Search Results for author:
Found 28 papers, 14 papers with code
RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation
Knowledge Distillation (KD) is extensively used in Natural Language Processing to compress the pre-training and task-specific fine-tuning phases of large neural language models.
Improved Genetic Algorithm Based on Greedy and Simulated Annealing Ideas for Vascular Robot Ordering Strategy
To address these challenges, this research introduces a novel strategy, combining mathematical modeling, a hybrid genetic algorithm, and ARIMA time series forecasting.
Self-supervised Photographic Image Layout Representation Learning
This shortfall makes the learning process for photographic image layouts suboptimal.
Resonance RoPE: Improving Context Length Generalization of Large Language Models
This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-trained on shorter sequences face difficulty with out-of-distribution (OOD) token positions in longer sequences.
Local Feature Matching Using Deep Learning: A Survey
The objective of this endeavor is to furnish a comprehensive overview of local feature matching methods.
EVI-SAM: Robust, Real-time, Tightly-coupled Event-Visual-Inertial State Estimation and 3D Dense Mapping
To the best of our knowledge, this is the first non-learning work to realize event-based dense mapping.
RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation
Real-time multi-person pose estimation presents significant challenges in balancing speed and precision.
Ranked #1 on
Multi-Person Pose Estimation
on CrowdPose
(using extra training data)
Hyperparameter Optimization for Large Language Model Instruction-Tuning
The performance on downstream tasks of models fine-tuned with LoRA heavily relies on a set of hyperparameters including the rank of the decomposition.
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization
Label Smoothing (LS) is another simple, versatile and efficient regularization which can be applied to various supervised classification tasks.
RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
Recent studies on 2D pose estimation have achieved excellent performance on public benchmarks, yet its application in the industrial community still suffers from heavy model parameters and high latency.
Ranked #3 on
Pose Estimation
on OCHuman
(using extra training data)
Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging
Moreover, we observe that this simple optimization technique is able to outperform the state-of-the-art KD methods for compact models.
PL-EVIO: Robust Monocular Event-based Visual Inertial Odometry with Point and Line Features
Compared with the standard cameras, it can provide reliable visual perception during high-speed motions and in high dynamic range scenarios.
Mixed noise reduction via sparse error constraint representation of high frequency image for wildlife image
Wildlife image noise reduction is a difficult and challenging problem since the images are inevitably corrupted by the mixed noise in the complex field environments.
Do we need Label Regularization to Fine-tune Pre-trained Language Models?
Knowledge Distillation (KD) is a prominent neural model compression technique that heavily relies on teacher network predictions to guide the training of a student model.
Pseudo Knowledge Distillation: Towards Learning Optimal Instance-specific Label Smoothing Regularization
Knowledge Distillation (KD) is an algorithm that transfers the knowledge of a trained, typically larger, neural network into another model under training.
Identification and Avoidance of Static and Dynamic Obstacles on Point Cloud for UAVs Navigation
The approach is able to avoid both static obstacles and dynamic ones in the same framework.
Weakly Supervised Real-time Image Cropping based on Aesthetic Distributions
In order to tackle this problem, a weakly supervised cropping frame- work is proposed, where the distribution dissimilarity between high quality images and cropped images is used to guide the coordinate predictor’s training and the ground truths of cropping windows are not required by the proposed method.
Learning Consistency Pursued Correlation Filters for Real-Time UAV Tracking
By minimizing the difference between the practical and the scheduled ideal consistency map, the consistency level is constrained to maintain temporal smoothness, and rich temporal information contained in response maps is introduced.
Towards Robust Visual Tracking for Unmanned Aerial Vehicle with Tri-Attentional Correlation Filters
Object tracking has been broadly applied in unmanned aerial vehicle (UAV) tasks in recent years.
Balanced Alignment for Face Recognition: A Joint Learning Approach
There lacks an understanding of how important face alignment is and how it should be performed, for recognition.
Training-Set Distillation for Real-Time UAV Object Tracking
After the establishment of a new slot, the weighted fusion of the previous samples generates one key-sample, in order to reduce the number of samples to be scored.
Boundary Effect-Aware Visual Tracking for UAV with Online Enhanced Background Learning and Multi-Frame Consensus Verification
Meanwhile, convolutional features are extracted to provide a more comprehensive representation of the object.
Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking
Traditional framework of discriminative correlation filters (DCF) is often subject to undesired boundary effects.
An End-to-End Neural Network for Image Cropping by Learning Composition from Aesthetic Photos
In this paper, we primarily focus on improving the accuracy of automatic image cropping, and on further exploring its potential in public datasets with high efficiency.
SC-LSTM: Learning Task-Specific Representations in Multi-Task Learning for Sequence Labeling
Multi-task learning (MTL) has been studied recently for sequence labeling.
Domain-Aware SE Network for Sketch-based Image Retrieval with Multiplicative Euclidean Margin Softmax
This paper proposes a novel approach for Sketch-Based Image Retrieval (SBIR), for which the key is to bridge the gap between sketches and photos in terms of the data representation.
Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network
Additionally, to study the tasks of sketch-based hairstyle retrieval, this paper contributes a new instance-level photo-sketch dataset - Hairstyle Photo-Sketch dataset, which is composed of 3600 sketches and photos, and 2400 sketch-photo pairs.
Finding More Relevance: Propagating Similarity on Markov Random Field for Image Retrieval
To effectively retrieve objects from large corpus with high accuracy is a challenge task.
