Search Results for author:
Found 52 papers, 21 papers with code
Low-Resource Multi-Granularity Academic Function Recognition Based on Multiple Prompt Knowledge
Inspired by recent advancement in prompt learning, in this paper, we propose the Mix Prompt Tuning (MPT), which is a semi-supervised method to alleviate the dependence on annotated data and improve the performance of multi-granularity academic function recognition tasks with a small number of labeled examples.
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
However, test-cases in these datasets can be limited in both quantity and quality for fully assessing the functional correctness of the generated code.
Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric
PTQ optimizes the quantization parameters by different metrics to minimize the perturbation of quantization.
NPS: A Framework for Accurate Program Sampling Using Graph Neural Network
Furthermore, NPS shows higher accuracy and generality than the state-of-the-art GNN approach in code behavior learning, enabling the generation of high-quality execution embeddings.
RPTQ: Reorder-based Post-training Quantization for Large Language Models
In this paper, we identify that the challenge in quantizing activations in LLMs arises from varying ranges across channels, rather than solely the presence of outliers.
Abnormal Event Detection via Hypergraph Contrastive Learning
AEHCL designs the intra-event and inter-event contrastive modules to exploit self-supervised AHIN information.
Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation
In this work, we concentrate on a rarely investigated problem of text guided sounding video generation and propose the Sounding Video Generator (SVG), a unified framework for generating realistic videos along with audio signals.
Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance
Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures.
Multi-Channel Attentive Feature Fusion for Radio Frequency Fingerprinting
The features extracted from different channels are fused adaptively using a shared attention module, where the weights of neural features from multiple channels are learned during training the McAFF model.
Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving
To achieve simultaneous detection for both common and rare objects, we propose a novel task, called generalized few-shot 3D object detection, where we have a large amount of training data for common (base) objects, but only a few data for rare (novel) classes.
NeuRI: Diversifying DNN Generation via Inductive Rule Inference
The correctness of DL systems is crucial for trust in DL applications.
AI vs. Human -- Differentiation Analysis of Scientific Content Generation
We find that there exists a "writing style" gap between AI-generated scientific text and human-written scientific text.
Edge-Aware Regional Message Passing Controller for Image Forgery Localization
In the second step, guided by the learnable edges, a region message passing controller is devised to weaken the message passing between the forged and authentic regions.
PD-Quant: Post-Training Quantization based on Prediction Difference Metric
It determines the quantization parameters by using the information of differences between network prediction before and after quantization.
Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models
In this study, we propose an imitation adversarial attack on black-box neural passage ranking models.
Generalised Co-Salient Object Detection
To evaluate the performance of CoSOD models under the GCoSOD setting, we propose two new testing datasets, namely CoCA-Common and CoCA-Zero, where a common salient object is partially present in the former and completely absent in the latter.
NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers
In this work, we propose a new fuzz testing approach for finding bugs in deep-learning compilers.
Improve Ranking Correlation of Super-net through Training Scheme from One-shot NAS to Few-shot NAS
To address this problem, we propose a step-by-step training super-net scheme from one-shot NAS to few-shot NAS.
Label Noise-Resistant Mean Teaching for Weakly Supervised Fake News Detection
LNMT leverages unlabeled news and feedback comments of users to enlarge the amount of training data and facilitates model training by generating refined labels as weak supervision.
Realizing Ultra-Fast and Energy-Efficient Baseband Processing Using Analogue Resistive Switching Memory
To support emerging applications ranging from holographic communications to extended reality, next-generation mobile wireless communication systems require ultra-fast and energy-efficient (UFEE) baseband processors.
Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification
RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images.
Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification
In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization.
Generalizable Person Re-identification
Representation Learning
Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation
Our results show that Tzer substantially outperforms existing fuzzing techniques on tensor compiler testing, with 75% higher coverage and 50% more valuable tests than the 2nd-best technique.
Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification
Image-to-video person re-identification aims to retrieve the same pedestrian as the image-based query from a video-based gallery set.
Image-To-Video Person Re-Identification
reinforcement-learning
+4
Semi-supervised Salient Object Detection with Effective Confidence Estimation
The success of existing salient object detection models relies on a large pixel-wise labeled training dataset.
Calibrated Feature Decomposition for Generalizable Person Re-Identification
The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one.
Domain Generalization
Generalizable Person Re-identification
Enhanced countering adversarial attacks via input denoising and feature restoring
Despite the fact that deep neural networks (DNNs) have achieved prominent performance in various applications, it is well known that DNNs are vulnerable to adversarial examples/samples (AEs) with imperceptible perturbations in clean/original samples.
A Two-Stage Data-Free Adversarial Patch Generation Framework
The proxy dataset selection stage calculates the proposed average patch saliency (APS) of each available dataset to select a high-APS proxy dataset that can guarantee patches' fooling abilities.
A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis
Chatbot is increasingly thriving in different domains, however, because of unexpected discourse complexity and training data sparseness, its potential distrust hatches vital apprehension.
Fast and Flexible Human Pose Estimation with HyperPose
When it comes to customising these algorithms for real-world applications, none of the existing libraries can offer both the flexibility of developing custom pose estimation algorithms and the high-performance of executing these algorithms on commodity devices.
ECNUICA at SemEval-2021 Task 11: Rule based Information Extraction Pipeline
The purpose of the task was to extract triples from a paper in the Nature Language Processing field for constructing an Open Research Knowledge Graph.
Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
Occluded person re-identification (ReID) aims to match person images with occlusion.
Confidence-Aware Learning for Camouflaged Object Detection
Then, we concatenate it with the input image and feed it to the confidence estimation network to produce an one channel confidence map. We generate dynamic supervision for the confidence estimation network, representing the agreement of camouflage prediction with the ground truth camouflage map.
Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification
It describes unseen target domain as a combination of the known source ones, and explicitly learns domain-specific representation with target distribution to improve the model's generalization by a meta-learning pipeline.
Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video sequences.
Learning structure-aware semantic segmentation with image-level supervision
Within this pipeline, the class activation map (CAM) is obtained and further processed to serve as a pseudo label to train the semantic segmentation model in a fully-supervised manner.
Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
Our framework extracts the knowledge of an arbitrary learned GNN model (teacher model), and injects it into a well-designed student model.
Ranked #1 on
Node Classification
on Cora (0.5%)
Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff
Is chatbot able to completely replace the human agent?
Hierarchical Gumbel Attention Network for Text-based Person Search
This hard selection strategy is able to fuse the strong-relevant multi-modality features for alleviating the problem of matching redundancy.
Ranked #9 on
Text based Person Retrieval
on CUHK-PEDES
Local Label Point Correction for Edge Detection of Overlapping Cervical Cells
The qualitative and quantitative experimental results show that our LLPC can improve the quality of manual labels and the accuracy of overlapping cell edge detection.
Temporal Attribute-Appearance Learning Network for Video-based Person Re-Identification
TALNet simultaneously exploits human attributes and appearance to learn comprehensive and effective pedestrian representations from videos.
Decorrelated Clustering with Data Selection Bias
Most of existing clustering algorithms are proposed without considering the selection bias in data.
Co-Designing Statistical MIMO Radar and In-band Full-Duplex Multi-User MIMO Communications
We consider a spectral sharing problem in which a statistical (or widely distributed) multiple-input-multiple-output (MIMO) radar and an in-band full-duplex (IBFD) multi-user MIMO (MU-MIMO) communications system concurrently operate within the same frequency band.
Revisiting Regex Generation for Modeling Industrial Applications by Incorporating Byte Pair Encoder
The results demonstrate the effectiveness of our method, which outperforms the baseline on 10 kinds of data and achieves nearly 50 percent improvement on average.
Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos
Person re-identification aims at identifying a certain pedestrian across non-overlapping camera networks.
Adaptive Transfer Network for Cross-Domain Person Re-Identification
In particular, ATNet consists of a transfer network composed by multiple factor-wise CycleGANs and an ensemble CycleGAN as well as a selection network that infers the affects of different factors on transferring each image.
Automated Essay Scoring based on Two-Stage Learning
Current state-of-art feature-engineered and end-to-end Automated Essay Score (AES) methods are proven to be unable to detect adversarial samples, e. g. the essays composed of permuted sentences and the prompt-irrelevant essays.
CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
An appearance network is developed to learn appearance features from the full body, horizontal and vertical body parts of pedestrians with spatial dependencies among body parts.
A First Look at Deep Learning Apps on Smartphones
We are in the dawn of deep learning explosion for smartphones.
Incorporating Latent Meanings of Morphological Compositions to Enhance Word Embeddings
Experiments on word similarity, syntactic analogy and text classification are conducted to validate the feasibility of our models.
Implicitly Incorporating Morphological Information into Word Embedding
In this paper, we propose three novel models to enhance word embedding by implicitly using morphological information.
