Search Results for author: MingJie Sun

Found 18 papers, 12 papers with code

Data Poisoning Attack against Unsupervised Node Embedding Methods

no code implementations30 Oct 2018 Mingjie Sun, Jian Tang, Huichen Li, Bo Li, Chaowei Xiao, Yao Chen, Dawn Song

In this paper, we take the task of link prediction as an example, which is one of the most fundamental problems for graph analysis, and introduce a data positioning attack to node embedding methods.

Data Poisoning Link Prediction

Extreme Values are Accurate and Robust in Deep Networks

no code implementations25 Sep 2019 Jianguo Li, MingJie Sun, ChangShui Zhang

Recent evidence shows that convolutional neural networks (CNNs) are biased towards textures so that CNNs are non-robust to adversarial perturbations over textures, while traditional robust visual features like SIFT (scale-invariant feature transforms) are designed to be robust across a substantial range of affine distortion, addition of noise, etc with the mimic of human perception nature.

Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning

1 code implementation27 Sep 2019 Mingjie Sun, Jimin Xiao, Eng Gee Lim, Yanchu Xie, Jiashi Feng

In this paper, we aim to tackle the task of semi-supervised video object segmentation across a sequence of frames where only the ground-truth segmentation of the first frame is provided.

reinforcement-learning Reinforcement Learning (RL) +4

Fast Template Matching and Update for Video Object Tracking and Segmentation

1 code implementation CVPR 2020 Mingjie Sun, Jimin Xiao, Eng Gee Lim, Bingfeng Zhang, Yao Zhao

Specifically, the reinforcement learning agent learns to decide whether to update the target template according to the quality of the predicted result.

reinforcement-learning Reinforcement Learning (RL) +5

Poisoned classifiers are not only backdoored, they are fundamentally broken

1 code implementation18 Oct 2020 MingJie Sun, Siddhant Agarwal, J. Zico Kolter

Under this threat model, we propose a test-time, human-in-the-loop attack method to generate multiple effective alternative triggers without access to the initial backdoor and the training data.

Extreme Value Preserving Networks

no code implementations17 Nov 2020 MingJie Sun, Jianguo Li, ChangShui Zhang

Recent evidence shows that convolutional neural networks (CNNs) are biased towards textures so that CNNs are non-robust to adversarial perturbations over textures, while traditional robust visual features like SIFT (scale-invariant feature transforms) are designed to be robust across a substantial range of affine distortion, addition of noise, etc with the mimic of human perception nature.

Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning

1 code implementation CVPR 2021 MingJie Sun, Jimin Xiao, Eng Gee Lim

In this paper, we are tackling the proposal-free referring expression grounding task, aiming at localizing the target object according to a query sentence, without relying on off-the-shelf object proposals.

Referring Expression reinforcement-learning +2

Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding

1 code implementation8 Jun 2021 MingJie Sun, Jimin Xiao, Eng Gee Lim, Si Liu, John Y. Goulermas

In this paper, we are tackling the weakly-supervised referring expression grounding task, for the localization of a referent object in an image according to a query sentence, where the mapping between image regions and queries are not available during the training stage.

Referring Expression Sentence

(Certified!!) Adversarial Robustness for Free!

1 code implementation21 Jun 2022 Nicholas Carlini, Florian Tramer, Krishnamurthy Dj Dvijotham, Leslie Rice, MingJie Sun, J. Zico Kolter

In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models.

Adversarial Robustness Denoising

Test-Time Adaptation via Conjugate Pseudo-labels

1 code implementation20 Jul 2022 Sachin Goyal, MingJie Sun, aditi raghunathan, Zico Kolter

In this paper, we start by presenting a surprising phenomenon: if we attempt to meta-learn the best possible TTA loss over a wide class of functions, then we recover a function that is remarkably similar to (a temperature-scaled version of) the softmax-entropy employed by TENT.

Meta-Learning Test-time Adaptation

Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning

no code implementations17 Dec 2022 Hui Li, MingJie Sun, Jimin Xiao, Eng Gee Lim, Yao Zhao

To validate our framework on a weakly-supervised setting, we annotated three RES benchmark datasets (RefCOCO, RefCOCO+ and RefCOCOg) with click annotations. Our method is simple but surprisingly effective, outperforming all previous state-of-the-art RES methods on fully- and weakly-supervised settings by a large margin.

Position Referring Expression +3

Single Image Backdoor Inversion via Robust Smoothed Classifiers

1 code implementation CVPR 2023 MingJie Sun, J. Zico Kolter

Insipired by recent advances in adversarial robustness, our method SmoothInv starts from a single clean image, and then performs projected gradient descent towards the target class on a robust smoothed version of the original backdoored classifier.

Adversarial Robustness Image Generation

A Simple and Effective Pruning Approach for Large Language Models

2 code implementations20 Jun 2023 MingJie Sun, Zhuang Liu, Anna Bair, J. Zico Kolter

Motivated by the recent observation of emergent large magnitude features in LLMs, our approach prunes weights with the smallest magnitudes multiplied by the corresponding input activations, on a per-output basis.

Network Pruning

Dance with You: The Diversity Controllable Dancer Generation via Diffusion Models

1 code implementation23 Aug 2023 Siyue Yao, MingJie Sun, Bingliang Li, Fengyu Yang, Junle Wang, Ruimao Zhang

In this paper, we introduce a novel multi-dancer synthesis task called partner dancer generation, which involves synthesizing virtual human dancers capable of performing dance with users.

Reliable Test-Time Adaptation via Agreement-on-the-Line

no code implementations7 Oct 2023 Eungyeup Kim, MingJie Sun, aditi raghunathan, Zico Kolter

In this work, we make a notable and surprising observation that TTAed models strongly show the agreement-on-the-line phenomenon (Baek et al., 2022) across a wide range of distribution shifts.

Test-time Adaptation

Massive Activations in Large Language Models

1 code implementation27 Feb 2024 MingJie Sun, Xinlei Chen, J. Zico Kolter, Zhuang Liu

We observe an empirical phenomenon in Large Language Models (LLMs) -- very few activations exhibit significantly larger values than others (e. g., 100, 000 times larger).

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