Search Results for author:
Found 47 papers, 13 papers with code
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation
The emergence of Neural Radiance Fields (NeRF) has greatly impacted 3D scene modeling and novel-view synthesis.
PROMPT-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression
Large language models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks.
Multi-hop Question Answering under Temporal Knowledge Editing
Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models.
Parallelized Midpoint Randomization for Langevin Monte Carlo
We explore the sampling problem within the framework where parallel evaluations of the gradient of the log-density are feasible.
MONAL: Model Autophagy Analysis for Modeling Human-AI Interactions
The increasing significance of large models and their multi-modal variants in societal information processing has ignited debates on social safety and ethics.
Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies
The advent of large language models (LLMs) such as ChatGPT, PaLM, and GPT-4 has catalyzed remarkable advances in natural language processing, demonstrating human-like language fluency and reasoning capacities.
Hierarchical Prompts for Rehearsal-free Continual Learning
Nonetheless, these learnable prompts tend to concentrate on the discriminatory knowledge of the current task while ignoring past task knowledge, leading to that learnable prompts still suffering from catastrophic forgetting.
Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning
Considering this challenge, we propose a novel framework of fine-grained knowledge selection and restoration.
CACFNet: Cross-Modal Attention Cascaded Fusion Network for RGB-T Urban Scene Parsing
Color–thermal (RGB-T) urban scene parsing has recently attracted widespread interest.
Ranked #5 on
Thermal Image Segmentation
on PST900
VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis
Unsupervised learning of 3D-aware generative adversarial networks has lately made much progress.
Edit-DiffNeRF: Editing 3D Neural Radiance Fields using 2D Diffusion Model
To address this challenge, we propose the Edit-DiffNeRF framework, which is composed of a frozen diffusion model, a proposed delta module to edit the latent semantic space of the diffusion model, and a NeRF.
Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited
To provide a more thorough explanation of our method for establishing the computable upper bound, we conduct an analysis of the midpoint discretization for the vanilla Langevin process.
Camera-Incremental Object Re-Identification with Identity Knowledge Evolution
In this paper, we propose a novel Identity Knowledge Evolution (IKE) framework for CIOR, consisting of the Identity Knowledge Association (IKA), Identity Knowledge Distillation (IKD), and Identity Knowledge Update (IKU).
Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment
In this paper, we propose a quality-agnostic framework to improve the performance and robustness of image captioning models for visually impaired people.
Knowledge Distillation for Efficient Sequences of Training Runs
We find that augmenting future runs with KD from previous runs dramatically reduces the time necessary to train these models, even taking into account the overhead of KD.
X-Pruner: eXplainable Pruning for Vision Transformers
Recent studies have proposed to prune transformers in an unexplainable manner, which overlook the relationship between internal units of the model and the target class, thereby leading to inferior performance.
DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation
In recommendation scenarios, there are two long-standing challenges, i. e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks.
SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory
Neural Radiance Fields (NeRF) have demonstrated superior novel view synthesis performance but are slow at rendering.
Going for GOAL: A Resource for Grounded Football Commentaries
As the course of a game is unpredictable, so are commentaries, which makes them a unique resource to investigate dynamic language grounding.
GEBNet: Graph-Enhancement Branch Network for RGB-T Scene Parsing
RGB-T (red–green–blue and thermal) scene parsing has recently drawn considerable research attention.
Ranked #9 on
Thermal Image Segmentation
on PST900
Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering
We first propose three plausible task formulations and demonstrate their impact on the performance of continual learning algorithms.
Few-shot News Recommendation via Cross-lingual Transfer
Second, the user preference over these topics is transferable across different platforms.
eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised Semantic Segmentation
To close these crucial gaps, we propose a novel vision transformer dubbed the eXplainable Vision Transformer (eX-ViT), an intrinsically interpretable transformer model that is able to jointly discover robust interpretable features and perform the prediction.
Adversarial Robustness of Visual Dialog
This study is the first to investigate the robustness of visually grounded dialog models towards textual attacks.
Q-LIC: Quantizing Learned Image Compression with Channel Splitting
Learned image compression (LIC) has reached a comparable coding gain with traditional hand-crafted methods such as VVC intra.
MTANet: Multitask-Aware Network With Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding
To improve the fusion of multimodal features and the segmentation accuracy, we propose a multitask-aware network (MTANet) with hierarchical multimodal fusion (multiscale fusion strategy) for RGB-T urban scene understanding.
Ranked #10 on
Thermal Image Segmentation
on PST900
Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance
We study stochastic convex optimization under infinite noise variance.
Spectral Clustering with Variance Information for Group Structure Estimation in Panel Data
Consider a panel data setting where repeated observations on individuals are available.
Continually Learning Self-Supervised Representations with Projected Functional Regularization
Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches.
End-to-End Learned Image Compression with Quantized Weights and Activations
To our best knowledge, this is the first work to give a complete analysis on the coding gain and the memory cost for a quantized LIC network, which validates the feasibility of the hardware implementation.
Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data
Therefore, we investigate knowledge distillation to transfer knowledge from a high-quality unconditioned generative model (e. g., StyleGAN) to a conditioned synthetic image generation modules in a variety of systems.
A Simple and Debiased Sampling Method for Personalized Ranking
Pairwise ranking models have been widely used to address various problems, such as recommendation.
Fully Neural Network Mode Based Intra Prediction of Variable Block Size
As far as we know, this is the first work to explore a fully NM based framework for intra prediction, and we reach a better coding gain with a lower complexity compared with the previous work.
Subjective evaluation of traditional and learning-based image coding methods
Additionally, we utilize some typical and frequently used objective quality metrics to evaluate the coding methods in the experiment as comparison.
Self-Training for Class-Incremental Semantic Segmentation
In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks.
Class-Incremental Semantic Segmentation
Incremental Learning
DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs
To enable the training of deep I2I models on small datasets, we propose a novel transfer learning method, that transfers knowledge from pre-trained GANs.
Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases
Multi-hop relation reasoning over knowledge base is to generate effective and interpretable relation prediction through reasoning paths.
Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition
Although the facial makeup transfer network has achieved high-quality performance in generating perceptually pleasing makeup images, its capability is still restricted by the massive computation and storage of the network architecture.
SAIL: Self-Augmented Graph Contrastive Learning
This paper studies learning node representations with graph neural networks (GNNs) for unsupervised scenario.
An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias
Structured non-convex learning problems, for which critical points have favorable statistical properties, arise frequently in statistical machine learning.
Addressing Class-Imbalance Problem in Personalized Ranking
Pairwise ranking models have been widely used to address recommendation problems.
Semantic Drift Compensation for Class-Incremental Learning
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
False Discovery Rates in Biological Networks
The increasing availability of data has generated unprecedented prospects for network analyses in many biological fields, such as neuroscience (e. g., brain networks), genomics (e. g., gene-gene interaction networks), and ecology (e. g., species interaction networks).
Methodology Quantitative Methods Applications
Learning Metrics from Teachers: Compact Networks for Image Embedding
In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks.
Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
Despite enjoying extensive applications in video analysis, three-dimensional convolutional neural networks (3D CNNs)are restricted by their massive computation and storage consumption.
Weakly Supervised Domain-Specific Color Naming Based on Attention
The attention branch is used to modulate the pixel-wise color naming predictions of the network.
Oracle Inequalities for High-dimensional Prediction
The abundance of high-dimensional data in the modern sciences has generated tremendous interest in penalized estimators such as the lasso, scaled lasso, square-root lasso, elastic net, and many others.
