Search Results for author:
Found 22 papers, 15 papers with code
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
This strategy effectively alleviates the interference between the two tasks of image-text alignment and instruction following and achieves strong multi-modal reasoning with only a small-scale image-text and instruction dataset.
Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement
The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its application to diverse downstream vision tasks.
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model.
FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation
The first method is One-to-many Matching via Data Augmentation (denoted as DataAug-DETR).
Omni-Dimensional Dynamic Convolution
Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs).
An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers
(1) From algorithm perspective, we propose a sparsity inheritance mechanism along with an inherited dynamic pruning (IDP) method to obtain a series of N:M sparse candidate Transformers rapidly.
Group R-CNN for Weakly Semi-supervised Object Detection with Points
The core of this task is to train a point-to-box regressor on well-labeled images that can be used to predict credible bounding boxes for each point annotation.
Pyramid Fusion Transformer for Semantic Segmentation
The recently proposed MaskFormer gives a refreshed perspective on the task of semantic segmentation: it shifts from the popular pixel-level classification paradigm to a mask-level classification method.
DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks
However, the existing N:M algorithms only address the challenge of how to train N:M sparse neural networks in a uniform fashion (i. e. every layer has the same N:M sparsity) and suffer from a significant accuracy drop for high sparsity (i. e. when sparsity > 80\%).
Group Fisher Pruning for Practical Network Compression
Our method can be used to prune any structures including those with coupled channels.
Incorporating Convolution Designs into Visual Transformers
Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e. g., ViT and DeiT) to apply Transformers to the vision domain.
Ranked #1 on
Image Classification
on Oxford-IIIT Pets
Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network, which can maintain the advantages of both unstructured fine-grained sparsity and structured coarse-grained sparsity simultaneously on specifically designed GPUs.
Differentiable Dynamic Wirings for Neural Networks
A standard practice of deploying deep neural networks is to apply the same architecture to all the input instances.
Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
To facilitate the training, we represent the network connectivity of each sample in an adjacency matrix.
Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization
Experiment results show that SCT improves accuracy of single Resnet-50 on ImageNet by 1. 7% and 11. 5% accuracy when testing on image sizes of 224 and 128 respectively.
HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions
MobileNets, a class of top-performing convolutional neural network architectures in terms of accuracy and efficiency trade-off, are increasingly used in many resourceaware vision applications.
Deeply-supervised Knowledge Synergy
Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet.
Adversarial Robustness vs Model Compression, or Both?
Furthermore, this work studies two hypotheses about weight pruning in the conventional setting and finds that weight pruning is essential for reducing the network model size in the adversarial setting, training a small model from scratch even with inherited initialization from the large model cannot achieve both adversarial robustness and high standard accuracy.
SnapQuant: A Probabilistic and Nested Parameterization for Binary Networks
During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.
Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks
Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective.
Deep Neural Network Compression with Single and Multiple Level Quantization
In this paper, we propose two novel network quantization approaches, single-level network quantization (SLQ) for high-bit quantization and multi-level network quantization (MLQ) for extremely low-bit quantization (ternary). We are the first to consider the network quantization from both width and depth level.
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
The weights in the other group are responsible to compensate for the accuracy loss from the quantization, thus they are the ones to be re-trained.
