tsingqguo Goto Github PK

a-pytorch-tutorial-to-object-detection

SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection

aba

We propose the adversarial blur attack (ABA) against visual object tracking.

abba

attacktracker

augmix

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

bgmix

We propose a novel data augmentation by enriching the backgrounds for change detection in a weakly-superivsed way.

ccotssr

abc

cfmix

init

ctca4cslr

We propose a cross- temporal context aggregation (CTCA) model for continuous sign language recognition

deepmix

deeprhythm

dsiam

Learning Dynamic Siamese Network for Visual Object Tracking

efficientderain

we propose EfficientDerain for high-efficiency single-image deraining

efficientderainplus

We further extend the efficientderain in https://github.com/tsingqguo/efficientderain via a novel predictive filtering framework.

evadingfakedetector

We propose a statistical consistency attack (StatAttack) against diverse DeepFake detectors.

exposure-fusion-shadow-removal

We propose a new method for effective shadow removal by regarding it as an exposure fusion problem.

frequency-tuned-acm

This repository contains the demos of frequency-tuned ACM.

inpaint4shadow

We propose the shadow-guided inpainting task to take advantage of the shadow removal and image inpainting.

irad

We introduce a novel approach to counter adversarial attacks, namely, image resampling. The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks.

jadena

Official implementation of "Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection" in CVPR 2022.

jpgnet

We proposed a novel framework for image inpainting. https://arxiv.org/abs/2107.04281

misf

msiam

Try to build a new tracking framework with Siamese network

pytorch-sepconv

an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch(Backward Implemented)

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

resample4defense

We have identified a novel adversarial defense solution, i.e., image resampling, which can break the adversarial textures while maintaining the main semantic information in the input image. This work has been accepted to ICLR 2024.

robustot

We build a benchmark to involve existing adversairal tracking attacks and defense methods and evaluates their performance, which could trick a series of novel works and push the progress to build a robust tracking system.

sair

We propose the semantic-aware implicit representation by learning semantic-aware implicit representation (SAIR), that is, we make the implicit representation of each pixel rely on both its appearance and semantic information (e.g., which object does the pixel belong to). This work is publised in ECCV 2024.

sharel

We propose a shadow-removal benchmark dataset (i.e., SHAREL) to explore the mutual influence of shadow removal and facial landmark detection tasks.

siamf