CCNet: Criss-Cross Attention for Semantic Segmentation (ICCV 2019).

Code for paper Unsupervised Object Segmentation by Redrawing

Tensorflow implementation of "Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization"[ICCV 2017]

Code for the Paper "LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks"

Weakly Supervised Object Detection In Practice

EfficientNet-GradCam Visualization

Weakly Supervised Dense Event Captioning in Videos, i.e. generating multiple sentence descriptions for a video in a weakly-supervised manner.

Visualizing the Multi-scale dense network with Grad-CAM

Detect model's attention

The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR'19].

Self-produced Guidance for Weakly-supervised Object Localization

[ECCV 2018] code for Choose Your Neuron: Incorporating Domain Knowledge Through Neuron Importance

CAM using GSAP

I implemented a detection algorithm with a classification data set that does not have annotation information for the bounding box. Based on resnet50 network, I implemented text detector using class activation mapping method.

Weakly Supervised Learning Framework for Image Segmentation Tasks