Search Results for author:
Found 272 papers, 80 papers with code
Data Augmentation for Low-resource Word Segmentation and POS Tagging of Ancient Chinese Texts
Although SikuRoberta significantly boosts performance on WSG and POS tasks on ancient Chinese texts, the lack of labeled data still limits the performance of the model.
On the Transferability of Adversarial Attacks against Neural Text Classifier
Based on these studies, we propose a genetic algorithm to find an ensemble of models that can be used to induce adversarial examples to fool almost all existing models.
Sense Embeddings are also Biased – Evaluating Social Biases in Static and Contextualised Sense Embeddings
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word.
HUMOTO: A 4D Dataset of Mocap Human Object Interactions
We present Human Motions with Objects (HUMOTO), a high-fidelity dataset of human-object interactions for motion generation, computer vision, and robotics applications.
Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions
Additionally, we harness the capabilities of a pretrained language model to predict both continuous shape parameters and motion tokens, facilitating the synthesis of text-aligned motions and decoding them into shape-aware motions.
StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion
It contains a dual-modal sketch feature learning network that maps strokes into a high-quality latent space.
Nested Stochastic Gradient Descent for (Generalized) Sinkhorn Distance-Regularized Distributionally Robust Optimization
For this class of regularized DRO problems, we derive a novel dual formulation taking the form of nested stochastic programming, where the dual variable depends on the data sample.
RLDBF: Enhancing LLMs Via Reinforcement Learning With DataBase FeedBack
While current large language models (LLMs) demonstrate remarkable linguistic capabilities through training on massive unstructured text corpora, they remain inadequate in leveraging structured scientific data (e. g., chemical molecular properties in databases) that encapsulate centuries of accumulated scientific expertise.
Video Motion Graphs
HMInterp i) employs a dual-branch interpolation approach, combining a Motion Diffusion Model for human skeleton motion interpolation with a diffusion-based video frame interpolation model for final frame generation.
Dual Audio-Centric Modality Coupling for Talking Head Generation
The generation of audio-driven talking head videos is a key challenge in computer vision and graphics, with applications in virtual avatars and digital media.
Multiple-Particle Autofocusing Algorithm Using Axial Resolution and Morphological Analyses Based on Digital Holography
Based on the mean intensity and equivalent diameter of each candidate focused particle, all focused particles are eventually secured.
CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement
The meaning conveyed by a sentence often depends on the context in which it appears.
SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection
The data instances are multi-labeled into six emotional classes, with additional datasets in 11 languages annotated for emotion intensity.
Universal Incremental Learning: Mitigating Confusion from Inter- and Intra-task Distribution Randomness
In this work, we investigate $\textbf{Universal Incremental Learning (UIL)}$, where a model neither knows which new classes or domains will increase along sequential tasks, nor the scale of the increments within each task.
FREAK: Frequency-modulated High-fidelity and Real-time Audio-driven Talking Portrait Synthesis
To address this, we propose a FREquency-modulated, high-fidelity, and real-time Audio-driven talKing portrait synthesis framework, named FREAK, which models talking portraits from the frequency domain perspective, enhancing the fidelity and naturalness of the synthesized portraits.
Evaluating the Effect of Retrieval Augmentation on Social Biases
Retrieval Augmented Generation (RAG) has gained popularity as a method for conveniently incorporating novel facts that were not seen during the pre-training stage in Large Language Model (LLM)-based Natural Language Generation (NLG) systems.
GneissWeb: Preparing High Quality Data for LLMs at Scale
In this paper, we introduce GneissWeb, a large dataset yielding around 10 trillion tokens that caters to the data quality and quantity requirements of training LLMs.
BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages
In this paper, we present BRIGHTER-- a collection of multilabeled emotion-annotated datasets in 28 different languages.
MedMimic: Physician-Inspired Multimodal Fusion for Early Diagnosis of Fever of Unknown Origin
By combining the strengths of pretrained large models and deep learning, MedMimic offers a promising solution for disease classification.
MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining
Vision-language pretraining (VLP) has been investigated to generalize across diverse downstream tasks for fundus image analysis.
A Post-Processing-Based Fair Federated Learning Framework
In the first stage, a global model is trained without fairness constraints using a standard federated learning algorithm (e. g. FedAvg).
On Learning Representations for Tabular Data Distillation
Dataset distillation generates a small set of information-rich instances from a large dataset, resulting in reduced storage requirements, privacy or copyright risks, and computational costs for downstream modeling, though much of the research has focused on the image data modality.
Computational Protein Science in the Era of Large Language Models (LLMs)
As a result, researchers have actively introduced LLM techniques in computational protein science, developing protein Language Models (pLMs) that skillfully grasp the foundational knowledge of proteins and can be effectively generalized to solve a diversity of sequence-structure-function reasoning problems.
Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning
This paper discovers a counter-intuitive observation: by incorporating domain shift into CIL tasks, the forgetting rate is significantly reduced.
FaceLift: Single Image to 3D Head with View Generation and GS-LRM
Our pipeline begins by employing a multi-view latent diffusion model that generates consistent side and back views of the head from a single facial input.
DMesh++: An Efficient Differentiable Mesh for Complex Shapes
Recent probabilistic methods for 3D triangular meshes capture diverse shapes by differentiable mesh connectivity, but face high computational costs with increased shape details.
Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image Segmentation
In this paper, we propose a learnable prompting SAM-induced Knowledge distillation framework (KnowSAM) for semi-supervised medical image segmentation.
EvTTC: An Event Camera Dataset for Time-to-Collision Estimation
To explore the potential of event cameras in the above-mentioned challenging cases, we propose EvTTC, which is, to the best of our knowledge, the first multi-sensor dataset focusing on TTC tasks under high-relative-speed scenarios.
ProteinWeaver: A Divide-and-Assembly Approach for Protein Backbone Design
Comprehensive experiments demonstrate that ProteinWeaver: (1) generates high-quality, novel protein backbones through versatile domain assembly; (2) outperforms RFdiffusion, the current state-of-the-art in backbone design, by 13\% and 39\% for long-chain proteins; (3) shows the potential for cooperative function design through illustrative case studies.
Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey
World models and video generation are pivotal technologies in the domain of autonomous driving, each playing a critical role in enhancing the robustness and reliability of autonomous systems.
MAP: Multi-Human-Value Alignment Palette
Ensuring that generative AI systems align with human values is essential but challenging, especially when considering multiple human values and their potential trade-offs.
Mitigating Forgetting in LLM Supervised Fine-Tuning and Preference Learning
Post-training of pre-trained LLMs, which typically consists of the supervised fine-tuning (SFT) stage and the preference learning (RLHF or DPO) stage, is crucial to effective and safe LLM applications.
Adaptive Gradient Normalization and Independent Sampling for (Stochastic) Generalized-Smooth Optimization
Recent studies have shown that many nonconvex machine learning problems satisfy a generalized-smooth condition that extends beyond traditional smooth nonconvex optimization.
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date.
ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras
To this end, a compact back-end is proposed for continuously updating the IMU bias and predicting the linear velocity, enabling an accurate motion prediction for camera pose tracking.
CryoFM: A Flow-based Foundation Model for Cryo-EM Densities
Cryo-electron microscopy (cryo-EM) is a powerful technique in structural biology and drug discovery, enabling the study of biomolecules at high resolution.
Efficient Top-k s-Biplexes Search over Large Bipartite Graphs
We formulate the problem as the {\em top-$k$ $s$-biplex search (TBS) problem}, which aims to find the top-$k$ maximal $s$-biplexes with the most vertices, where $k$ is an input parameter.
KALE-LM: Unleash The Power Of AI For Science Via Knowledge And Logic Enhanced Large Model
Artificial intelligence is gradually demonstrating its immense potential, and increasing attention is being given to how AI can be harnessed to advance scientific research.
MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents
MOSS ensures consistency and adaptability by using a mechanism that maintains the Python context across interactions, including isolation of local variables and preservation of runtime integrity.
Multi-Modal Diffusion for Hand-Object Grasp Generation
Compared to previous works of generating hand poses with a given object, we aim to allow the generalization of both hand and object shapes by a single model.
GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models
This framework primarily includes a subgraph partitioning algorithm designed to generate negatives and neighbors.
Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
We present Perm, a learned parametric representation of human 3D hair designed to facilitate various hair-related applications.
COEFF-KANs: A Paradigm to Address the Electrolyte Field with KANs
Firstly, we adopt the publicly available MoLFormer model to obtain feature vectors for each solvent and salt in the electrolyte.
Exploring The Neural Burden In Pruned Models: An Insight Inspired By Neuroscience
Vision Transformer and its variants have been adopted in many visual tasks due to their powerful capabilities, which also bring significant challenges in computation and storage.
A Faster Branching Algorithm for the Maximum $k$-Defective Clique Problem
In the paper, we propose a new branching algorithm that takes advantage of the structural properties of the $k$-defective clique and uses the efficient maximum clique algorithm as a subroutine.
Motion and Structure from Event-based Normal Flow
Its success in standard vision is attributed to the maturity of feature extraction, data association and multi-view geometry.
Turning Generative Models Degenerate: The Power of Data Poisoning Attacks
Moreover, we demonstrate that existing popular defenses are ineffective against our poisoning attacks.
Event-Aided Time-to-Collision Estimation for Autonomous Driving
Predicting a potential collision with leading vehicles is an essential functionality of any autonomous/assisted driving system.
BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Stream
Our method can jointly learn both the implicit neural scene representation and recover the camera motion by minimizing the differences between the synthesized data and the real measurements without pre-computed camera poses from COLMAP.
SimTxtSeg: Weakly-Supervised Medical Image Segmentation with Simple Text Cues
Weakly-supervised medical image segmentation is a challenging task that aims to reduce the annotation cost while keep the segmentation performance.
RefXVC: Cross-Lingual Voice Conversion with Enhanced Reference Leveraging
This paper proposes RefXVC, a method for cross-lingual voice conversion (XVC) that leverages reference information to improve conversion performance.
Evaluating Short-Term Temporal Fluctuations of Social Biases in Social Media Data and Masked Language Models
Given that MLMs are continuously trained with increasing amounts of additional data collected over time, an important yet unanswered question is how the social biases encoded with MLMs vary over time.
Is Your HD Map Constructor Reliable under Sensor Corruptions?
These insights provide a pathway for developing more reliable HD map construction methods, which are essential for the advancement of autonomous driving technology.
Multi-Scale Accent Modeling and Disentangling for Multi-Speaker Multi-Accent Text-to-Speech Synthesis
However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS) systems is challenging due to the complex variations of accents and the inherent entanglement between speaker and accent identities.
BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
To address this issue, we introduce BLEnD, a hand-crafted benchmark designed to evaluate LLMs' everyday knowledge across diverse cultures and languages.
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
We demonstrate that our LRM-Zero, trained with our fully synthesized Zeroverse, can achieve high visual quality in the reconstruction of real-world objects, competitive with models trained on Objaverse.
Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
Specifically, existing studies show that AC converges to an $\epsilon+\varepsilon_{\text{critic}}$ neighborhood of stationary points with the best known sample complexity of $\mathcal{O}(\epsilon^{-2})$ (up to a log factor), and NAC converges to an $\epsilon+\varepsilon_{\text{critic}}+\sqrt{\varepsilon_{\text{actor}}}$ neighborhood of the global optimum with the best known sample complexity of $\mathcal{O}(\epsilon^{-3})$, where $\varepsilon_{\text{critic}}$ is the approximation error of the critic and $\varepsilon_{\text{actor}}$ is the approximation error induced by the insufficient expressive power of the parameterized policy class.
Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challenge
Leveraging this information, we propose a multi-modal UAV detection, classification, and 3D tracking method for accurate UAV classification and tracking.
MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise
Current fundus image analysis models are predominantly built for specific tasks relying on individual datasets.
Team Samsung-RAL: Technical Report for 2024 RoboDrive Challenge-Robust Map Segmentation Track
In this report, we describe the technical details of our submission to the 2024 RoboDrive Challenge Robust Map Segmentation Track.
BugBlitz-AI: An Intelligent QA Assistant
The evolution of software testing from manual to automated methods has significantly influenced quality assurance (QA) practices.
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles.
IMU-Aided Event-based Stereo Visual Odometry
In this paper, we improve our previous direct pipeline \textit{Event-based Stereo Visual Odometry} in terms of accuracy and efficiency.
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
Increasingly, code LLMs are being integrated into software development environments to improve the productivity of human programmers, and LLM-based agents are beginning to show promise for handling complex tasks autonomously.
DMesh: A Differentiable Mesh Representation
We present a differentiable representation, DMesh, for general 3D triangular meshes.
End-to-End Mesh Optimization of a Hybrid Deep Learning Black-Box PDE Solver
In this study, we explore the feasibility of end-to-end training of a hybrid model with a black-box PDE solver and a deep learning model for fluid flow prediction.
Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization
We prove that our algorithm finds an $\epsilon$-stationary point with a computational complexity of $\mathcal O(\epsilon^{-3k_*-5})$, where $k_*$ is the parameter of the Cressie-Read divergence.
Convergence Guarantees for RMSProp and Adam in Generalized-smooth Non-convex Optimization with Affine Noise Variance
Specifically, to solve the challenges due to dependence among adaptive update, unbounded gradient estimate and Lipschitz constant, we demonstrate that the first-order term in the descent lemma converges and its denominator is upper bounded by a function of gradient norm.
Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings
Sentence embeddings produced by Pretrained Language Models (PLMs) have received wide attention from the NLP community due to their superior performance when representing texts in numerous downstream applications.
HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction
Concretely, we introduce a hybrid representation called HIQuery to represent all map elements, and propose a point-element interactor to interactively extract and encode the hybrid information of elements, e. g. point position and element shape, into the HIQuery.
Transfer Learning-Enhanced Instantaneous Multi-Person Indoor Localization by CSI
Passive indoor localization, integral to smart buildings, emergency response, and indoor navigation, has traditionally been limited by a focus on single-target localization and reliance on multi-packet CSI.
Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes
Although large language models demonstrate emergent abilities in solving math word problems, there is a challenging task in complex multi-step mathematical reasoning tasks.
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
Large language models (LLMs) are displaying emergent abilities for math reasoning tasks, and there is a growing attention on enhancing the ability of open-source LLMs through supervised fine-tuning (SFT). In this paper, we aim to explore a general data strategy for supervised data to help optimize and expand math reasoning ability. Firstly, we determine the ability boundary of reasoning paths augmentation by identifying these paths' minimal optimal set. Secondly, we validate that different abilities of the model can be cumulatively enhanced by Mix of Minimal Optimal Sets of corresponding types of data, while our models MMOS achieve SOTA performance on series base models under much lower construction costs. Besides, we point out GSM-HARD is not really hard and today's LLMs no longer lack numerical robustness. Also, we provide an Auto Problem Generator for robustness testing and educational applications. Our code and data are publicly available at https://github. com/cyzhh/MMOS.
Ranked #2 on
Math Word Problem Solving
on ASDiv-A
(using extra training data)
Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives
Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems.
Multimodal-Enhanced Objectness Learner for Corner Case Detection in Autonomous Driving
Previous works on object detection have achieved high accuracy in closed-set scenarios, but their performance in open-world scenarios is not satisfactory.
Enhancing In-context Learning via Linear Probe Calibration
However, applying ICL in real cases does not scale with the number of samples, and lacks robustness to different prompt templates and demonstration permutations.
A Pure Integral-Type PLL with a Damping Branch to Enhance the Stability of Grid-Tied Inverter under Weak Grids
In a phase-locked loop (PLL) synchronized inverter, due to the strong nonlinear coupling between the PLL's parame-ters and the operation power angle, the equivalent damping coefficient will quickly deteriorate while the power angle is close to 90{\deg} under an ultra-weak grid, which causes the synchronous instability.
Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation
To address scale variation, we present a scale-enhanced consistency constraint, which ensures consistency in the segmentation maps generated from the same input image at different scales.
Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
To this end, we introduce Carve3D, an improved RLFT algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, to enhance the consistency of multi-view diffusion models.
Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks
Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs. It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs through poisoning attacks aimed at generating undesirable outputs.
Segment Anything Model-guided Collaborative Learning Network for Scribble-supervised Polyp Segmentation
Specifically, we first propose a Cross-level Enhancement and Aggregation Network (CEA-Net) for weakly-supervised polyp segmentation.
A Survey on Deep Learning for Polyp Segmentation: Techniques, Challenges and Future Trends
This paper provides a comprehensive review of polyp segmentation algorithms.
Scaling User Modeling: Large-scale Online User Representations for Ads Personalization in Meta
To address these challenges, we present Scaling User Modeling (SUM), a framework widely deployed in Meta's ads ranking system, designed to facilitate efficient and scalable sharing of online user representation across hundreds of ads models.
Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset
Since the dataset only involves a narrow range of knowledge, it is easy to separately analyse the knowledge a model possesses and the reasoning ability it has.
Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection
The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment network system (PNS) and its partner banks.
Single-shot General Hyper-parameter Optimization for Federated Learning
We address the problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO).
A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models
Various types of social biases have been reported with pretrained Masked Language Models (MLMs) in prior work.
Can Word Sense Distribution Detect Semantic Changes of Words?
Given this relationship between WSD and SCD, we explore the possibility of predicting whether a target word has its meaning changed between two corpora collected at different time steps, by comparing the distributions of senses of that word in each corpora.
Study on the Time Domain Precision Evolution Mechanism of CNC Machine Tool Feed Systems Based on Acceleration and Deceleration Capability Indicator
This paper innovatively proposes the need to consider the coupling effects among subsystems, directing the optimization design of CNC machine tool feed systems towards time domain dynamic precision.
Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic Enhancement
The effectiveness of text-based methods largely hinges on the quality and richness of the training data.
Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
To address these issues, we propose a novel Memory-Assisted Sub-Prototype Mining (MemSPM) method that can learn the differences between samples belonging to the same category and mine sub-classes when there exists significant concept shift between them.
Super Denoise Net: Speech Super Resolution with Noise Cancellation in Low Sampling Rate Noisy Environments
Speech super-resolution (SSR) aims to predict a high resolution (HR) speech signal from its low resolution (LR) corresponding part.
A Tutorial on Uniform B-Spline
This document facilitates understanding of core concepts about uniform B-spline and its matrix representation.
Edge-aware Feature Aggregation Network for Polyp Segmentation
Besides, a Scale-aware Convolution Module (SCM) is proposed to learn scale-aware features by using dilated convolutions with different ratios, in order to effectively deal with scale variation.
GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency
In contrast, we introduce GRIP, a learning-based method that takes, as input, the 3D motion of the body and the object, and synthesizes realistic motion for both hands before, during, and after object interaction.
COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation
SF-UniDA methods eliminate the need for direct access to source samples when performing adaptation to the target domain.
Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
Our approach succeeds in performance while significantly saving inference steps.
Boosting Multi-modal Model Performance with Adaptive Gradient Modulation
In addition, we find that the jointly trained model typically has a preferred modality on which the competition is weaker than other modalities.
Fast Maximum $k$-Plex Algorithms Parameterized by Small Degeneracy Gaps
We define a novel parameter of the input instance, $g_k(G)$, the gap between the degeneracy bound and the size of the maximum $k$-plex in the given graph, and present an exact algorithm parameterized by this $g_k(G)$, which has a worst-case running time polynomial in the size of the input graph and exponential in $g_k(G)$.
Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement
By combining the DPRNN module with Convolution Recurrent Network (CRN), the DPCRN obtained a promising performance in speech separation with a limited model size.
Together We Make Sense -- Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddings
Our proposed method can combine source sense embeddings that cover different sets of word senses.
An Efficient Multilingual Language Model Compression through Vocabulary Trimming
Multilingual language model (LM) have become a powerful tool in NLP especially for non-English languages.
Solving Cosine Similarity Underestimation between High Frequency Words by L2 Norm Discounting
This similarity underestimation problem is particularly severe for highly frequent words.
Accented Text-to-Speech Synthesis with Limited Data
Both objective and subjective evaluation results show that the accented TTS front-end fine-tuned with a small accented phonetic lexicon (5k words) effectively handles the phonetic variation of accents, while the accented TTS acoustic model fine-tuned with a limited amount of accented speech data (approximately 3 minutes) effectively improves the prosodic rendering including pitch and duration.
Dual Residual Attention Network for Image Denoising
The proposed DRANet includes two different parallel branches, which can capture complementary features to enhance the learning ability of the model.
Ranked #1 on
Image Denoising
on SIDD
(Average PSNR metric)
LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
As part of the training, the parties wish to remove unimportant features in the system to improve generalization, efficiency, and explainability.
Can SAM Segment Polyps?
Recently, Meta AI Research releases a general Segment Anything Model (SAM), which has demonstrated promising performance in several segmentation tasks.
Edge-cloud Collaborative Learning with Federated and Centralized Features
Federated learning (FL) is a popular way of edge computing that doesn't compromise users' privacy.
Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification
Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies.
DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior
To handle this, we propose a new RGB-NIR fusion algorithm called Dark Vision Net (DVN) with two technical novelties: Deep Structure and Deep Inconsistency Prior (DIP).
Normal-guided Garment UV Prediction for Human Re-texturing
To edit human videos in a physically plausible way, a texture map must take into account not only the garment transformation induced by the body movements and clothes fitting, but also its 3D fine-grained surface geometry.
Self-Paced Learning for Open-Set Domain Adaptation
Open-set domain adaptation aims to not only recognize target samples belonging to common classes shared by source and target domains but also perceive unknown class samples.
Structure-informed Language Models Are Protein Designers
This paper demonstrates that language models are strong structure-based protein designers.
TTS-Guided Training for Accent Conversion Without Parallel Data
Specifically, a text-to-speech (TTS) system is first pretrained with target-accented speech data.
Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence
We attribute this deficiency to the lack of ability to extract the spatial configuration of visual feature layouts and models' overfitting on low-level details from the training set.
Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis
To take advantage of both paired and unpaired data, in this paper, we propose a Multi-scale Transformer Network (MT-Net) with edge-aware pre-training for cross-modality MR image synthesis.
Feature Aggregation and Propagation Network for Camouflaged Object Detection
In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection.
Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA
Natural language is ambiguous.
On the Curious Case of $\ell_2$ norm of Sense Embeddings
We show that the $\ell_2$ norm of a static sense embedding encodes information related to the frequency of that sense in the training corpus used to learn the sense embeddings.
PARAGEN : A Parallel Generation Toolkit
PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation.
Finite-Time Error Bounds for Greedy-GQ
Our finite-time error bounds match with one of the stochastic gradient descent algorithms for general smooth non-convex optimization problems, despite its additonal challenge in the two time-scale updates.
Federated XGBoost on Sample-Wise Non-IID Data
Federated Learning (FL) is a paradigm for jointly training machine learning algorithms in a decentralized manner which allows for parties to communicate with an aggregator to create and train a model, without exposing the underlying raw data distribution of the local parties involved in the training process.
Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation
We then generate prompts by filling manually compiled templates using the extracted pivot and anchor terms.
Learning Visibility for Robust Dense Human Body Estimation
An alternative approach is to estimate dense vertices of a predefined template body in the image space.
A Repulsive Force Unit for Garment Collision Handling in Neural Networks
Despite recent success, deep learning-based methods for predicting 3D garment deformation under body motion suffer from interpenetration problems between the garment and the body.
NeMF: Neural Motion Fields for Kinematic Animation
We present an implicit neural representation to learn the spatio-temporal space of kinematic motions.
3D-VFD: A Victim-free Detector against 3D Adversarial Point Clouds
3D deep models consuming point clouds have achieved sound application effects in computer vision.
DDDM: a Brain-Inspired Framework for Robust Classification
The mechanism is well described by the Drift-Diffusion Model (DDM).
SHAPE: An Unified Approach to Evaluate the Contribution and Cooperation of Individual Modalities
Our experiments suggest that for some tasks where different modalities are complementary, the multi-modal models still tend to use the dominant modality alone and ignore the cooperation across modalities.
Data Sampling Affects the Complexity of Online SGD over Dependent Data
Moreover, we show that online SGD with mini-batch sampling can further substantially improve the sample complexity over online SGD with periodic data-subsampling over highly dependent data.
A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization
In this work, we study a proximal gradient-type algorithm that adopts the approximate implicit differentiation (AID) scheme for nonconvex bi-level optimization with possibly nonconvex and nonsmooth regularizers.
Delving into the Estimation Shift of Batch Normalization in a Network
We define the estimation shift magnitude of BN to quantitatively measure the difference between its estimated population statistics and expected ones.
Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word.
Extended Load Flexibility of Industrial P2H Plants: A Process Constraint-Aware Scheduling Approach
The operational flexibility of industrial power-to-hydrogen (P2H) plants enables admittance of volatile renewable power and provides auxiliary regulatory services for the power grid.
Listing Maximal k-Plexes in Large Real-World Graphs
Our first contribution is algorithm ListPlex that lists all maximal $k$-plexes in $O^*(\gamma^D)$ time for each constant $k$, where $\gamma$ is a value related to $k$ but strictly smaller than 2, and $D$ is the degeneracy of the graph that is far less than the vertex number $n$ in real-word graphs.
Single-shot Hyper-parameter Optimization for Federated Learning: A General Algorithm & Analysis
We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO).
On Unbalanced Optimal Transport: Gradient Methods, Sparsity and Approximation Error
In this paper, we propose a novel algorithm based on Gradient Extrapolation Method (GEM-UOT) to find an $\varepsilon$-approximate solution to the UOT problem in $O\big( \kappa \log\big(\frac{\tau n}{\varepsilon}\big) \big)$ iterations with $\widetilde{O}(n^2)$ per-iteration cost, where $\kappa$ is the condition number depending on only the two input measures.
Coordinated Frequency Control through Safe Reinforcement Learning
With widespread deployment of renewables, the electric power grids are experiencing increasing dynamics and uncertainties, with its secure operation being threatened.
Accelerated Proximal Alternating Gradient-Descent-Ascent for Nonconvex Minimax Machine Learning
Alternating gradient-descent-ascent (AltGDA) is an optimization algorithm that has been widely used for model training in various machine learning applications, which aims to solve a nonconvex minimax optimization problem.
Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation
We encode all panoptic entities in a video, including both foreground instances and background semantics, with a unified representation called panoptic slots.
FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning
We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO).
Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks
Despite its great success, deep learning severely suffers from robustness; that is, deep neural networks are very vulnerable to adversarial attacks, even the simplest ones.
Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting
In this paper, we present a cascaded two-level multi-model fitting method for identifying independently moving objects (i. e., the motion segmentation problem) with a monocular event camera.
A Cubic Regularization Approach for Finding Local Minimax Points in Nonconvex Minimax Optimization
However, GDA has been proved to converge to stationary points for nonconvex minimax optimization, which are suboptimal compared with local minimax points.
Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy
Contextualised word embeddings generated from Neural Language Models (NLMs), such as BERT, represent a word with a vector that considers the semantics of the target word as well its context.
How to Improve Sample Complexity of SGD over Highly Dependent Data?
Specifically, with a $\phi$-mixing model that captures both exponential and polynomial decay of the data dependence over time, we show that SGD with periodic data-subsampling achieves an improved sample complexity over the standard SGD in the full spectrum of the $\phi$-mixing data dependence.
Escaping Saddle Points in Nonconvex Minimax Optimization via Cubic-Regularized Gradient Descent-Ascent
Our result shows that Cubic-GDA achieves an orderwise faster convergence rate than the standard GDA for a wide spectrum of gradient dominant geometry.
Sample Efficient Stochastic Policy Extragradient Algorithm for Zero-Sum Markov Game
Two-player zero-sum Markov game is a fundamental problem in reinforcement learning and game theory.
The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation.
Assisted Learning for Organizations with Limited Imbalanced Data
In this work, we develop an assisted learning framework for assisting organizations to improve their learning performance.
Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis
Actor-critic (AC) algorithms have been widely adopted in decentralized multi-agent systems to learn the optimal joint control policy.
Stochastic Scene-Aware Motion Prediction
A long-standing goal in computer vision is to capture, model, and realistically synthesize human behavior.
Specificity-preserving RGB-D Saliency Detection
To effectively fuse cross-modal features in the shared learning network, we propose a cross-enhanced integration module (CIM) and then propagate the fused feature to the next layer for integrating cross-level information.
Ranked #2 on
Object Detection
on PKU-DDD17-Car
Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble
Although deep neural networks have achieved prominent performance on many NLP tasks, they are vulnerable to adversarial examples.
LEGATO: A LayerwisE Gradient AggregaTiOn Algorithm for Mitigating Byzantine Attacks in Federated Learning
This global model can be corrupted when Byzantine workers send malicious gradients, which necessitates robust methods for aggregating gradients that mitigate the adverse effects of Byzantine inputs.
Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection
The learned AU semantic embeddings are then used as guidance for the generation of attention maps through a cross-modality attention network.
using multiple losses for accurate facial age estimation
Age estimation is an essential challenge in computer vision.
Improving Entity Linking through Semantic Reinforced Entity Embeddings
We propose a simple yet effective method, FGS2EE, to inject fine-grained semantic information into entity embeddings to reduce the distinctiveness and facilitate the learning of contextual commonality.
Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation
Temporal-difference learning with gradient correction (TDC) is a two time-scale algorithm for policy evaluation in reinforcement learning.
Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
Federated learning is an emerging data-private distributed learning framework, which, however, is vulnerable to adversarial attacks.
Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity
Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control.
Multi-Agent Off-Policy TD Learning: Finite-Time Analysis with Near-Optimal Sample Complexity and Communication Complexity
Under Markovian sampling and linear function approximation, we proved that the finite-time sample complexity of both algorithms for achieving an $\epsilon$-accurate solution is in the order of $\mathcal{O}(\epsilon^{-1}\ln \epsilon^{-1})$, matching the near-optimal sample complexity of centralized TD(0) and TDC.
FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Data
We empirically demonstrate the applicability for multiple types of ML models and show a reduction of 10%-70% of training time and 80% to 90% in data transfer with respect to the state-of-the-art approaches.
A Deep Emulator for Secondary Motion of 3D Characters
Being a local method, our network is independent of the mesh topology and generalizes to arbitrarily shaped 3D character meshes at test time.
Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming.
Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry
By leveraging this Lyapunov function and the K{\L} geometry that parameterizes the local geometries of general nonconvex functions, we formally establish the variable convergence of proximal-GDA to a critical point $x^*$, i. e., $x_t\to x^*, y_t\to y^*(x^*)$.
Global existence for semilinear wave equations with scaling invariant damping in 3-D
Global existence for small data Cauchy problem of semilinear wave equations with scaling invariant damping in 3-D is established in this work, assuming that the data are radial and the constant in front of the damping belongs to $[1. 5, 2)$.
Analysis of PDEs
Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning
Data heterogeneity has been identified as one of the key features in federated learning but often overlooked in the lens of robustness to adversarial attacks.
Visual-Textual Attentive Semantic Consistency for Medical Report Generation
Second, the progressive report decoder consists of a sentence decoder and a word decoder, where we propose image-sentence matching and description accuracy losses to constrain the visual-textual semantic consistency.
CCT-Net: Category-Invariant Cross-Domain Transfer for Medical Single-to-Multiple Disease Diagnosis
A category-invariant cross-domain transfer (CCT) method is proposed to address this single-to-multiple extension.
Enhancing Balanced Graph Edge Partition with Effective Local Search
The graph edge partition problem, which is to split the edge set into multiple balanced parts to minimize the total number of copied vertices, has been widely studied from the view of optimization and algorithms.
Event-based Motion Segmentation with Spatio-Temporal Graph Cuts
We develop a method to identify independently moving objects acquired with an event-based camera, i. e., to solve the event-based motion segmentation problem.
Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment
The present paper reviews the classical problem of free-form curve registration and applies it to an efficient RGBD visual odometry system called Canny-VO, as it efficiently tracks all Canny edge features extracted from the images.
Adaptive Histogram-Based Gradient Boosted Trees for Federated Learning
This approach makes the use of gradient boosted trees practical in enterprise federated learning.
Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation
We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths, which can be used for training more accurate segmentation models.
Ranked #38 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
(using extra training data)
Mitigating Bias in Federated Learning
As methods to create discrimination-aware models develop, they focus on centralized ML, leaving federated learning (FL) unexplored.
A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning
Using this framework, we show that space-filling sample designs, such as blue noise and Poisson disk sampling, which optimize spectral properties, outperform random designs in terms of the generalization gap and characterize this gain in a closed-form.
Multimodal Learning for Hateful Memes Detection
Memes are used for spreading ideas through social networks.
Contrastive Weight Regularization for Large Minibatch SGD
The minibatch stochastic gradient descent method (SGD) is widely applied in deep learning due to its efficiency and scalability that enable training deep networks with a large volume of data.
On the Transferability of Adversarial Attacksagainst Neural Text Classifier
Based on these studies, we propose a genetic algorithm to find an ensemble of models that can be used to induce adversarial examples to fool almost all existing models.
Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study
Specifically, we find that the optimization trajectories of successful DNN trainings consistently obey a certain regularity principle that regularizes the model update direction to be aligned with the trajectory direction.
Cross-Lingual Dependency Parsing by POS-Guided Word Reordering
The words in each sentence of a source language corpus are rearranged to meet the word order in a target language under the guidance of a part-of-speech based language model (LM).
Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis
In the Markovian setting, our algorithm achieves the state-of-the-art sample complexity $O(\epsilon^{-1} \log {\epsilon}^{-1})$ that is near-optimal.
Boosting One-Point Derivative-Free Online Optimization via Residual Feedback
As a result, our regret bounds are much tighter compared to existing regret bounds for ZO with conventional one-point feedback, which suggests that ZO with residual feedback can better track the optimizer of online optimization problems.
UNISON: Unpaired Cross-lingual Image Captioning
In this work, we present a novel unpaired cross-lingual method to generate image captions without relying on any caption corpus in the source or the target language.
Group Whitening: Balancing Learning Efficiency and Representational Capacity
Results show that GW consistently improves the performance of different architectures, with absolute gains of $1. 02\%$ $\sim$ $1. 49\%$ in top-1 accuracy on ImageNet and $1. 82\%$ $\sim$ $3. 21\%$ in bounding box AP on COCO.
Normalization Techniques in Training DNNs: Methodology, Analysis and Application
Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications.
FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling
We develop FedCluster--a novel federated learning framework with improved optimization efficiency, and investigate its theoretical convergence properties.
Exploring the Hierarchy in Relation Labels for Scene Graph Generation
By assigning each relationship a single label, current approaches formulate the relationship detection as a classification problem.
Small-floating Target Detection in Sea Clutter via Visual Feature Classifying in the Time-Doppler Spectra
It is challenging to detect small-floating object in the sea clutter for a surface radar.
A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability
This dataset has 1, 842 images with pixel-level DR-related lesion annotations, and 1, 000 images with image-level labels graded by six board-certified ophthalmologists with intra-rater consistency.
Learning to Generate Diverse Dance Motions with Transformer
We also introduce new evaluation metrics for the quality of synthesized dance motions, and demonstrate that our system can outperform state-of-the-art methods.
Spatio-temporal Attention Model for Tactile Texture Recognition
Recently, tactile sensing has attracted great interest in robotics, especially for facilitating exploration of unstructured environments and effective manipulation.
Event-based Stereo Visual Odometry
We present a solution to the problem of visual odometry from the data acquired by a stereo event-based camera rig.
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume.
Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle
Specifically, minimizer incoherence measures the discrepancy between the global minimizers of a sample loss and those of the total loss and affects the convergence error of SGD with random reshuffle.
Evaluating and Enhancing the Robustness of Neural Network-based Dependency Parsing Models with Adversarial Examples
Despite achieving prominent performance on many important tasks, it has been reported that neural networks are vulnerable to adversarial examples.
Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
Despite neural networks have achieved prominent performance on many natural language processing (NLP) tasks, they are vulnerable to adversarial examples.
A New One-Point Residual-Feedback Oracle For Black-Box Learning and Control
When optimizing a deterministic Lipschitz function, we show that the query complexity of ZO with the proposed one-point residual feedback matches that of ZO with the existing two-point schemes.
Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels
Learning latent representations of registered meshes is useful for many 3D tasks.
