Search Results for author: Ming Lin

Found 52 papers, 23 papers with code

Prompt Mixing in Diffusion Models using the Black Scholes Algorithm

1 code implementation22 May 2024 Divya Kothandaraman, Ming Lin, Dinesh Manocha

We introduce a novel approach for prompt mixing, aiming to generate images at the intersection of multiple text prompts using pre-trained text-to-image diffusion models.


Merino: Entropy-driven Design for Generative Language Models on IoT Devices

no code implementations28 Feb 2024 Youpeng Zhao, Ming Lin, Huadong Tang, Qiang Wu, Jun Wang

Generative Large Language Models (LLMs) stand as a revolutionary advancement in the modern era of artificial intelligence (AI).

SHARE: Single-view Human Adversarial REconstruction

no code implementations30 Dec 2023 Shreelekha Revankar, Shijia Liao, Yu Shen, Junbang Liang, Huaishu Peng, Ming Lin

We perform a comprehensive analysis on the impact of camera poses on HPS reconstruction outcomes.

Data Augmentation

Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge

no code implementations9 Dec 2023 Xuan Shen, Peiyan Dong, Lei Lu, Zhenglun Kong, Zhengang Li, Ming Lin, Chao Wu, Yanzhi Wang

Recent works show that 8-bit or lower weight quantization is feasible with minimal impact on end-to-end task performance, while the activation is still not quantized.

Language Modelling Quantization

HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors

no code implementations28 Nov 2023 Shutong Zhang, Yi-Ling Qiao, Guanglei Zhu, Eric Heiden, Dylan Turpin, Jingzhou Liu, Ming Lin, Miles Macklin, Animesh Garg

We demonstrate that HandyPriors attains comparable or superior results in the pose estimation task, and that the differentiable physics module can predict contact information for pose refinement.

Human-Object Interaction Detection Object +1

HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View

2 code implementations27 Nov 2023 Divya Kothandaraman, Tianyi Zhou, Ming Lin, Dinesh Manocha

It seamlessly blends the visual features from the input image within a pretrained text-to-2Dimage stable diffusion model with a test-time optimization process for a careful bias-variance trade-off, which uses an Inverse Perspective Mapping (IPM) homography transformation to provide subtle cues for aerialview synthesis.

Novel View Synthesis

ICAR: Image-based Complementary Auto Reasoning

no code implementations17 Aug 2023 Xijun Wang, Anqi Liang, Junbang Liang, Ming Lin, Yu Lou, Shan Yang

Based on this notion, we propose a compatibility learning framework, a category-aware Flexible Bidirectional Transformer (FBT), for visual "scene-based set compatibility reasoning" with the cross-domain visual similarity input and auto-regressive complementary item generation.


Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities

1 code implementation5 Jul 2023 Guihong Li, Duc Hoang, Kartikeya Bhardwaj, Ming Lin, Zhangyang Wang, Radu Marculescu

Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process.

Neural Architecture Search

Making Vision Transformers Efficient from A Token Sparsification View

1 code implementation CVPR 2023 Shuning Chang, Pichao Wang, Ming Lin, Fan Wang, David Junhao Zhang, Rong Jin, Mike Zheng Shou

In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks.

Efficient ViTs Instance Segmentation +4

PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification

no code implementations9 Mar 2023 Xuan Li, Yi-Ling Qiao, Peter Yichen Chen, Krishna Murthy Jatavallabhula, Ming Lin, Chenfanfu Jiang, Chuang Gan

In this work, we aim to identify parameters characterizing a physical system from a set of multi-view videos without any assumption on object geometry or topology.

Neural Rendering Object

Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition

1 code implementation5 Mar 2023 Junyan Wang, Zhenhong Sun, Yichen Qian, Dong Gong, Xiuyu Sun, Ming Lin, Maurice Pagnucco, Yang song

In this work, we propose to automatically design efficient 3D CNN architectures via a novel training-free neural architecture search approach tailored for 3D CNNs considering the model complexity.

Action Recognition Computational Efficiency +2

DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network

1 code implementation CVPR 2023 Xuan Shen, Yaohua Wang, Ming Lin, Yilun Huang, Hao Tang, Xiuyu Sun, Yanzhi Wang

To this end, a novel framework termed Mathematical Architecture Design for Deep CNN (DeepMAD) is proposed to design high-performance CNN models in a principled way.

Image Classification Neural Architecture Search

Entropy-Driven Mixed-Precision Quantization for Deep Network Design

1 code implementation Conference on Neural Information Processing Systems 2022 Zhenhong Sun, Ce Ge, Junyan Wang, Ming Lin, Hesen Chen, Hao Li, Xiuyu Sun

Deploying deep convolutional neural networks on Internet-of-Things (IoT) devices is challenging due to the limited computational resources, such as limited SRAM memory and Flash storage.

Face Detection Hardware Aware Neural Architecture Search +3

Differentiable Analog Quantum Computing for Optimization and Control

1 code implementation28 Oct 2022 Jiaqi Leng, Yuxiang Peng, Yi-Ling Qiao, Ming Lin, Xiaodi Wu

We formulate the first differentiable analog quantum computing framework with a specific parameterization design at the analog signal (pulse) level to better exploit near-term quantum devices via variational methods.

Robust Graph Structure Learning via Multiple Statistical Tests

1 code implementation8 Oct 2022 Yaohua Wang, Fangyi Zhang, Ming Lin, Senzhang Wang, Xiuyu Sun, Rong Jin

A natural way to construct a graph among images is to treat each image as a node and assign pairwise image similarities as weights to corresponding edges.

Face Clustering Graph structure learning

Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition

no code implementations15 Sep 2022 Divya Kothandaraman, Ming Lin, Dinesh Manocha

We build a differentiable static-dynamic frequency mask prior to model the salient static and dynamic pixels in the video, crucial for the underlying task of action recognition.

Action Recognition Activity Recognition In Videos +2

FAR: Fourier Aerial Video Recognition

1 code implementation21 Mar 2022 Divya Kothandaraman, Tianrui Guan, Xijun Wang, Sean Hu, Ming Lin, Dinesh Manocha

Our formulation uses a novel Fourier object disentanglement method to innately separate out the human agent (which is typically small) from the background.

Action Recognition Disentanglement +1

Entroformer: A Transformer-based Entropy Model for Learned Image Compression

2 code implementations ICLR 2022 Yichen Qian, Ming Lin, Xiuyu Sun, Zhiyu Tan, Rong Jin

One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules.

Image Classification Image Compression +1

GiraffeDet: A Heavy-Neck Paradigm for Object Detection

2 code implementations ICLR 2022 Yiqi Jiang, Zhiyu Tan, Junyan Wang, Xiuyu Sun, Ming Lin, Hao Li

This heavy-backbone design paradigm is mostly due to the historical legacy when transferring image recognition models to object detection rather than an end-to-end optimized design for object detection.

Object object-detection +1

Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

2 code implementations ICLR 2022 Yaohua Wang, Yaobin Zhang, Fangyi Zhang, Ming Lin, Yuqi Zhang, Senzhang Wang, Xiuyu Sun

In Ada-NETS, each face is transformed to a new structure space, obtaining robust features by considering face features of the neighbour images.

Clustering Face Clustering

Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering

no code implementations NeurIPS 2021 Yu Shen, Laura Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming Lin

We introduce a simple yet effective framework for improving the robustness of learning algorithms against image corruptions for autonomous driving.

Autonomous Driving Self-Driving Cars

MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection

1 code implementation26 Nov 2021 Zhenhong Sun, Ming Lin, Xiuyu Sun, Zhiyu Tan, Hao Li, Rong Jin

Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS).

Neural Architecture Search Object +2

ZenDet: Revisiting Efficient Object Detection Backbones from Zero-Shot Neural Architecture Search

no code implementations29 Sep 2021 Zhenhong Sun, Ming Lin, Zhiyu Tan, Xiuyu Sun, Rong Jin

Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS).

Neural Architecture Search Object +2

NAS-Bench-Zero: A Large Scale Dataset for Understanding Zero-Shot Neural Architecture Search

no code implementations29 Sep 2021 Hanlin Chen, Ming Lin, Xiuyu Sun, Hao Li

Based on these new discoveries, we propose i) a novel hybrid zero-shot proxy which outperforms existing ones by a large margin and is transferable among popular search spaces; ii) a new index for better measuring the true performance of ZS-NAS proxies in constrained NAS.

Benchmarking Neural Architecture Search

Hierarchical Cross Contrastive Learning of Visual Representations

no code implementations29 Sep 2021 Hesen Chen, Ming Lin, Xiuyu Sun, Rong Jin

In this work, we propose a novel approach termed Hierarchical Cross Contrastive Learning(HCCL) to further distill the information mismatched by the conventional contrastive loss.

Contrastive Learning Few-Shot Learning +1

Fine-Grained AutoAugmentation for Multi-Label Classification

no code implementations12 Jul 2021 Ya Wang, Hesen Chen, Fangyi Zhang, Yaohua Wang, Xiuyu Sun, Ming Lin, Hao Li

Data augmentation is a commonly used approach to improving the generalization of deep learning models.

Classification Data Augmentation +3

KVT: k-NN Attention for Boosting Vision Transformers

1 code implementation28 May 2021 Pichao Wang, Xue Wang, Fan Wang, Ming Lin, Shuning Chang, Hao Li, Rong Jin

A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies.

Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving

no code implementations15 Mar 2021 Shivam Akhauri, Laura Zheng, Tom Goldstein, Ming Lin

Practical learning-based autonomous driving models must be capable of generalizing learned behaviors from simulated to real domains, and from training data to unseen domains with unusual image properties.

Autonomous Driving Data Augmentation +2

Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition

2 code implementations1 Feb 2021 Ming Lin, Pichao Wang, Zhenhong Sun, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin

Comparing with previous NAS methods, the proposed Zen-NAS is magnitude times faster on multiple server-side and mobile-side GPU platforms with state-of-the-art accuracy on ImageNet.

Image Classification Neural Architecture Search

Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition

2 code implementations ICCV 2021 Ming Lin, Pichao Wang, Zhenhong Sun, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin

To address this issue, instead of using an accuracy predictor, we propose a novel zero-shot index dubbed Zen-Score to rank the architectures.

Neural Architecture Search Vocal Bursts Intensity Prediction

Driving through the Lens: Improving Generalization of Learning-based Steering using Simulated Adversarial Examples

no code implementations1 Jan 2021 Yu Shen, Laura Yu Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming Lin

To ensure the wide adoption and safety of autonomous driving, the vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments.

Autonomous Driving Data Augmentation +2

Learning Accurate Entropy Model with Global Reference for Image Compression

2 code implementations ICLR 2021 Yichen Qian, Zhiyu Tan, Xiuyu Sun, Ming Lin, Dongyang Li, Zhenhong Sun, Hao Li, Rong Jin

In this work, we propose a novel Global Reference Model for image compression to effectively leverage both the local and the global context information, leading to an enhanced compression rate.

Image Compression

Robust Finite Mixture Regression for Heterogeneous Targets

no code implementations12 Oct 2020 Jian Liang, Kun Chen, Ming Lin, ChangShui Zhang, Fei Wang

FMR is an effective scheme for handling sample heterogeneity, where a single regression model is not enough for capturing the complexities of the conditional distribution of the observed samples given the features.

feature selection regression

WeMix: How to Better Utilize Data Augmentation

no code implementations3 Oct 2020 Yi Xu, Asaf Noy, Ming Lin, Qi Qian, Hao Li, Rong Jin

To this end, we develop two novel algorithms, termed "AugDrop" and "MixLoss", to correct the data bias in the data augmentation.

Data Augmentation

Enhanced Transfer Learning for Autonomous Driving with Systematic Accident Simulation

no code implementations23 Jul 2020 Shivam Akhauri, Laura Zheng, Ming Lin

Simulation data can be utilized to extend real-world driving data in order to cover edge cases, such as vehicle accidents.

Autonomous Driving Collision Avoidance +1

Neural Architecture Design for GPU-Efficient Networks

2 code implementations24 Jun 2020 Ming Lin, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin

To address this issue, we propose a general principle for designing GPU-efficient networks based on extensive empirical studies.

Neural Architecture Search

Knapsack Pruning with Inner Distillation

1 code implementation19 Feb 2020 Yonathan Aflalo, Asaf Noy, Ming Lin, Itamar Friedman, Lihi Zelnik

Through this we produce compact architectures with the same FLOPs as EfficientNet-B0 and MobileNetV3 but with higher accuracy, by $1\%$ and $0. 3\%$ respectively on ImageNet, and faster runtime on GPU.

Knowledge Distillation Network Pruning +1

Differentiable Cloth Simulation for Inverse Problems

1 code implementation NeurIPS 2019 Junbang Liang, Ming Lin, Vladlen Koltun

We propose a differentiable cloth simulator that can be embedded as a layer in deep neural networks.

Robust Gaussian Process Regression for Real-Time High Precision GPS Signal Enhancement

no code implementations3 Jun 2019 Ming Lin, Xiaomin Song, Qi Qian, Hao Li, Liang Sun, Shenghuo Zhu, Rong Jin

We validate the superiority of the proposed method in our real-time high precision positioning system against several popular state-of-the-art robust regression methods.


Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis

no code implementations19 Jul 2017 Xiang Li, Aoxiao Zhong, Ming Lin, Ning Guo, Mu Sun, Arkadiusz Sitek, Jieping Ye, James Thrall, Quanzheng Li

However, the development of a robust and reliable deep learning model for computer-aided diagnosis is still highly challenging due to the combination of the high heterogeneity in the medical images and the relative lack of training samples.

Computed Tomography (CT) Lesion Detection

Nonconvex One-bit Single-label Multi-label Learning

no code implementations17 Mar 2017 Shuang Qiu, Tingjin Luo, Jieping Ye, Ming Lin

We study an extreme scenario in multi-label learning where each training instance is endowed with a single one-bit label out of multiple labels.

Multi-Label Learning

The Second Order Linear Model

no code implementations2 Mar 2017 Ming Lin, Shuang Qiu, Bin Hong, Jieping Ye

We show that the conventional gradient descent heuristic is biased by the skewness of the distribution therefore is no longer the best practice of learning the SLM.

Open-Ended Question Answering

A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing

no code implementations NeurIPS 2016 Ming Lin, Jieping Ye

We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees.

Matrix Completion Retrieval

Strategies for Searching Video Content with Text Queries or Video Examples

no code implementations17 Jun 2016 Shoou-I Yu, Yi Yang, Zhongwen Xu, Shicheng Xu, Deyu Meng, Zexi Mao, Zhigang Ma, Ming Lin, Xuanchong Li, Huan Li, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann, Chuang Gan, Xingzhong Du, Xiaojun Chang

The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.

Event Detection Retrieval +1

Handcrafted Local Features are Convolutional Neural Networks

no code implementations16 Nov 2015 Zhenzhong Lan, Shoou-I Yu, Ming Lin, Bhiksha Raj, Alexander G. Hauptmann

We approach this problem by first showing that local handcrafted features and Convolutional Neural Networks (CNNs) share the same convolution-pooling network structure.

Action Recognition Optical Flow Estimation +2

The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition

no code implementations17 May 2015 Zhenzhong Lan, Dezhong Yao, Ming Lin, Shoou-I Yu, Alexander Hauptmann

First, we propose a two-stream Stacked Convolutional Independent Subspace Analysis (ConvISA) architecture to show that unsupervised learning methods can significantly boost the performance of traditional local features extracted from data-independent models.

Action Recognition Multi-class Classification +3

Long-short Term Motion Feature for Action Classification and Retrieval

no code implementations13 Feb 2015 Zhenzhong Lan, Xuanchong Li, Ming Lin, Alexander G. Hauptmann

Therefore, they need to occur frequently enough in the videos and to be be able to tell the difference among different types of motions.

Action Classification Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.