Search Results for author:
Found 55 papers, 21 papers with code
Meta Distant Transfer Learning for Pre-trained Language Models
For tasks related to distant domains with different class label sets, PLMs may memorize non-transferable knowledge for the target domain and suffer from negative transfer.
VIVID-10M: A Dataset and Baseline for Versatile and Interactive Video Local Editing
VIVID-10M is the first large-scale hybrid image-video local editing dataset aimed at reducing data construction and model training costs, which comprises 9. 7M samples that encompass a wide range of video editing tasks.
Unified Pathological Speech Analysis with Prompt Tuning
This system uses prompt tuning to adjust only a small part of the parameters to detect different diseases from speeches of possible patients.
Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier
However, in many realistic scenarios, we only have access to few samples and knowledge of the class names (e. g., when considering instances of classes).
Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies
When adapting large models to specific downstream tasks, their massive parameter scale poses a significant challenge in fine-tuning on hardware platforms with limited computational power and GPU memory.
Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content
As visual generation technologies continue to advance, the scale of video datasets has expanded rapidly, and the quality of these datasets is critical to the performance of video generation models.
GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models
In this paper, we introduce a diffusion-based method, termed \ourmethod, to generate fonts that vividly embody specific impressions, utilizing an input consisting of a single letter and a set of descriptive impression keywords.
Automatic Extraction of Relationships among Motivations, Emotions and Actions from Natural Language Texts
We propose a new graph-based framework to reveal relationships among motivations, emotions and actions explicitly given natural language texts.
Efficient Channel Estimation for Millimeter Wave and Terahertz Systems Enabled by Integrated Super-resolution Sensing and Communication
We compare the performance of the minimum mean square error (MMSE) of channel estimation and the resulting beamforming gains of our proposed scheme with the traditional scheme that rely exclusively on channel training.
ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
Vision Transformers (ViTs) have exhibited exceptional performance across diverse computer vision tasks, while their substantial parameter size incurs significantly increased memory and computational demands, impeding effective inference on resource-constrained devices.
LocInv: Localization-aware Inversion for Text-Guided Image Editing
Large-scale Text-to-Image (T2I) diffusion models demonstrate significant generation capabilities based on textual prompts.
Machine Unlearning for Document Classification
In our research, we explore machine unlearning for document classification problems, representing, to the best of our knowledge, the first investigation into this area.
Parallel Proportional Fusion of Spiking Quantum Neural Network for Optimizing Image Classification
The recent emergence of the hybrid quantum-classical neural network (HQCNN) architecture has garnered considerable attention due to the potential advantages associated with integrating quantum principles to enhance various facets of machine learning algorithms and computations.
Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Specifically, our TES leverages the property that CLIP can generate aligned vision-language features, converting visual embeddings into tokens of the CLIP's text encoder to generate pseudo text embeddings.
Auxiliary Classifiers Improve Stability and Efficiency in Continual Learning
Continual learning is crucial for applications in dynamic environments, where machine learning models must adapt to changing data distributions while retaining knowledge of previous tasks.
FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization
The 4-bit matrix multiplication introduced in the FlattenQuant method can effectively address the compute-bound caused by large matrix calculation.
Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment
Large language models (LLMs) such as GPT-3, OPT, and LLaMA have demonstrated remarkable accuracy in a wide range of tasks.
Exploring Post-Training Quantization of Protein Language Models
In summary, our study introduces an innovative PTQ method for ProteinLMs, addressing specific quantization challenges and potentially leading to the development of more efficient ProteinLMs with significant implications for various protein-related applications.
Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing
Large-scale text-to-image generative models have been a ground-breaking development in generative AI, with diffusion models showing their astounding ability to synthesize convincing images following an input text prompt.
ScrollNet: Dynamic Weight Importance for Continual Learning
The importance of weights for each task can be determined either explicitly through learning a task-specific mask during training (e. g., parameter isolation-based approaches) or implicitly by introducing a regularization term (e. g., regularization-based approaches).
Recognition of Mental Adjectives in An Efficient and Automatic Style
We propose a new lexical inference task, Mental and Physical Classification (MPC), to handle commonsense reasoning in a reasoning graph.
Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited
In fact, this question was answered ten years ago when IDRec beats MoRec by a strong margin in both recommendation accuracy and efficiency.
Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation
Secondly, we propose a new method of feature drift compensation that accommodates feature drift in the backbone when learning new tasks.
Attention Distillation: self-supervised vision transformer students need more guidance
In experiments on ImageNet-Subset and ImageNet-1K, we show that our method AttnDistill outperforms existing self-supervised knowledge distillation (SSKD) methods and achieves state-of-the-art k-NN accuracy compared with self-supervised learning (SSL) methods learning from scratch (with the ViT-S model).
SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision
Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications.
Free-form Lesion Synthesis Using a Partial Convolution Generative Adversarial Network for Enhanced Deep Learning Liver Tumor Segmentation
The lesion synthesis framework was evaluated for lesion textures, and the synthetic lesions were used to train a lesion segmentation network to further validate the effectiveness of this framework.
Exploring evolution-aware & -free protein language models as protein function predictors
Large-scale Protein Language Models (PLMs) have improved performance in protein prediction tasks, ranging from 3D structure prediction to various function predictions.
Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i. e., biased domain adaptation.
Slimmable Video Codec
Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands.
Towards Unified Prompt Tuning for Few-shot Text Classification
Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts.
An effective coaxiality measurement for twist drill based on line structured light sensor
Aiming at the accurate and effective coaxiality measurement for twist drill with irregular surface, an optical measurement mechanism is proposed in this paper.
A Novel Framework for Image-to-image Translation and Image Compression
Thus, we further propose a unified framework that allows both translation and autoencoding capabilities in a single codec.
OneFlow: Redesign the Distributed Deep Learning Framework from Scratch
Aiming at a simple, neat redesign of distributed deep learning frameworks for various parallelism paradigms, we present OneFlow, a novel distributed training framework based on an SBP (split, broadcast and partial-value) abstraction and the actor model.
Continuous Conditional Random Field Convolution for Point Cloud Segmentation
Furthermore, we build an encoder-decoder network based on the proposed continuous CRF graph convolution (CRFConv), in which the CRFConv embedded in the decoding layers can restore the details of high-level features that were lost in the encoding stage to enhance the location ability of the network, thereby benefiting segmentation.
3D Shapes Local Geometry Codes Learning with SDF
We propose Local Geometry Code Learning (LGCL), a model that improves the original DeepSDF results by learning from a local shape geometry of the full 3D shape.
DANICE: Domain adaptation without forgetting in neural image compression
Neural image compression (NIC) is a new coding paradigm where coding capabilities are captured by deep models learned from data.
Slimmable Compressive Autoencoders for Practical Neural Image Compression
Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance.
Representation, Analysis of Bayesian Refinement Approximation Network: A Survey
In our modified U-Net model, the result of background subtraction from other models will be combined with the source image as input for learning the statistical distribution.
Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data
Railway systems require regular manual maintenance, a large part of which is dedicated to inspecting track deformation.
Gaussian Constrained Attention Network for Scene Text Recognition
In this paper, we propose Gaussian Constrained Attention Network to deal with this problem.
Two-Level Residual Distillation based Triple Network for Incremental Object Detection
Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data.
Self-Training for Domain Adaptive Scene Text Detection
To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images.
Variable Rate Deep Image Compression with Modulated Autoencoder
Addressing these limitations, we formulate the problem of variable rate-distortion optimization for deep image compression, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific rate-distortion tradeoff via a modulation network.
Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component.
Sparse data interpolation using the geodesic distance affinity space
In this paper, we adapt the geodesic distance-based recursive filter to the sparse data interpolation problem.
In-the-wild Facial Expression Recognition in Extreme Poses
In the computer research area, facial expression recognition is a hot research problem.
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
Random data augmentation is a critical technique to avoid overfitting in training deep neural network models.
Ranked #3 on
Pose Estimation
on Leeds Sports Poses
Quality Classified Image Analysis with Application to Face Detection and Recognition
We will present experimental results to show that our quality classified framework can accurately classify images based on the type and severity of image degradations and can significantly boost the performances of state-of-the-art face detector and recognizer in dealing with image datasets containing mixed quality images.
Web Scale Photo Hash Clustering on A Single Machine
In addition, we propose an online clustering method based on binary k-means that is capable of clustering large photo stream on a single machine, and show applications to spam detection and trending photo discovery.
Deep Sparse Representation for Robust Image Registration
The definition of the similarity measure is an essential component in image registration.
Deep Poselets for Human Detection
We train the poselet model on top of PDF features and combine them with object-level CNNs for detection and bounding box prediction.
Face Recognition via Globality-Locality Preserving Projections
We present an improved Locality Preserving Projections (LPP) method, named Gloablity-Locality Preserving Projections (GLPP), to preserve both the global and local geometric structures of data.
Adaptive low rank and sparse decomposition of video using compressive sensing
We address the problem of reconstructing and analyzing surveillance videos using compressive sensing.
Recognition of Nonmanual Markers in American Sign Language (ASL) Using Non-Parametric Adaptive 2D-3D Face Tracking
This paper addresses the problem of automatically recognizing linguistically significant nonmanual expressions in American Sign Language from video.
