaptive Feature Selection
It is a common practice to exploit pyramidal feature representation to tackle the problem of scale variation in object instances.
HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory
The emergence of heterogeneous memory (HM) brings a solution to significantly increase memory capacity and break the above tradeoff: Using HM, billions of data points can be placed in the main memory on a single machine without using any data compression.
What About Inputing Policy in Value Function: Policy Representation and Policy-extended Value Function Approximator
We study Policy-extended Value Function Approximator (PeVFA) in Reinforcement Learning (RL), which extends conventional value function approximator (VFA) to take as input not only the state (and action) but also an explicit policy representation.
Towards Optimal Filter Pruning with Balanced Performance and Pruning Speed
In this paper, we propose a balanced filter pruning method for both performance and pruning speed.
Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning
How to collect informative trajectories of which the corresponding context reflects the specification of tasks?
What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator
The value function lies in the heart of Reinforcement Learning (RL), which defines the long-term evaluation of a policy in a given state.
Transfer among Agents: An Efficient Multiagent Transfer Learning Framework
In many cases, each agent's experience is inconsistent with each other which causes the option-value estimation to oscillate and to become inaccurate.
Smart-PGSim: Using Neural Network to Accelerate AC-OPF Power Grid Simulation
In this paper, we develop a neural network approach to the problem of accelerating the current optimal power flow (AC-OPF) by generating an intelligent initial solution.
Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation
Evaluating with 20, 480 input problems, we show that Smartfluidnet achieves 1. 46x and 590x speedup comparing with a state-of-the-art neural network model and the original fluid simulation respectively on an NVIDIA Titan X Pascal GPU, while providing better simulation quality than the state-of-the-art model.
Large-scale Real-time Personalized Similar Product Recommendations
Similar product recommendation is one of the most common scenes in e-commerce.
Long Short-Term Relation Networks for Video Action Detection
It has been well recognized that modeling human-object or object-object relations would be helpful for detection task.
Feedback Graph Convolutional Network for Skeleton-based Action Recognition
It transmits the high-level semantic features to the low-level layers and flows temporal information stage by stage to progressively model global spatial-temporal features for action recognition; (3) The FGCN model provides early predictions.
Ranked #24 on
Skeleton Based Action Recognition
on NTU RGB+D 120
FLAME: A Self-Adaptive Auto-labeling System for Heterogeneous Mobile Processors
How to accurately and efficiently label data on a mobile device is critical for the success of training machine learning models on mobile devices.
Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning
Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation.
Artificial intelligence empowered multi-AGVs in manufacturing systems
AGVs are driverless robotic vehicles that picks up and delivers materials.
Spam Review Detection with Graph Convolutional Networks
Furthermore, we deploy our system to process million-scale data daily at Xianyu.
MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks
Second, all baggage images are captured by specially-designed multi-view camera system to handle pose variation and occlusion, in order to obtain the 3D information of baggage surface as complete as possible.
Combining Q&A Pair Quality and Question Relevance Features on Community-based Question Retrieval
The Q&A community has become an important way for people to access knowledge and information from the Internet.
Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
This notebook paper presents an overview and comparative analysis of our systems designed for the following three tasks in ActivityNet Challenge 2019: trimmed action recognition, dense-captioning events in videos, and spatio-temporal action localization.
Performance Analysis and Characterization of Training Deep Learning Models on Mobile Devices
In this paper, we perform a variety of experiments on a representative mobile device (the NVIDIA TX2) to study the performance of training deep learning models.
Graph Attention Memory for Visual Navigation
To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module.
A Preliminary Study of Neural Network-based Approximation for HPC Applications
Machine learning, as a tool to learn and model complicated (non)linear relationships between input and output data sets, has shown preliminary success in some HPC problems.
Enhanced Expressive Power and Fast Training of Neural Networks by Random Projections
The key in our proof is that random projections embed stably the set of sparse vectors or a low-dimensional smooth manifold into a low-dimensional subspace.
Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving
The control module which is based on reinforcement learning then makes a control decision based on these features.
Runtime Concurrency Control and Operation Scheduling for High Performance Neural Network Training
These frameworks employ a dataflow model where the NN training is modeled as a directed graph composed of a set of nodes.
Recurrent Tubelet Proposal and Recognition Networks for Action Detection
The RTP initializes action proposals of the start frame through a Region Proposal Network and then estimates the movements of proposals in next frame in a recurrent manner.
Baidu Apollo EM Motion Planner
In this manuscript, we introduce a real-time motion planning system based on the Baidu Apollo (open source) autonomous driving platform.
Progressive Representation Adaptation for Weakly Supervised Object Localization
In classification adaptation, we transfer a pre-trained network to a multi-label classification task for recognizing the presence of a certain object in an image.
Joint Maximum Purity Forest with Application to Image Super-Resolution
In the JMPF scheme, the original feature space is transformed into a compactly pre-clustered feature space, via a trained rotation matrix.
Ranked #48 on
Image Super-Resolution
on BSD100 - 4x upscaling
Learning Structured Semantic Embeddings for Visual Recognition
First, we exploit the discriminative constraints to capture the intra- and inter-class relationships of image embeddings.
Weakly Supervised Object Localization With Progressive Domain Adaptation
In this paper, we address this problem by progressive domain adaptation with two main steps: classification adaptation and detection adaptation.
