Where is the Model Looking At?--Concentrate and Explain the Network Attention

2020-09-29 · Wenjia Xu, Jiuniu Wang, Yang Wang, Guangluan Xu, Wei Dai, Yirong Wu

Image classification models have achieved satisfactory performance on many datasets, sometimes even better than human. However, The model attention is unclear since the lack of interpretability. This paper investigates the fidelity and interpretability of model attention. We propose an Explainable Attribute-based Multi-task (EAT) framework to concentrate the model attention on the discriminative image area and make the attention interpretable. We introduce attributes prediction to the multi-task learning network, helping the network to concentrate attention on the foreground objects. We generate attribute-based textual explanations for the network and ground the attributes on the image to show visual explanations. The multi-model explanation can not only improve user trust but also help to find the weakness of network and dataset. Our framework can be generalized to any basic model. We perform experiments on three datasets and five basic models. Results indicate that the EAT framework can give multi-modal explanations that interpret the network decision. The performance of several recognition approaches is improved by guiding network attention.

📄 PDF Abstract BibTeX arXiv:2009.13862

Code (0)

등록된 구현이 없습니다.

Tasks

Attributeimage-classification Image Classification Multi-Task Learning

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Few-shot Classification via Adaptive Attention

2020-08-06 · Zi-Hang Jiang, Bingyi Kang, Kuangqi Zhou, Jiashi Feng

Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-lear…

Classification Few-Shot Learning General Classification Meta-Learning

Towards the Linear Algebra Based Taxonomy of XAI Explanations

2023-01-30 · Sven Nomm

This paper proposes an alternative approach to the basic taxonomy of explanations produced by explainable artificial intelligence techniques. Methods of Explainable Artificial Intelligence (XAI) were developed to answer …

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks

2018-06-01 · CVPR 2018 6 · Ping Wei, Yang Liu, Tianmin Shu, Nanning Zheng 외

This paper addresses a new problem - jointly inferring human attention, intentions, and tasks from videos. Given an RGB-D video where a human performs a task, we answer three questions simultaneously: 1) where the human …

RAT: Retrieval-Augmented Transformer for Click-Through Rate Prediction

2024-04-02 · Yushen Li, Jinpeng Wang, Tao Dai, Jieming Zhu 외

Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions. Current methodologies predominantly concentrate on modeling featu…

Click-Through Rate Prediction Retrieval

$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models

2026-02-09 · Ryozo Masukawa, Sanggeon Yun, Hyunwoo Oh, SuhgHeon Jeong 외 arxiv

Recent progress in reinforcement learning with verifiable rewards (RLVR) shows that small, specialized language models (SLMs) can exhibit structured reasoning without relying on large monolithic LLMs. We introduce soft h…

Reinforcement Learning