paper-with-me

홈 › Papers

Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery

2018-07-19 · ECCV 2018 9 · Pau Rodríguez, Josep M. Gonfaus, Guillem Cucurull, F. Xavier Roca, Jordi Gonzàlez

We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature activations without requiring part annotations and uses these activations to update and rectify the output likelihood distribution. In contrast to other approaches, the proposed mechanism is modular, architecture-independent and efficient both in terms of parameters and computation required. Experiments show that networks augmented with our approach systematically improve their classification accuracy and become more robust to clutter. As a result, Wide Residual Networks augmented with our proposal surpasses the state of the art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford dogs, and UEC Food-100.

📄 PDF Abstract BibTeX arXiv:1807.07320

Code (1)

prlz77/attend-and-rectify 공식 구현 pytorch

Tasks

ClassificationGeneral ClassificationImage Classification

Similar Papers 제목 키워드 기반

Not All Attention Is Needed: Gated Attention Network for Sequence Data

2019-12-01 · Lanqing Xue, Xiaopeng Li, Nevin L. Zhang

Although deep neural networks generally have fixed network structures, the concept of dynamic mechanism has drawn more and more attention in recent years. Attention mechanisms compute input-dependent dynamic attention we…

AllSentencetext-classificationText Classification

Co-attending Regions and Detections with Multi-modal Multiplicative Embedding for VQA

2017-11-18 · The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) 2017 11 · Lu, Pan; Li, Hongsheng; Zhang, Wei; Wang 외

Recently, the Visual Question Answering (VQA) task has gained increasing attention in artificial intelligence. Existing VQA methods mainly adopt the visual attention mechanism to associate the input question with corresp…

FormQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering

2017-11-18 · Pan Lu, Hongsheng Li, Wei zhang, Jianyong Wang 외

Recently, the Visual Question Answering (VQA) task has gained increasing attention in artificial intelligence. Existing VQA methods mainly adopt the visual attention mechanism to associate the input question with corresp…

FormVisual Question AnsweringVisual Question Answering (VQA)

Gated Sparse Attention: Combining Computational Efficiency with Training Stability for Long-Context Language Models

2026-01-12 · Alfred Shen, Aaron Shen arxiv

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated att…

Computational Efficiency

System 2 Attention (is something you might need too)

2023-11-20 · Jason Weston, Sainbayar Sukhbaatar

Soft attention in Transformer-based Large Language Models (LLMs) is susceptible to incorporating irrelevant information from the context into its latent representations, which adversely affects next token generations. To…

Math