Search Results for author:
Found 87 papers, 49 papers with code
Mamba or Transformer for Time Series Forecasting? Mixture of Universals (MoU) Is All You Need
To address these challenges, we introduce Mixture of Universals (MoU), a versatile model to capture both short-term and long-term dependencies for enhancing performance in time series forecasting.
Adaptive Mix for Semi-Supervised Medical Image Segmentation
Given that, in general, a model's performance gradually improves during training, AdaMix is equipped with a self-paced curriculum that, in the initial training stage, provides relatively simple perturbed samples and then gradually increases the difficulty of perturbed images by adaptively controlling the perturbation degree based on the model's learning state estimated by a self-paced regularize.
Empowering Graph Invariance Learning with Deep Spurious Infomax
To bridge this gap, we introduce a novel graph invariance learning paradigm, which induces a robust and general inductive bias.
FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation
This work presents a Fully BInarized Large Language Model (FBI-LLM), demonstrating for the first time how to train a large-scale binary language model from scratch (not the partial binary or ternary LLM like BitNet b1. 58) to match the performance of its full-precision counterparts (e. g., FP16 or BF16) in transformer-based LLMs.
Self-Paced Sample Selection for Barely-Supervised Medical Image Segmentation
The existing barely-supervised medical image segmentation (BSS) methods, adopting a registration-segmentation paradigm, aim to learn from data with very few annotations to mitigate the extreme label scarcity problem.
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
To address this problem, we propose Web2Code, a benchmark consisting of a new large-scale webpage-to-code dataset for instruction tuning and an evaluation framework for the webpage understanding and HTML code translation abilities of MLLMs.
Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena
To address them, a more thorough approach involves shifting from MCQ to open-style questions, which can fundamentally eliminate selection bias and random guessing issues.
Rethinking Barely-Supervised Volumetric Medical Image Segmentation from an Unsupervised Domain Adaptation Perspective
To this end, we propose a novel BSS framework, \textbf{B}arely-supervised learning \textbf{via} unsupervised domain \textbf{A}daptation (BvA), as an alternative to the dominant registration paradigm.
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
Our approach relaxes the discrete jailbreak optimization into a continuous optimization and progressively increases the sparsity of the optimizing vectors.
Elucidating the Design Space of Dataset Condensation
Dataset condensation, a concept within data-centric learning, efficiently transfers critical attributes from an original dataset to a synthetic version, maintaining both diversity and realism.
TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
Specifically, we identify four critical protection properties that existing methods fail to simultaneously satisfy: (1) maintaining protection after a model is physically copied; (2) authorizing model access at request level; (3) safeguarding runtime reverse engineering; (4) achieving high security with negligible runtime overhead.
Self-supervised Dataset Distillation: A Good Compression Is All You Need
In this work, we consider addressing this task through the new lens of model informativeness in the compression stage on the original dataset pretraining.
Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving
We present a new 3D point-based detector model, named Shift-SSD, for precise 3D object detection in autonomous driving.
Precise Knowledge Transfer via Flow Matching
We name this framework Knowledge Transfer with Flow Matching (FM-KT), which can be integrated with a metric-based distillation method with any form (\textit{e. g.} vanilla KD, DKD, PKD and DIST) and a meta-encoder with any available architecture (\textit{e. g.} CNN, MLP and Transformer).
FerKD: Surgical Label Adaptation for Efficient Distillation
For instance, FerKD achieves 81. 2% on ImageNet-1K with ResNet-50, outperforming FKD and FunMatch by remarkable margins.
Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
This paper introduces 26 guiding principles designed to streamline the process of querying and prompting large language models.
LLM360: Towards Fully Transparent Open-Source LLMs
The recent surge in open-source Large Language Models (LLMs), such as LLaMA, Falcon, and Mistral, provides diverse options for AI practitioners and researchers.
Initializing Models with Larger Ones
Weight selection offers a new approach to leverage the power of pretrained models in resource-constrained settings, and we hope it can be a useful tool for training small models in the large-model era.
Dataset Distillation in Large Data Era
Dataset distillation aims to generate a smaller but representative subset from a large dataset, which allows a model to be trained efficiently, meanwhile evaluating on the original testing data distribution to achieve decent performance.
Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
We call this perspective "generalized matching" and propose Generalized Various Backbone and Statistical Matching (G-VBSM) in this work, which aims to create a synthetic dataset with densities, ensuring consistency with the complete dataset across various backbones, layers, and statistics.
ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy
Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging.
Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
GBLM-Pruner leverages the first-order term of the Taylor expansion, operating in a training-free manner by harnessing properly normalized gradients from a few calibration samples to determine the pruning metric, and substantially outperforms competitive counterparts like SparseGPT and Wanda in multiple benchmarks.
SlimPajama-DC: Understanding Data Combinations for LLM Training
This paper aims to understand the impacts of various data combinations (e. g., web text, Wikipedia, GitHub, books) on the pretraining of large language models using SlimPajama.
Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
We release two open versions of the model -- the foundation Jais model, and an instruction-tuned Jais-chat variant -- with the aim of promoting research on Arabic LLMs.
Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment
To address this challenge, we propose the Self Structural Semantic Alignment (S^3A) framework, which extracts the structural semantic information from unlabeled data while simultaneously self-learning.
Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos
In this paper, we propose a Masked Spatio-Temporal Structure Prediction (MaST-Pre) method to capture the structure of point cloud videos without human annotations.
Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos
Instead of contrasting the representations of clips or frames, in this paper, we propose a unified self-supervised framework by conducting contrastive learning at the point level.
Variation-aware Vision Transformer Quantization
We also find that the variations in ViTs cause training oscillations, bringing instability during quantization-aware training (QAT).
Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
The proposed method demonstrates flexibility across diverse dataset scales and exhibits multiple advantages in terms of arbitrary resolutions of synthesized images, low training cost and memory consumption with high-resolution synthesis, and the ability to scale up to arbitrary evaluation network architectures.
One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning
We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks.
Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning
We present a new self-supervised paradigm on point cloud sequence understanding.
PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos
Self-supervised learning can extract representations of good quality from solely unlabeled data, which is appealing for point cloud videos due to their high labelling cost.
Dropout Reduces Underfitting
Additionally, we explore a symmetric technique for regularizing overfitting models - late dropout, where dropout is not used in the early iterations and is only activated later in training.
Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation
Combining the strengths of UMIX with CMT, UCMT can retain model disagreement and enhance the quality of pseudo labels for the co-training segmentation.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery
The GNCD setting aims to categorize unlabeled training data coming from known and novel classes by leveraging the information of partially labeled known classes.
i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?
(2) Whether we can enhance the representations in the latent feature space by controlling the degree of semantics during sampling on Masked Autoencoders?
MixMask: Revisiting Masking Strategy for Siamese ConvNets
These include (I) the inability to drop uninformative masked regions in ConvNets as they process data continuously, resulting in low training efficiency compared to ViT models; and (II) the mismatch between erase-based masking and the contrastive-based objective in Siamese ConvNets, which differs from the MIM approach.
SDQ: Stochastic Differentiable Quantization with Mixed Precision
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used.
Stereo Neural Vernier Caliper
We propose a new object-centric framework for learning-based stereo 3D object detection.
Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space
This paper explores the feasibility of finding an optimal sub-model from a vision transformer and introduces a pure vision transformer slimming (ViT-Slim) framework.
Data-Free Neural Architecture Search via Recursive Label Calibration
We identify that the NAS task requires the synthesized data (we target at image domain here) with enough semantics, diversity, and a minimal domain gap from the natural images.
A Fast Knowledge Distillation Framework for Visual Recognition
In this study, we present a Fast Knowledge Distillation (FKD) framework that replicates the distillation training phase and generates soft labels using the multi-crop KD approach, while training faster than ReLabel since no post-processes such as RoI align and softmax operations are used.
Ranked #555 on
Image Classification
on ImageNet
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
The nonuniform quantization strategy for compressing neural networks usually achieves better performance than its counterpart, i. e., uniform strategy, due to its superior representational capacity.
Sliced Recursive Transformer
The proposed weight sharing mechanism by sliced recursion structure allows us to build a transformer with more than 100 or even 1000 shared layers with ease while keeping a compact size (13~15M), to avoid optimization difficulties when the model is too large.
Ranked #273 on
Image Classification
on ImageNet
Multi-modal Self-supervised Pre-training for Regulatory Genome Across Cell Types
The core problem is to model how regulatory elements interact with each other and its variability across different cell types.
Multi-modal Self-supervised Pre-training for Large-scale Genome Data
In this work, we propose a simple yet effective approach for pre-training genome data in a multi-modal and self-supervised manner, which we call GeneBERT.
How Do Adam and Training Strategies Help BNNs Optimization?
We show the regularization effect of second-order momentum in Adam is crucial to revitalize the weights that are dead due to the activation saturation in BNNs.
COTR: Convolution in Transformer Network for End to End Polyp Detection
Motivated by the detection transformer (DETR), COTR is constituted by a CNN for feature extraction, transformer encoder layers interleaved with convolutional layers for feature encoding and recalibration, transformer decoder layers for object querying, and a feed-forward network for detection prediction.
"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 #172 on
Image Classification
on CIFAR-100
Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study
This work aims to empirically clarify a recently discovered perspective that label smoothing is incompatible with knowledge distillation.
Unsupervised Disentanglement of Linear-Encoded Facial Semantics
We propose a method to disentangle linear-encoded facial semantics from StyleGAN without external supervision.
Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection
In this work, we investigate utilizing this semantic relation together with the visual information and introduce explicit relation reasoning into the learning of novel object detection.
Ranked #16 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Interpretative Computer-aided Lung Cancer Diagnosis: from Radiology Analysis to Malignancy Evaluation
In addition, explanations of CDAM features proved that the shape and density of nodule regions were two critical factors that influence a nodule to be inferred as malignant, which conforms with the diagnosis cognition of experienced radiologists.
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
In this paper, we focus on this more difficult scenario: learning networks where both weights and activations are binary, meanwhile, without any human annotated labels.
Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning
A common practice for this task is to train a model on the base set first and then transfer to novel classes through fine-tuning (Here fine-tuning procedure is defined as transferring knowledge from base to novel data, i. e. learning to transfer in few-shot scenario.)
Contrast and Order Representations for Video Self-Supervised Learning
To address this, we present a contrast-and-order representation (CORP) framework for learning self-supervised video representations that can automatically capture both the appearance information within each frame and temporal information across different frames.
Ranked #3 on
Self-Supervised Action Recognition Linear
on UCF101
Action Recognition
Self-Supervised Action Recognition Linear
+1
DR 21 South Filament: a Parsec-sized Dense Gas Accretion Flow onto the DR 21 Massive Young Cluster
DR21 south filament (DR21SF) is a unique component of the giant network of filamentary molecular clouds in the north region of Cygnus X complex.
Astrophysics of Galaxies
Conditional Link Prediction of Category-Implicit Keypoint Detection
Keypoints of objects reflect their concise abstractions, while the corresponding connection links (CL) build the skeleton by detecting the intrinsic relations between keypoints.
Online Ensemble Model Compression using Knowledge Distillation
This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble.
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
Our result can be regarded as a strong baseline using knowledge distillation, and to our best knowledge, this is also the first method that is able to boost vanilla ResNet-50 to surpass 80% on ImageNet without architecture modification or additional training data.
Ranked #11 on
Image Classification
on OmniBenchmark
Channel-wise Alignment for Adaptive Object Detection
Existing methods on this task usually draw attention on the high-level alignment based on the whole image or object of interest, which naturally, cannot fully utilize the fine-grained channel information.
Cross-Supervised Object Detection
After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects.
Joint Multi-Dimension Pruning via Numerical Gradient Update
To tackle these three naturally different dimensions, we proposed a general framework by defining pruning as seeking the best pruning vector (i. e., the numerical value of layer-wise channel number, spacial size, depth) and construct a unique mapping from the pruning vector to the pruned network structures.
Binarizing MobileNet via Evolution-based Searching
Inspired by one-shot architecture search frameworks, we manipulate the idea of group convolution to design efficient 1-Bit Convolutional Neural Networks (CNNs), assuming an approximately optimal trade-off between computational cost and model accuracy.
Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification
In this paper, we propose Attentive CutMix, a naturally enhanced augmentation strategy based on CutMix.
Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning
This drawback hinders the model from learning subtle variance and fine-grained information.
ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions
In this paper, we propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost.
Solving Missing-Annotation Object Detection with Background Recalibration Loss
In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image.
Soft Anchor-Point Object Detection
In this work, we boost the performance of the anchor-point detector over the key-point counterparts while maintaining the speed advantage.
Ranked #3 on
Dense Object Detection
on SKU-110K
SAPD：Soft Anchor-Point Detector
In this work, we aim at finding a new balance of speed and accuracy for anchor-free detectors.
SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
Unsupervised domain adaptive object detection aims to learn a robust detector in the domain shift circumstance, where the training (source) domain is label-rich with bounding box annotations, while the testing (target) domain is label-agnostic and the feature distributions between training and testing domains are dissimilar or even totally different.
Exploring Simple and Transferable Recognition-Aware Image Processing
Interestingly, the processing model's ability to enhance recognition quality can transfer when evaluated on models of different architectures, recognized categories, tasks and training datasets.
Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement
In order to distill diverse knowledge from different trained (teacher) models, we propose to use adversarial-based learning strategy where we define a block-wise training loss to guide and optimize the predefined student network to recover the knowledge in teacher models, and to promote the discriminator network to distinguish teacher vs. student features simultaneously.
MoBiNet: A Mobile Binary Network for Image Classification
MobileNet and Binary Neural Networks are two among the most widely used techniques to construct deep learning models for performing a variety of tasks on mobile and embedded platforms. In this paper, we present a simple yet efficient scheme to exploit MobileNet binarization at activation function and model weights.
Towards Instance-level Image-to-Image Translation
The proposed INIT exhibits three import advantages: (1) the instance-level objective loss can help learn a more accurate reconstruction and incorporate diverse attributes of objects; (2) the styles used for target domain of local/global areas are from corresponding spatial regions in source domain, which intuitively is a more reasonable mapping; (3) the joint training process can benefit both fine and coarse granularity and incorporates instance information to improve the quality of global translation.
MEAL: Multi-Model Ensemble via Adversarial Learning
In this paper, we present a method for compressing large, complex trained ensembles into a single network, where knowledge from a variety of trained deep neural networks (DNNs) is distilled and transferred to a single DNN.
Object Detection from Scratch with Deep Supervision
Thus, a better solution to handle these critical problems is to train object detectors from scratch, which motivates our proposed method.
TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C).
Improving Object Detection from Scratch via Gated Feature Reuse
In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i. e., without pre-trained models).
Learning Efficient Convolutional Networks through Network Slimming
For VGGNet, a multi-pass version of network slimming gives a 20x reduction in model size and a 5x reduction in computing operations.
DSOD: Learning Deeply Supervised Object Detectors from Scratch
State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets like ImageNet, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks.
Weakly Supervised Dense Video Captioning
This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences.
Iterative Object and Part Transfer for Fine-Grained Recognition
On both datasets, we achieve better results than many state-of-the-art approaches, including a few using oracle (manually annotated) bounding boxes in the test images.
Multiple Granularity Descriptors for Fine-Grained Categorization
Fine-grained categorization, which aims to distinguish subordinate-level categories such as bird species or dog breeds, is an extremely challenging task.
Do More Dropouts in Pool5 Feature Maps for Better Object Detection
In these fields, the outputs of all layers of CNNs are usually considered as a high dimensional feature vector extracted from an input image and the correspondence between finer level feature vectors and concepts that the input image contains is all-important.
