Search Results for author:
Found 71 papers, 29 papers with code
Retrieve, Discriminate and Rewrite: A Simple and Effective Framework for Obtaining Affective Response in Retrieval-Based Chatbots
To address this problem, we propose a simple and effective Retrieve-Discriminate-Rewrite framework.
Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis
Given a reference face and a text prompt, FaceCLIP produces a unified representation that encodes both identity and text, which conditions a base diffusion model to generate images that are identity-consistent and text-aligned.
NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results.
Flux Already Knows -- Activating Subject-Driven Image Generation without Training
We propose a simple yet effective zero-shot framework for subject-driven image generation using a vanilla Flux model.
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX.
Prediction Interval Construction Method for Electricity Prices
Accurate prediction of electricity prices plays an essential role in the electricity market.
Promoting Shared Energy Storage Aggregation among High Price-Tolerance Prosumer: An Incentive Deposit and Withdrawal Service
To incentivize these high price-tolerance residential prosumers to participate in SES, a novel SES aggregation framework is proposed, which does not require prosumers to take additional actions and allows them to maintain existing energy storage patterns.
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models
A key issue is that fine-tuning often compromises the safety alignment of LLMs.
Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation
To overcome this challenge, existing methods often use multi-modal models like CLIP, which combine image and text features in a shared embedding space to bridge the gap between limited and extensive vocabulary recognition, resulting in a two-stage approach: In the first stage, a mask generator takes an input image to generate mask proposals, and the in the second stage the target mask is picked based on the query.
Multi-object Tracking by Detection and Query: an efficient end-to-end manner
Multi-object tracking is advancing through two dominant paradigms: traditional tracking by detection and newly emerging tracking by query.
GSpect: Spectral Filtering for Cross-Scale Graph Classification
Compared with other methods, we use graph wavelet neural networks for the convolution layer of the model, which aggregates multi-scale messages to generate graph representations.
PriorMapNet: Enhancing Online Vectorized HD Map Construction with Priors
To address this issue, we introduce PriorMapNet to enhance online vectorized HD map construction with priors.
Intermittent Semi-working Mask: A New Masking Paradigm for LLMs
In this way, ISM is able to maintain the high quality of prefix LLM and low generation latency of causal LLM, simultaneously.
Enhancing context models for point cloud geometry compression with context feature residuals and multi-loss
In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the probability distribution predicted by the context model as the loss function.
Enhancing octree-based context models for point cloud geometry compression with attention-based child node number prediction
The proposed module can predict the number of occupied child nodes and map it into an 8- dimensional vector to assist the context model in predicting the probability distribution of the occupancy of the current node for efficient entropy coding.
PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression
Learning-based methods have proven successful in compressing geometric information for point clouds.
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse.
TraceNet: Segment one thing efficiently
To address this, we propose and formulate a one tap driven single instance segmentation task that segments a single instance selected by a user via a positive tap.
Non-autoregressive Personalized Bundle Generation
The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation.
Network Structure Governs Drosophila Brain Functionality
The results revealed that even with rudimentary neuronal activation mechanisms, models grounded in real neural network structures can generate activation patterns strikingly similar to those observed in the actual brain.
A Dual-domain Regularization Method for Ring Artifact Removal of X-ray CT
The proposed model corrects the vertical stripe artifacts on the sinogram by innovatively updating the response inconsistency compensation coefficients of detector units, which is achieved by employing the group sparse constraint and the projection-view direction sparse constraint on the stripe artifacts.
How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers
Through analysis, we found the contribution ratio of Multi-Head Attention (a combination function) to pre-trained language modeling is a key factor affecting base capabilities.
Vanilla Transformers are Transfer Capability Teachers
However, studies have indicated that MoE Transformers underperform vanilla Transformers in many downstream tasks, significantly diminishing the practical value of MoE models.
Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering
Dr. Bokeh then takes the layered representation and user-defined lens parameters to render photo-realistic lens blur based on the novel occlusion-aware bokeh rendering method.
Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval
To handle this limitation, we substitute convolutional descriptors for attention-guided features and propose an Attributes Grouping and Mining Hashing (AGMH), which groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation for efficient fine-grained image retrieval.
Data-Centric Financial Large Language Models
Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance.
Hybrid of representation learning and reinforcement learning for dynamic and complex robotic motion planning
Reinforcement learning algorithms generate optimal or near-optimal time-sequential predictions.
Text2Layer: Layered Image Generation using Latent Diffusion Model
To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation.
Is ChatGPT Equipped with Emotional Dialogue Capabilities?
This report presents a study on the emotional dialogue capability of ChatGPT, an advanced language model developed by OpenAI.
Detecting Temporal shape changes with the Euler Characteristic Transform
Organoids are multi-cellular structures which are cultured in vitro from stem cells to resemble specific organs (e. g., brain, liver) in their three-dimensional composition.
Boosting Binary Neural Networks via Dynamic Thresholds Learning
For ViTs, DyBinaryCCT presents the superiority of the convolutional embedding layer in fully binarized ViTs and achieves 56. 1% on the ImageNet dataset, which is nearly 9% higher than the baseline.
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Long-tail distribution is widely spread in real-world applications.
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning
Specifically, there are an object detection task (consisting of an instance-classification task and a localization task) and an image-classification task in our framework, responsible for utilizing the two types of supervision.
Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness
As a critical step to achieve human-like chatbots, empathetic response generation has attained increasing interests.
Neighbor Regularized Bayesian Optimization for Hyperparameter Optimization
Bayesian Optimization (BO) is a common solution to search optimal hyperparameters based on sample observations of a machine learning model.
Multiscale methods for signal selection in single-cell data
Analysis of single-cell transcriptomics often relies on clustering cells and then performing differential gene expression (DGE) to identify genes that vary between these clusters.
A Unified Model for Multi-class Anomaly Detection
For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88. 1% to 96. 5%) and anomaly localization (from 89. 5% to 96. 8%).
Ranked #3 on
Multi-class Anomaly Detection
on MVTec AD
Few-shot Object Counting with Similarity-Aware Feature Enhancement
This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i. e., described by one or several support images) occurring in the query image.
Ranked #2 on
Object Counting
on CARPK
On Efficient Transformer-Based Image Pre-training for Low-Level Vision
Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems.
Ranked #11 on
Image Super-Resolution
on Set5 - 2x upscaling
(using extra training data)
Improving Image Restoration by Revisiting Global Information Aggregation
Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images.
Ranked #1 on
Color Image Denoising
on Urban100 sigma30
Dynamic Binary Neural Network by learning channel-wise thresholds
The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs.
Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
A detailed description of all models developed in the challenge is provided in this paper.
HINet: Half Instance Normalization Network for Image Restoration
Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks.
Ranked #3 on
Single Image Deraining
on Test2800
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner.
A Transition-based Parser for Unscoped Episodic Logical Forms
"Episodic Logic:Unscoped Logical Form" (EL-ULF) is a semantic representation capturing predicate-argument structure as well as more challenging aspects of language within the Episodic Logic formalism.
Interplay between charge order and superconductivity in the kagome metal KV$_3$Sb$_5$
Beyond $p\approx10$ GPa, a second superconducting dome emerges with maximum $T_{\rm c}\approx1. 0$ K at $p_{\rm c2}\approx22$ GPa, which becomes fully suppressed at $p\approx28$ GPa.
Superconductivity
Growth, Electronic Structure and Superconductivity of Ultrathin Epitaxial CoSi2 Films
We report growth, electronic structure and superconductivity of ultrathin epitaxial CoSi2 films on Si(111).
Mesoscale and Nanoscale Physics
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally.
Ranked #18 on
Instance Segmentation
on LVIS v1.0 val
An Iterative Emotion Interaction Network for Emotion Recognition in Conversations
We noticed that the gold emotion labels of the context utterances can provide explicit and accurate emotion interaction, but it is impossible to input gold labels at inference time.
Ranked #46 on
Emotion Recognition in Conversation
on IEMOCAP
MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
In this paper, we propose MimicDet, a novel and efficient framework to train a one-stage detector by directly mimic the two-stage features, aiming to bridge the accuracy gap between one-stage and two-stage detectors.
Dirac quantum well engineering on the surface of topological insulator
We investigate possible hybridization between these interface states as a function of the width of the topological material and of the characteristic interface size.
Mesoscale and Nanoscale Physics High Energy Physics - Theory Quantum Physics
Information Mandala: Statistical Distance Matrix with Clustering
In machine learning, observation features are measured in a metric space to obtain their distance function for optimization.
MMDetection: Open MMLab Detection Toolbox and Benchmark
In this paper, we introduce the various features of this toolbox.
A deep learning framework for quality assessment and restoration in video endoscopy
Given the widespread use of endoscopy in different clinical applications, we contend that the robust and reliable identification of such artifacts and the automated restoration of corrupted video frames is a fundamental medical imaging problem.
Foreground-aware Image Inpainting
We show that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inpainting.
Grid R-CNN
This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.
Ranked #10 on
2D Object Detection
on SARDet-100K
Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias
While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts.
Flow-Grounded Spatial-Temporal Video Prediction from Still Images
Existing video prediction methods mainly rely on observing multiple historical frames or focus on predicting the next one-frame.
Free-Form Image Inpainting with Gated Convolution
We present a generative image inpainting system to complete images with free-form mask and guidance.
Ranked #3 on
Image Inpainting
on Places2 val
Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios.
Generative Image Inpainting with Contextual Attention
Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.
MAttNet: Modular Attention Network for Referring Expression Comprehension
In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression.
Generalized Referring Expression Segmentation
Referring Expression
+1
Scene Parsing with Global Context Embedding
We present a scene parsing method that utilizes global context information based on both the parametric and non- parametric models.
Universal Style Transfer via Feature Transforms
The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.
Recurrent Multimodal Interaction for Referring Image Segmentation
In this paper we are interested in the problem of image segmentation given natural language descriptions, i. e. referring expressions.
Diversified Texture Synthesis with Feed-forward Networks
Recent progresses on deep discriminative and generative modeling have shown promising results on texture synthesis.
High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis
Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal.
Deep Multi-Patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation
We propose a deep multi-patch aggregation network training approach, which allows us to train models using multiple patches generated from one image.
Ranked #8 on
Aesthetics Quality Assessment
on AVA
