representation sparsification learning robust
Proj CDeepFuzz Paper Reading: TensorFlow: a system for Large-Scale machine learning
## Abstract 本文:Tensorflow Github: https://github.com/tensorflow/tensorflow Task: Detail on Tensorflow dataflow model 特点: 1. operates at large scale an ......
Proj CDeepFuzz Paper Reading: PyTorch: an imperative style, high-performance deep learning library
## Abstract 本文： PyTorch Task: detail the implementation and architecture of PyTorch Github: https://github.com/pytorch/pytorch 特点： 1. PyTorch同时关注可用性和速 ......
EVA: Visual Representation Fantasies from BAAI
本文做个简单总结，博主不是做自监督领域的，如果错误，欢迎指正。 链接 Code： Official：baaivision/EVA MMpretrain：open-mmlab/mmpretrain/tree/main/configs/eva02 Paper： EVA01：EVA: Explorin ......
Learn Git in 30 days——第 13 天：暂存工作目录与索引的变更状态
写的非常好的一个Git系列文章，强烈推荐 原文链接：https://github.com/doggy8088/Learn-Git-in-30-days/tree/master/zh-cn 有没有遇过这种情境，某个系统开发写到一半，结果被老板或客戶「插单」，被要求紧急修正一个现有系统的 Bug 或添加 ......
Proj CDeepFuzz Paper Reading: PELICAN: Exploiting Backdoors of Naturally Trained Deep Learning Models In Binary Code Analysis
## Abstract 背景： 1. 本文研究的不是被恶意植入的后门，而是products of defects in training 2. 攻击模式: injecting some small fixed input pattern(backdoor) to induce misclassifi ......
Proj CDeepFuzz Paper Reading: Balancing Effectiveness and Flakiness of Non-Deterministic Machine Learning Tests
## Abstract 背景：In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of deep learning mod ......
Proj CDeepFuzz Paper Reading: COMET: Coverage-guided Model Generation For Deep Learning Library Testing
## Abstract 背景：已有的方法(Muffin, Lemon, Cradle) can cover at most 34.1% layer inputs, 25.9% layer parameter values, and 15.6% layer sequences. 本文：COMET Gi ......
Proj CDeepFuzz Paper Reading: IvySyn: Automated Vulnerability Discovery in Deep Learning Frameworks
## Abstract 本文：IvySyn Task: discover memory error vulnerabilities in DL frameworks BugType: memory safety errors, fatal runtime errors Method: 1. 利用na ......
【ICML2022】Understanding The Robustness in Vision Transformers
来自NUS&NVIDIA 文章地址：[2204.12451] Understanding The Robustness in Vision Transformers (arxiv.org) 项目地址：https://github.com/NVlabs/FAN 一、Motivation CNN使用滑动 ......
Proj CDeepFuzz Paper Reading: Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
## Abstract 本文： Task: 1. prove invariance-inducing regularizers can increase predictive accuracy for worst-case spatial transformations 2. prove that ......
[论文阅读] Learning Semi-supervised Gaussian Mixture Model
# Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery ## Abstract 在本文中，我们解决了广义类别发现(generalized category discovery, GCD ......
Learn Git in 30 days——第 12 天：认识 Git 物件的相对名称
写的非常好的一个Git系列文章，强烈推荐 原文链接：https://github.com/doggy8088/Learn-Git-in-30-days/tree/master/zh-cn 在认识了 Git 物件的「绝对名称」与「参照名称」后，最后我们来介绍 Git 版控过程中也很常用到的「相对名称」 ......
Proj CDeepFuzz Paper Reading: Differential Testing of Cross Deep Learning Framework APIs: Revealing Inconsistencies and Vulnerabilities
## Abstract 背景：目前对cross-framework conversion中的inconsistencies和security bugs的研究少有 本文：TensorScope Task: test cross-frame APIs in Machine Learning Librar ......
Learn Git in 30 days——第 11 天：认识 Git 物件的一般参照与符号参照
写的非常好的一个Git系列文章，强烈推荐 原文链接：https://github.com/doggy8088/Learn-Git-in-30-days/tree/master/zh-cn 在认识了 Git 物件的「绝对名称」后，接下来就要介绍 Git 版控过程中最常用到的「参照名称」。 认识物件的参 ......
Proj CDeepFuzz Paper Reading: DeepGauge: multi-granularity testing criteria for deep learning systems
## Abstract 本文: DeepGauge Task: provide multi-granularity testing criteria for DL systems Method: multi-granularity testing criteria for DL systems: 1 ......
[论文阅读] Prototypical contrastive learning of unsupervis
# Prototypical contrastive learning of unsupervised representations ## abstract 这篇论文介绍了原型对比学习（PCL），一种将对比学习与聚类相结合的无监督表示学习方法。PCL不仅为实例区分任务学习低层特征，更重要的是==* ......
Proj CDeepFuzz Paper Reading: Combinatorial Testing for Deep Learning Systems
## Abstract 本文：DeepCT Task: Testing DL Models with Combinatorial Testing Method: 1. 将输出值的空间离散化为区间，以便覆盖每个区间,对不同层内的神经元交互进⾏采样，并减少必须执⾏的测试输⼊的数量。 2. a set o ......
机器学习 -> Machine Learning (III)
> 来做一些入门题吧. 以下大多是 kaggle 环境. **Q1 Titanic** https://www.kaggle.com/competitions/titanic import ``` # This Python 3 environment comes with many helpful ......
Meta-Learning, A Survey
## 一、概述 通常在机器学习里，我们需要用大量的数据来训练一个模型；当场景发生改变时，模型就需要重新训练。这显然提升了成本，而人类学习方式与此不同，一个小孩子在学习动物的过程中，学习了很多动物的名称，当某次给他看一些没有见过的动物时，他总能很快的将新动物和别的动物区分开。Meta learning ......
aarch64/arm_v8 环境下编译Arcade-Learning-Environment —— ale-py
conda install g++=12 cmake ../ -DCMAKE_BUILD_TYPE=Release -DPYTHON_INCLUDE_DIR=/home/share/xxx/home/software/anaconda3/include -DPYTHON_LIBRARY=/home/ ......
论文解读（SPGJL）《Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis》
Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis论文作者：Jingli Shi、Weihua Li、Quan Bai ......
Q-learning and RL implementation
Aim: Train a model to properly play vintage video games... Deep Q-learning Algo~ Very short Brief of Notations: {A,pi(Policy),Q(quality of action-at a ......
Learn Git in 30 days——第 10 天：认识 Git 物件的绝对名称
写的非常好的一个Git系列文章，强烈推荐 原文链接：https://github.com/doggy8088/Learn-Git-in-30-days/tree/master/zh-cn 在 Git 版本控制的过程，每一个版本就代表一个 commit 物件。又因为版控过程中经常会建立分支，最终产出的 ......
Proj CDeepFuzz Paper Reading: ACETest: Automated Constraint Extraction for Testing Deep Learning Operators
## Abstract Github: https://github.com/shijy16/ACETest 背景： 1. DL operators 用来计算多维tensors，很重要 本文：ACETest Task: automatically extract input validation c ......
[论文阅读] Momentum contrast for unsupervised visual representation learning
# Momentum contrast for unsupervised visual representation learning ## Introduction 我们提出了动量对比（MoCo）作为一种构建具有对比损失的无监督学习的大型一致字典的方法（图1）。 我们将字典维护为数据样本队列：当前 ......
Learn Git in 30 days——第 09 天：比对文件与版本差异
写的非常好的一个Git系列文章，强烈推荐 原文链接：https://github.com/doggy8088/Learn-Git-in-30-days/tree/master/zh-cn 使用任何版本控制软件的过程中，经常会需要查看历史记录与比对版本之间的差异。而在使用 Git 的时候要如何进行比对 ......
论文解读（WDGRL）《Wasserstein Distance Guided Representation Learning for Domain Adaptation》
Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Wasserstein Distance Guided Representation Learning for Domain Adaptation论文作者：Jian Shen、Yanru Qu、Weinan ......
【五期邹昱夫】CCF-A（TIFS'23）SAFELearning: Secure Aggregation in Federated Learning with Backdoor Detectability
> "Zhang, Zhuosheng, et al. "SAFELearning: Secure Aggregation in Federated Learning with Backdoor Detectability." IEEE Transactions on Information For ......
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection (2)
Feature backbone采用DLA,输入维度为3×H×W的RGB图,得到维度D×h×w的特征图F,然后将特征图送入几个轻量级regression heads,2D bouding boxes的中心特征图用下面的模块得到: 其中AN是Attentive Normalization.用公式表示: ......
【五期邹昱夫】CCF-A（SP'23）3DFed: Adaptive and Extensible Framework for Covert Backdoor Attack in Federated Learning
> "Li, Haoyang, et al. "3DFed: Adaptive and Extensible Framework for Covert Backdoor Attack in Federated Learning." 2023 IEEE Symposium on Security an ......