paper-with-me

Papers

Explanations for Occluded Images

2021-03-05 · ICCV 2021 10 · Hana Chockler, Daniel Kroening, Youcheng Sun

Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded. We present a novel, black-box algorithm for computing explanations that uses a principled approach based on causal theory. We have implemented the method in the DEEPCOVER tool. We obtain explanations that are much more accurate than those generated by the existing explanation tools on images with occlusions and observe a level of performance comparable to the state of the art when explaining images without occlusions.

📄 PDF Abstract BibTeX arXiv:2103.03622

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Complete Gaussian Splats from a Single Image with Denoising Diffusion Models

2025-08-29 · Ziwei Liao, Mohamed Sayed, Steven L. Waslander, Sara Vicente 외 arxiv

Gaussian splatting typically requires dense observations of the scene and can fail to reconstruct occluded and unobserved areas. We propose a latent diffusion model to reconstruct a complete 3D scene with Gaussian splats…

Deep Feature Augmentation for Occluded Image Classification

2020-11-02 · Feng Cen, Xiaoyu Zhao, Wuzhuang Li, Guanghui Wang

Due to the difficulty in acquiring massive task-specific occluded images, the classification of occluded images with deep convolutional neural networks (CNNs) remains highly challenging. To alleviate the dependency on la…

ClassificationGeneral Classificationimage-classificationImage Classification

Transforming gradient-based techniques into interpretable methods

2024-01-25 · Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman

The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels extracted from images, engenders complex c…

Reliable Local Explanations for Machine Listening

2020-05-15 · Saumitra Mishra, Emmanouil Benetos, Bob L. Sturm, Simon Dixon

One way to analyse the behaviour of machine learning models is through local explanations that highlight input features that maximally influence model predictions. Sensitivity analysis, which involves analysing the effec…

Occluded Person Re-identification

2018-04-09 · Jiaxuan Zhuo, Zeyu Chen, Jian-Huang Lai, Guangcong Wang

Person re-identification (re-id) suffers from a serious occlusion problem when applied to crowded public places. In this paper, we propose to retrieve a full-body person image by using a person image with occlusions. Thi…

Occluded Person Re-IdentificationPerson Re-Identification