Search Results for author:
Found 69 papers, 24 papers with code
Unveiling Deep Shadows: A Survey on Image and Video Shadow Detection, Removal, and Generation in the Era of Deep Learning
Shadows are formed when light encounters obstacles, leading to areas of diminished illumination.
Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models
This paper investigates the task of the open-ended interactive robotic manipulation on table-top scenarios.
A dual-task mutual learning framework for predicting post-thrombectomy cerebral hemorrhage
Ischemic stroke is a severe condition caused by the blockage of brain blood vessels, and can lead to the death of brain tissue due to oxygen deprivation.
Enhancing Computer Programming Education with LLMs: A Study on Effective Prompt Engineering for Python Code Generation
This paper explores this potential by investigating three critical research questions: the systematic categorization of prompt engineering strategies tailored to diverse educational needs, the empowerment of LLMs to solve complex problems beyond their inherent capabilities, and the establishment of a robust framework for evaluating and implementing these strategies.
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
For this purpose, we establish a new benchmark comprising text prompts that fully reflect multiple dynamics grades, and define a set of dynamics scores corresponding to various temporal granularities to comprehensively evaluate the dynamics of each generated video.
Contextual Optimization under Covariate Shift: A Robust Approach by Intersecting Wasserstein Balls
To address this, we propose a distributionally robust approach that uses an ambiguity set by the intersection of two Wasserstein balls, each centered on typical nonparametric or parametric distribution estimators.
Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment
We first introduce encoders and decoders to associate the states and actions of the source robot with a latent space.
AIGB: Generative Auto-bidding via Conditional Diffusion Modeling
Auto-bidding plays a crucial role in facilitating online advertising by automatically providing bids for advertisers.
Batched Stochastic Bandit for Nondegenerate Functions
More specifically, we introduce an algorithm, called Geometric Narrowing (GN), whose regret bound is of order $\widetilde{{\mathcal{O}}} ( A_{+}^d \sqrt{T} )$.
Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation
In the next stage, we use an object network to estimate the depth of those moving objects assuming rigid motions.
Scaling on-chip photonic neural processors using arbitrarily programmable wave propagation
On-chip photonic processors for neural networks have potential benefits in both speed and energy efficiency but have not yet reached the scale at which they can outperform electronic processors.
etuner: A Redundancy-Aware Framework for Efficient Continual Learning Application on Edge Devices
Many emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and require the deployment of DNN models on edge devices.
Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications
Machine learning algorithms minimizing average risk are susceptible to distributional shifts.
The hardware is the software
Human brains and bodies are not hardware running software: the hardware is the software.
Variational Inference for Scalable 3D Object-centric Learning
We tackle the task of scalable unsupervised object-centric representation learning on 3D scenes.
WALL-E: Embodied Robotic WAiter Load Lifting with Large Language Model
The target instruction is then forwarded to a visual grounding system for object pose and size estimation, following which the robot grasps the object accordingly.
SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels
Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data.
Quantum-noise-limited optical neural networks operating at a few quanta per activation
We experimentally demonstrated MNIST classification with a test accuracy of 98% using an optical neural network with a hidden layer operating in the single-photon regime; the optical energy used to perform the classification corresponds to 0. 008 photons per multiply-accumulate (MAC) operation, which is equivalent to 0. 003 attojoules of optical energy per MAC.
Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data
Different distribution shifts require different interventions, and algorithms must be grounded in the specific shifts they address.
Probabilistic and Semantic Descriptions of Image Manifolds and Their Applications
This paper begins with a description of methods for estimating image probability density functions that reflects the observation that such data is usually constrained to lie in restricted regions of the high-dimensional image space-not every pattern of pixels is an image.
Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization
We develop a general bias correction approach, building on what we call Optimizer's Information Criterion (OIC), that directly approximates the first-order bias and does not require solving any additional optimization problems.
WYWEB: A NLP Evaluation Benchmark For Classical Chinese
To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE.
From Random Search to Bandit Learning in Metric Measure Spaces
We show that, when the environment is noise-free, the output of random search converges to the optimal value in probability at rate $ \widetilde{\mathcal{O}} \left( \left( \frac{1}{T} \right)^{ \frac{1}{d_s} } \right) $, where $ d_s \ge 0 $ is the scattering dimension of the underlying function.
WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal
To this end, we propose a method called Weather-aware Multi-scale MoE (WM-MoE) based on Transformer for blind weather removal.
Optical Transformers
We conclude that with well-engineered, large-scale optical hardware, it may be possible to achieve a $100 \times$ energy-efficiency advantage for running some of the largest current Transformer models, and that if both the models and the optical hardware are scaled to the quadrillion-parameter regime, optical computers could have a $>8, 000\times$ energy-efficiency advantage over state-of-the-art digital-electronic processors that achieve 300 fJ/MAC.
A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization
We also apply BLiE to search for noise schedule of diffusion models.
Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions
Inspired by this observation, we design an efficient unified framework with a two-stage training strategy to explore the weather-general and weather-specific features.
H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction
First, we decouple hand mesh reconstruction into two branches, one to exploit finger-level non-occluded information and the other to exploit global hand orientation, with lightweight structures to promote real-time inference.
Ranked #5 on
3D Hand Pose Estimation
on DexYCB
Hedging Complexity in Generalization via a Parametric Distributionally Robust Optimization Framework
We propose a simple approach in which the distribution of random perturbations is approximated using a parametric family of distributions.
Video Instance Shadow Detection Under the Sun and Sky
Instance shadow detection, crucial for applications such as photo editing and light direction estimation, has undergone significant advancements in predicting shadow instances, object instances, and their associations.
Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection
Importantly, we formulate the lightweight plug-in S2D module and the point cloud reconstruction module in SDet to densify 3D features and train SDet to produce 3D features, following the dense 3D features in DDet.
Linear RNNs Provably Learn Linear Dynamic Systems
We study the learning ability of linear recurrent neural networks with Gradient Descent.
Convergence Rates of Stochastic Zeroth-order Gradient Descent for Ł ojasiewicz Functions
We prove convergence rates of Stochastic Zeroth-order Gradient Descent (SZGD) algorithms for Lojasiewicz functions.
A Direct Approximation of AIXI Using Logical State Abstractions
We propose a practical integration of logical state abstraction with AIXI, a Bayesian optimality notion for reinforcement learning agents, to significantly expand the model class that AIXI agents can be approximated over to complex history-dependent and structured environments.
Image sensing with multilayer, nonlinear optical neural networks
In image sensing, a measurement, such as of an object's position, is performed by computational analysis of a digitized image.
Instance Shadow Detection with A Single-Stage Detector
This paper formulates a new problem, instance shadow detection, which aims to detect shadow instance and the associated object instance that cast each shadow in the input image.
Ranked #1 on
Instance Shadow Detection
on SOBA
Latent Policies for Adversarial Imitation Learning
We use an action encoder-decoder model to obtain a low-dimensional latent action space and train a LAtent Policy using Adversarial imitation Learning (LAPAL).
Stochastic Zeroth Order Gradient and Hessian Estimators: Variance Reduction and Refined Bias Bounds
In particular, we design estimators for smooth functions such that, if one uses $ \Theta \left( k \right) $ random directions sampled from the Stiefel's manifold $ \text{St} (n, k) $ and finite-difference granularity $\delta$, the variance of the gradient estimator is bounded by $ \mathcal{O} \left( \left( \frac{n}{k} - 1 \right) + \left( \frac{n^2}{k} - n \right) \delta^2 + \frac{ n^2 \delta^4 }{ k } \right) $, and the variance of the Hessian estimator is bounded by $\mathcal{O} \left( \left( \frac{n^2}{k^2} - 1 \right) + \left( \frac{n^4}{k^2} - n^2 \right) \delta^2 + \frac{n^4 \delta^4 }{k^2} \right) $.
On Sharp Stochastic Zeroth Order Hessian Estimators over Riemannian Manifolds
We show that, for an analytic real-valued function $f$, our estimator achieves a bias bound of order $ O \left( \gamma \delta^2 \right) $, where $ \gamma $ depends on both the Levi-Civita connection and function $f$, and $\delta$ is the finite difference step size.
DMF-Net: Dual-Branch Multi-Scale Feature Fusion Network for copy forgery identification of anti-counterfeiting QR code
We first analyze the production principle of anti-counterfeiting QR code, and convert the identification of copy forgery to device category forensics, and then a Dual-Branch Multi-Scale Feature Fusion network is proposed.
Lipschitz Bandits with Batched Feedback
Specifically, we show that for a $T$-step problem with Lipschitz reward of zooming dimension $d_z$, our algorithm achieves theoretically optimal (up to logarithmic factors) regret rate $\widetilde{\mathcal{O}}\left(T^{\frac{d_z+1}{d_z+2}}\right)$ using only $ \mathcal{O} \left( \log\log T\right) $ batches.
Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction
3D hand-mesh reconstruction from RGB images facilitates many applications, including augmented reality (AR).
Ranked #16 on
3D Hand Pose Estimation
on FreiHAND
From the Greene--Wu Convolution to Gradient Estimation over Riemannian Manifolds
Over a complete Riemannian manifold of finite dimension, Greene and Wu introduced a convolution, known as Greene-Wu (GW) convolution.
Single-Stage Instance Shadow Detection with Bidirectional Relation Learning
Instance shadow detection aims to find shadow instances paired with the objects that cast the shadows.
Ranked #2 on
Instance Shadow Detection
on SOBA
Distributionally Robust Prescriptive Analytics with Wasserstein Distance
In prescriptive analytics, the decision-maker observes historical samples of $(X, Y)$, where $Y$ is the uncertain problem parameter and $X$ is the concurrent covariate, without knowing the joint distribution.
Spatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition
Experimental results demonstrate that SPAIR3D has strong scalability and is capable of detecting and segmenting an unknown number of objects from a point cloud in an unsupervised manner.
Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
Deep neural networks have become a pervasive tool in science and engineering.
An optical neural network using less than 1 photon per multiplication
Here, we experimentally demonstrate an optical neural network achieving 99% accuracy on handwritten-digit classification using ~3. 2 detected photons per weight multiplication and ~90% accuracy using ~0. 64 photons (~$2. 4 \times 10^{-19}$ J of optical energy) per weight multiplication.
Conceptual similarity and communicative need shape colexification: an experimental study
Colexification refers to the phenomenon of multiple meanings sharing one word in a language.
WFA-IRL: Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata
This paper presents a method for learning logical task specifications and cost functions from demonstrations.
dame-flame: A Python Library Providing Fast Interpretable Matching for Causal Inference
dame-flame is a Python package for performing matching for observational causal inference on datasets containing discrete covariates.
Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning
The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert's observations and state-control trajectory.
Episodic Linear Quadratic Regulators with Low-rank Transitions
Consequently, the sample complexity of our algorithm only depends on the rank, $m$, rather than the ambient dimension, $d$, which can be orders-of-magnitude larger.
Towards Fundamental Limits of Multi-armed Bandits with Random Walk Feedback
In this paper, we consider a new Multi-Armed Bandit (MAB) problem where arms are nodes in an unknown and possibly changing graph, and the agent (i) initiates random walks over the graph by pulling arms, (ii) observes the random walk trajectories, and (iii) receives rewards equal to the lengths of the walks.
Bandits for BMO Functions
We study the bandit problem where the underlying expected reward is a Bounded Mean Oscillation (BMO) function.
Adaptive Discretization for Model-Based Reinforcement Learning
We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces.
Model-based Reinforcement Learning
reinforcement-learning
+2
Learning Navigation Costs from Demonstration with Semantic Observations
The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert's observations and state-control trajectory.
Learning Navigation Costs from Demonstrations with Semantic Observations
The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert’s observations and state-control trajectory.
Learning Navigation Costs from Demonstration in Partially Observable Environments
This paper focuses on inverse reinforcement learning (IRL) to enable safe and efficient autonomous navigation in unknown partially observable environments.
Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world.
Ranked #10 on
Shadow Detection
on CUHK-Shadow
Instance Shadow Detection
Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results.
Ranked #3 on
Instance Shadow Detection
on SOBA
Large Scale Model Predictive Control with Neural Networks and Primal Active Sets
The approach combines an offline-trained fully-connected neural network with an online primal active set solver.
Transfer Learning for Hate Speech Detection in Social Media
This paper uses a transfer learning technique to leverage two independent datasets jointly and builds a single representation of hate speech.
Social and Information Networks Computers and Society
Shortest Paths in HSI Space for Color Texture Classification
Color texture representation is an important step in the task of texture classification.
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
Second, to better cover the stochastic distribution of real rain streaks, we propose a novel SPatial Attentive Network (SPANet) to remove rain streaks in a local-to-global manner.
Ranked #3 on
Single Image Deraining
on RainCityscapes
SAC-Net: Spatial Attenuation Context for Salient Object Detection
This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects.
Towards Practical Lipschitz Bandits
Stochastic Lipschitz bandit algorithms balance exploration and exploitation, and have been used for a variety of important task domains.
FLAME: A Fast Large-scale Almost Matching Exactly Approach to Causal Inference
In this work, we propose a method that computes high quality almost-exact matches for high-dimensional categorical datasets.
