Search Results for author:
Found 30 papers, 11 papers with code
Simple Hierarchical Planning with Diffusion
Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets.
Computational Spectral Imaging with Unified Encoding Model: A Comparative Study and Beyond
Computational spectral imaging is drawing increasing attention owing to the snapshot advantage, and amplitude, phase, and wavelength encoding systems are three types of representative implementations.
Learning Exhaustive Correlation for Spectral Super-Resolution: Where Spatial-Spectral Attention Meets Linear Dependence
By integrating unified spatial-spectral attention and linear dependence, our ECT can model exhaustive correlation within HSI.
All Languages Matter: On the Multilingual Safety of Large Language Models
In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice.
An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software
Moreover, through retraining the models with the test cases generated by OASIS, the robustness of the moderation model can be improved without performance degradation.
Validating Multimedia Content Moderation Software via Semantic Fusion
To this end, content moderation software has been widely deployed on these platforms to detect and blocks toxic content.
Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables
However, the size of a single LUT grows exponentially with the increase of its indexing capacity, which restricts its receptive field and thus the performance.
TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training
In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the network topology.
Learning Steerable Function for Efficient Image Resampling
Image resampling is a basic technique that is widely employed in daily applications.
Toward RAW Object Detection: A New Benchmark and a New Model
In many computer vision applications (e. g., robotics and autonomous driving), high dynamic range (HDR) data is necessary for object detection algorithms to handle a variety of lighting conditions, such as strong glare.
Style Projected Clustering for Domain Generalized Semantic Segmentation
In contrast to existing methods, we instead utilize the difference between images to build a better representation space, where the distinct style features are extracted and stored as the bases of representation.
GARF:Geometry-Aware Generalized Neural Radiance Field
To address these issues, we propose Geometry-Aware Generalized Neural Radiance Field (GARF) with a geometry-aware dynamic sampling (GADS) strategy to perform real-time novel view rendering and unsupervised depth estimation on unseen scenes without per-scene optimization.
Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach
To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions.
Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
Trans4Map: Revisiting Holistic Bird's-Eye-View Mapping from Egocentric Images to Allocentric Semantics with Vision Transformers
Humans have an innate ability to sense their surroundings, as they can extract the spatial representation from the egocentric perception and form an allocentric semantic map via spatial transformation and memory updating.
TransDreamer: Reinforcement Learning with Transformer World Models
We then share this world model with a transformer-based policy network and obtain stability in training a transformer-based RL agent.
Model-based Reinforcement Learning
reinforcement-learning
+1
Retinal Vessel Segmentation with Pixel-wise Adaptive Filters
Accurate retinal vessel segmentation is challenging because of the complex texture of retinal vessels and low imaging contrast.
Contextual Outpainting With Object-Level Contrastive Learning
To model the contextual correlation between foreground and background contents, we incorporate an object-level contrastive loss to regularize the learning of cross-modal representations of foreground contents and the corresponding background semantic layout, facilitating accurate semantic reasoning.
Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representation
In this paper, we propose Neural Spectral Reconstruction (NeSR) to lift this limitation, by introducing a novel continuous spectral representation.
Flying Guide Dog: Walkable Path Discovery for the Visually Impaired Utilizing Drones and Transformer-based Semantic Segmentation
By recognizing the color of pedestrian traffic lights, our prototype can help the user to cross a street safely.
Light Field Super-Resolution With Zero-Shot Learning
To fill this gap, we propose a zero-shot learning framework for light field SR, which learns a mapping to super-resolve the reference view with examples extracted solely from the input low-resolution light field itself.
Advanced Deep Networks for 3D Mitochondria Instance Segmentation
Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods.
Ranked #1 on
3D Instance Segmentation
on MitoEM
Learning the Evolution of the Universe in N-body Simulations
Understanding the physics of large cosmological surveys down to small (nonlinear) scales will significantly improve our knowledge of the Universe.
Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study
A three-level hierarchical classification system for pulmonary lesions is developed, which covers most diseases in cancer-related diagnosis.
ROOTS: Object-Centric Representation and Rendering of 3D Scenes
A crucial ability of human intelligence is to build up models of individual 3D objects from partial scene observations.
Camera Trace Erasing
To reconcile these two demands, we propose Siamese Trace Erasing (SiamTE), in which a novel hybrid loss is designed on the basis of Siamese architecture for network training.
OBJECT-ORIENTED REPRESENTATION OF 3D SCENES
In this paper, we propose a generative model, called ROOTS (Representation of Object-Oriented Three-dimension Scenes), for unsupervised object-wise 3D-scene decomposition and and rendering.
Camera Lens Super-Resolution
Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling.
Deep Boosting for Image Denoising
Boosting is a classic algorithm which has been successfully applied to diverse computer vision tasks.
Achieving Human Parity on Automatic Chinese to English News Translation
Machine translation has made rapid advances in recent years.
Ranked #3 on
Machine Translation
on WMT 2017 English-Chinese
