Search Results for author:
Found 115 papers, 56 papers with code
Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph
Chinese pre-trained language models usually exploit contextual character information to learn representations, while ignoring the linguistics knowledge, e. g., word and sentence information.
NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains.
Cross-Domain Few-Shot
Cross-Domain Few-Shot Object Detection
+3
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
To address this issue, we investigate the internal reasoning structures of LLMs and categorize them into three primary thought types: execution, reflection, and transition thoughts.
Cross-Frame OTFS Parameter Estimation Based On Chinese Remainder Theorem
By designing co-prime numbers of subcarriers and time slots in different subframes, the difference in the responses of the subframes for a target can be used to estimate the distance and velocity of an out-of-range target.
Follow Your Motion: A Generic Temporal Consistency Portrait Editing Framework with Trajectory Guidance
However, they often face challenges with temporal consistency, particularly in the talking head domain, where continuous changes in facial expressions intensify the level of difficulty.
Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization
Multimodal Large Language Models excel in various tasks, yet often struggle with modality bias, where the model tends to rely heavily on a single modality and overlook critical information in other modalities, which leads to incorrect focus and generating irrelevant responses.
Time-EAPCR: A Deep Learning-Based Novel Approach for Anomaly Detection Applied to the Environmental Field
As human activities intensify, environmental systems such as aquatic ecosystems and water treatment systems face increasingly complex pressures, impacting ecological balance, public health, and sustainable development, making intelligent anomaly monitoring essential.
Inorganic Catalyst Efficiency Prediction Based on EAPCR Model: A Deep Learning Solution for Multi-Source Heterogeneous Data
The design of inorganic catalysts and the prediction of their catalytic efficiency are fundamental challenges in chemistry and materials science.
Unsupervised Waste Classification By Dual-Encoder Contrastive Learning and Multi-Clustering Voting (DECMCV)
On a real-world dataset of 4, 169 waste images, only 50 labeled samples were needed to accurately label thousands, improving classification accuracy by 29. 85% compared to supervised models.
Stable-SPAM: How to Train in 4-Bit More Stably than 16-Bit Adam
This paper comprehensively evaluates several recently proposed optimizers for 4-bit training, revealing that low-bit precision amplifies sensitivity to learning rates and often causes unstable gradient norms, leading to divergence at higher learning rates.
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
Large language models (LLMs) face inherent performance bottlenecks under parameter constraints, particularly in processing critical tokens that demand complex reasoning.
BeamLoRA: Beam-Constraint Low-Rank Adaptation
Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods.
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
To address this, we propose Mask-Enhanced Autoregressive Prediction (MEAP), a simple yet effective training paradigm that seamlessly integrates Masked Language Modeling (MLM) into Next-Token Prediction (NTP) to enhance the latter's in-context retrieval capabilities.
STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution
Image diffusion models have been adapted for real-world video super-resolution to tackle over-smoothing issues in GAN-based methods.
EasySplat: View-Adaptive Learning makes 3D Gaussian Splatting Easy
In this way, the proposed method tackles the limitation on initialization and optimization, leading to an efficient and accurate 3DGS modeling.
Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking
These temporal information tokens are used to guide the localization of the target in the next time state, establish long-range contextual relationships between video frames, and capture the temporal trajectory of the target.
Ranked #4 on
Rgb-T Tracking
on LasHeR
StrandHead: Text to Strand-Disentangled 3D Head Avatars Using Hair Geometric Priors
We propose StrandHead, a novel text to 3D head avatar generation method capable of generating disentangled 3D hair with strand representation.
OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation
As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing.
Learning to Decouple the Lights for 3D Face Texture Modeling
According to experiments on both single images and video sequences, we demonstrate the effectiveness of our approach in modeling facial textures under challenging illumination affected by occlusions.
APOLLO: SGD-like Memory, AdamW-level Performance
This memory burden necessitates using more or higher-end GPUs or reducing batch sizes, limiting training scalability and throughput.
Data Uncertainty-Aware Learning for Multimodal Aspect-based Sentiment Analysis
And in the real world, the quality of data usually varies for different samples, such noise is called data uncertainty.
ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidance
In this paper, we propose ConsistentAvatar, a novel framework for fully consistent and high-fidelity talking avatar generation.
Responsible AI in Construction Safety: Systematic Evaluation of Large Language Models and Prompt Engineering
Construction remains one of the most hazardous sectors.
EAPCR: A Universal Feature Extractor for Scientific Data without Explicit Feature Relation Patterns
The absence of explicit Feature Relation Patterns (FRPs) presents a significant challenge for deep learning techniques in scientific applications that are not image, text, and graph-based.
MoR: Mixture of Ranks for Low-Rank Adaptation Tuning
Low-Rank Adaptation (LoRA) drives research to align its performance with full fine-tuning.
Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots
In addition, we organize and propose a dehaze dataset for robotic vision in urological surgery (USRobot-Dehaze dataset).
Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
To ensure that each specialized expert in the MoE model works as expected, we select a small amount of seed data that each expert excels to pre-optimize the router.
Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition
Few-shot open-set recognition (FSOR) is a challenging task that requires a model to recognize known classes and identify unknown classes with limited labeled data.
MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems.
Barbie: Text to Barbie-Style 3D Avatars
In this paper, we propose Barbie, a novel framework for generating 3D avatars that can be dressed in diverse and high-quality Barbie-like garments and accessories.
NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time
Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows.
LoginMEA: Local-to-Global Interaction Network for Multi-modal Entity Alignment
Other studies refine each uni-modal information with graph structures, but may introduce unnecessary relations in specific modalities.
Predicting T-Cell Receptor Specificity
The result proves that adding a classifier to the model based on the random forest algorithm is very effective, and our model generally outperforms ordinary deep learning methods.
From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients
Modern Large Language Models (LLMs) are composed of matrices with billions of elements, making their storage and processing quite demanding in terms of computational resources and memory usage.
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients
To address these limitations, we introduce Q-Galore, a novel approach that substantially reduces memory usage by combining quantization and low-rank projection, surpassing the benefits of GaLore.
A Survey on Failure Analysis and Fault Injection in AI Systems
Moreover, this survey contributes to the field by providing a framework for fault diagnosis, evaluating the state-of-the-art in FI, and identifying areas for improvement in FI techniques to enhance the resilience of AI systems.
Healing Powers of BERT: How Task-Specific Fine-Tuning Recovers Corrupted Language Models
Language models like BERT excel at sentence classification tasks due to extensive pre-training on general data, but their robustness to parameter corruption is unexplored.
E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models
Most large language models (LLMs) are sensitive to prompts, and another synonymous expression or a typo may lead to unexpected results for the model.
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
Large language models (LLMs) with billions of parameters demonstrate impressive performance.
Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding
This framework is designed to perform understanding tasks for any 3D scene without requiring prior knowledge of the scene.
Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation
In this framework, each agent is specialized in a distinct aspect, such as foreground understanding, diversity enhancement, object integrity protection, and textual prompt consistency.
HFT: Half Fine-Tuning for Large Language Models
Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences.
Pathology-genomic fusion via biologically informed cross-modality graph learning for survival analysis
The PGHG consists of biological knowledge-guided representation learning network and pathology-genome heterogeneous graph.
AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation
Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs.
Deepfake Generation and Detection: A Benchmark and Survey
Deepfake is a technology dedicated to creating highly realistic facial images and videos under specific conditions, which has significant application potential in fields such as entertainment, movie production, digital human creation, to name a few.
Invertible Diffusion Models for Compressed Sensing
To enable such memory-intensive end-to-end fine-tuning, we propose a novel two-level invertible design to transform both (1) multi-step sampling process and (2) noise estimation U-Net in each step into invertible networks.
Tri-Perspective View Decomposition for Geometry-Aware Depth Completion
Depth completion is a vital task for autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements.
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Our approach reduces memory usage by up to 65. 5% in optimizer states while maintaining both efficiency and performance for pre-training on LLaMA 1B and 7B architectures with C4 dataset with up to 19. 7B tokens, and on fine-tuning RoBERTa on GLUE tasks.
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
To address this problem, this paper introduces Multi-scale Positional Encoding (Ms-PoE) which is a simple yet effective plug-and-play approach to enhance the capacity of LLMs to handle the relevant information located in the middle of the context, without fine-tuning or introducing any additional overhead.
Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability
In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
Many computational factors limit broader deployment of large language models.
Demystifying Chains, Trees, and Graphs of Thoughts
Among these, prompt engineering coupled with structures has emerged as a promising paradigm, with designs such as Chain-of-Thought, Tree of Thoughts, or Graph of Thoughts, in which the overall LLM reasoning is guided by a structure such as a graph.
QuantumSEA: In-Time Sparse Exploration for Noise Adaptive Quantum Circuits
To address these two pain points, we propose QuantumSEA, an in-time sparse exploration for noise-adaptive quantum circuits, aiming to achieve two key objectives: (1) implicit circuits capacity during training - by dynamically exploring the circuit's sparse connectivity and sticking a fixed small number of quantum gates throughout the training which satisfies the coherence time and enjoy light noises, enabling feasible executions on real quantum devices; (2) noise robustness - by jointly optimizing the topology and parameters of quantum circuits under real device noise models.
Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention
Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains.
FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity
The widespread of generative artificial intelligence has heightened concerns about the potential harms posed by AI-generated texts, primarily stemming from factoid, unfair, and toxic content.
Simple but Effective Unsupervised Classification for Specified Domain Images: A Case Study on Fungi Images
Addressing this, an unsupervised classification method with three key ideas is introduced: 1) dual-step feature dimensionality reduction using a pre-trained model and manifold learning, 2) a voting mechanism from multiple clustering algorithms, and 3) post-hoc instead of prior manual annotation.
Sam-Guided Enhanced Fine-Grained Encoding with Mixed Semantic Learning for Medical Image Captioning
With the development of multimodality and large language models, the deep learning-based technique for medical image captioning holds the potential to offer valuable diagnostic recommendations.
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge when it comes to practical deployment due to their colossal model size.
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks, however, they have issues like (a) High Memory Usage, due to duplication of the network layers into multiple copies as experts; and (b) Redundancy in Experts, as common learning-based routing policies suffer from representational collapse.
JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention
We propose Joint MLP/Attention (JoMA) dynamics, a novel mathematical framework to understand the training procedure of multilayer Transformer architectures.
A study on the impact of pre-trained model on Just-In-Time defect prediction
These findings emphasize the effectiveness of transformer-based pre-trained models in JIT defect prediction tasks, especially in scenarios with limited training data.
RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion
To tackle these challenges, we explore a repetitive design in our image guided network to gradually and sufficiently recover depth values.
AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization
Neural Radiance Fields (NeRF) have shown promise in generating realistic novel views from sparse scene images.
MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling
Estimating 3D human poses only from a 2D human pose sequence is thoroughly explored in recent years.
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Based on these insights, we propose Heavy Hitter Oracle (H$_2$O), a KV cache eviction policy that dynamically retains a balance of recent and H$_2$ tokens.
Variable Radiance Field for Real-Life Category-Specifc Reconstruction from Single Image
Our key contributions are: (1) We parameterize the geometry and appearance of the object using a multi-scale global feature extractor, which avoids frequent point-wise feature retrieval and camera dependency.
Are Large Kernels Better Teachers than Transformers for ConvNets?
We hereby carry out a first-of-its-kind study unveiling that modern large-kernel ConvNets, a compelling competitor to Vision Transformers, are remarkably more effective teachers for small-kernel ConvNets, due to more similar architectures.
Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution
Multi-stage strategies are frequently employed in image restoration tasks.
OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution
Model A aims to enhance the feature extraction ability of 360{\deg} image positional information, while Model B further focuses on the high-frequency information of 360{\deg} images.
Learning Versatile 3D Shape Generation with Improved AR Models
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space.
Graph Transformer GANs for Graph-Constrained House Generation
We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task.
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
In pursuit of a more general evaluation and unveiling the true potential of sparse algorithms, we introduce "Sparsity May Cry" Benchmark (SMC-Bench), a collection of carefully-curated 4 diverse tasks with 10 datasets, that accounts for capturing a wide range of domain-specific and sophisticated knowledge.
Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
Despite their remarkable achievement, gigantic transformers encounter significant drawbacks, including exorbitant computational and memory footprints during training, as well as severe collapse evidenced by a high degree of parameter redundancy.
Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
Given a robust model trained to be resilient to one or multiple types of distribution shifts (e. g., natural image corruptions), how is that "robustness" encoded in the model weights, and how easily can it be disentangled and/or "zero-shot" transferred to some other models?
Learning Neural Proto-Face Field for Disentangled 3D Face Modeling in the Wild
To address this problem, this paper presents a novel Neural Proto-face Field (NPF) for unsupervised robust 3D face modeling.
Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space
Specifically, we use the contrastive constraint to help CALoss learn a representation space with shape similarity, while we introduce the adversarial strategy to help CALoss mine differences between reconstructed results and ground truths.
Learning Versatile 3D Shape Generation with Improved Auto-regressive Models
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space.
Towards Generalized Open Information Extraction
Open Information Extraction (OpenIE) facilitates the open-domain discovery of textual facts.
DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion
Unsupervised depth completion aims to recover dense depth from the sparse one without using the ground-truth annotation.
QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks
Quantum neural networks (QNNs), an interdisciplinary field of quantum computing and machine learning, have attracted tremendous research interests due to the specific quantum advantages.
Sparse Winning Tickets are Data-Efficient Image Recognizers
Improving the performance of deep networks in data-limited regimes has warranted much attention.
ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts
Recent progress in diffusion models has revolutionized the popular technology of text-to-image generation.
Ranked #12 on
Text-to-Image Generation
on MS COCO
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding.
Ranked #2 on
Semantic entity labeling
on FUNSD
An Efficient End-to-End Transformer with Progressive Tri-modal Attention for Multi-modal Emotion Recognition
At the low-level, we propose the progressive tri-modal attention, which can model the tri-modal feature interactions by adopting a two-pass strategy and can further leverage such interactions to significantly reduce the computation and memory complexity through reducing the input token length.
Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration
In this paper, we propose a Layout-aware document-level Information Extraction dataset, LIE, to facilitate the study of extracting both structural and semantic knowledge from visually rich documents (VRDs), so as to generate accurate responses in dialogue systems.
Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness
Certifiable robustness is a highly desirable property for adopting deep neural networks (DNNs) in safety-critical scenarios, but often demands tedious computations to establish.
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
For example, on downstream CIFAR-10/100 datasets, we identify double-win matching subnetworks with the standard, fast adversarial, and adversarial pre-training from ImageNet, at 89. 26%/73. 79%, 89. 26%/79. 03%, and 91. 41%/83. 22% sparsity, respectively.
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free
Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a particular trigger.
Label Anchored Contrastive Learning for Language Understanding
Motivated by this, we propose a novel label anchored contrastive learning approach (denoted as LaCon) for language understanding.
Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion
To deal with the PDC task, we train a deep network that takes both depth and image as inputs for the dense panoramic depth recovery.
The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy
However, a "head-to-toe assessment" regarding the extent of redundancy in ViTs, and how much we could gain by thoroughly mitigating such, has been absent for this field.
Sparsity Winning Twice: Better Robust Generalization from More Efficient Training
We introduce two alternatives for sparse adversarial training: (i) static sparsity, by leveraging recent results from the lottery ticket hypothesis to identify critical sparse subnetworks arising from the early training; (ii) dynamic sparsity, by allowing the sparse subnetwork to adaptively adjust its connectivity pattern (while sticking to the same sparsity ratio) throughout training.
ASFD: Automatic and Scalable Face Detector
Along with current multi-scale based detectors, Feature Aggregation and Enhancement (FAE) modules have shown superior performance gains for cutting-edge object detection.
Ranked #1 on
Face Detection
on WIDER Face (Medium)
Physically-Guided Disentangled Implicit Rendering for 3D Face Modeling
This paper presents a novel Physically-guided Disentangled Implicit Rendering (PhyDIR) framework for high-fidelity 3D face modeling.
Learning To Restore 3D Face From In-the-Wild Degraded Images
In-the-wild 3D face modelling is a challenging problem as the predicted facial geometry and texture suffer from a lack of reliable clues or priors, when the input images are degraded.
You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership
The lottery ticket hypothesis (LTH) emerges as a promising framework to leverage a special sparse subnetwork (i. e., winning ticket) instead of a full model for both training and inference, that can lower both costs without sacrificing the performance.
FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection
As increasing development of text-to-speech (TTS) and voice conversion (VC) technologies, the detection of synthetic speech has been suffered dramatically.
Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning
Distantly supervised named entity recognition (DS-NER) efficiently reduces labor costs but meanwhile intrinsically suffers from the label noise due to the strong assumption of distant supervision.
MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features
To realize any-to-any (A2A) voice conversion (VC), most methods are to perform symmetric self-supervised reconstruction tasks (Xi to Xi), which usually results in inefficient performances due to inadequate feature decoupling, especially for unseen speakers.
DialogueBERT: A Self-Supervised Learning based Dialogue Pre-training Encoder
DialogueBERT was pre-trained with 70 million dialogues in real scenario, and then fine-tuned in three different downstream dialogue understanding tasks.
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
Monocular depth estimation aims at predicting depth from a single image or video.
RigNet: Repetitive Image Guided Network for Depth Completion
However, blurry guidance in the image and unclear structure in the depth still impede the performance of the image guided frameworks.
Ranked #2 on
Depth Completion
on KITTI Depth Completion
Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection
Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions.
Efficient Lottery Ticket Finding: Less Data is More
We observe that a high-quality winning ticket can be found with training and pruning the dense network on the very compact PrAC set, which can substantially save training iterations for the ticket finding process.
GANs Can Play Lottery Tickets Too
In this work, we for the first time study the existence of such trainable matching subnetworks in deep GANs.
Decentralized Baseband Processing with Gaussian Message Passing Detection for Uplink Massive MU-MIMO Systems
Decentralized baseband processing (DBP) architecture, which partitions the base station antennas into multiple antenna clusters, has been recently proposed to alleviate the excessively high interconnect bandwidth, chip input/output data rates, and detection complexity for massive multi-user multiple-input multiple-output (MU-MIMO) systems.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle for the efficient implementation of BNN training.
Ranked #179 on
Image Classification
on CIFAR-100
Hydrogen-assisted layer-by-layer growth and robust nontrivial topology of stanene films on Bi(111)
The atomistic growth mechanisms and nontrivial topology of stanene as presented here are also discussed in connection with recent experimental findings.
Materials Science
Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning
In view of those, we introduce two pruning options, e. g., top-down and bottom-up, for finding lifelong tickets.
Robust Overfitting may be mitigated by properly learned smoothening
A recent study (Rice et al., 2020) revealed overfitting to be a dominant phenomenon in adversarially robust training of deep networks, and that appropriate early-stopping of adversarial training (AT) could match the performance gains of most recent algorithmic improvements.
Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction
Dependency trees have been shown to be effective in capturing long-range relations between target entities.
Document-level Relation Extraction with Dual-tier Heterogeneous Graph
Document-level relation extraction (RE) poses new challenges over its sentence-level counterpart since it requires an adequate comprehension of the whole document and the multi-hop reasoning ability across multiple sentences to reach the final result.
Coarse-to-Fine Pre-training for Named Entity Recognition
More recently, Named Entity Recognition hasachieved great advances aided by pre-trainingapproaches such as BERT.
