Browse State-of-the-Art › Hard Attention
Hard Attention
41 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
No dataset record in the archive lists this task.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 100 · with a code link: 41 · where Syntology ran a sample: 9 (6 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (9 of 100 tagged: 6 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 100 of 100, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
24 Jun 2014 20 repositories listed Syntology 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 4 honoured, 2 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 24 harvested samples) · 2 pointer-only (licence)Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels.
-
28 Jun 2022 3 repositories listedSpecifically, by producing attention guidance from deep activations of input images, our hard-attention is realized by keeping a few useful deep descriptors and forming them as a bag of multi-instance learning.
-
5 Dec 2015 3 repositories listedA deep learning approach to reinforcement learning led to a general learner able to train on visual input to play a variety of arcade games at the human and superhuman levels.
-
7 Jun 2020 2 repositories listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 1 pointer-only (licence)In this paper, we propose a novel Texture Transformer Network for Image Super-Resolution (TTSR), in which the LR and Ref images are formulated as queries and keys in a transformer, respectively.
-
20 Aug 2019 2 repositories listedAlthough deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret.
-
15 May 2019 2 repositories listedOur models achieve state-of-the-art performance on morphological inflection.
-
29 Aug 2018 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)We compare soft and hard non-monotonic attention experimentally and find that the exact algorithm significantly improves performance over the stochastic approximation and outperforms soft attention.
-
4 Jan 2018 2 repositories listedIn this paper, we propose a task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning.
-
21 Mar 2025 1 repository listedi. e., larger intraclass variance, which makes semantic segmentation for remote sensing images more challenging.
-
5 Jul 2024 1 repository listedTo address overfitting and enhance model generalization in gastroenterological polyp size assessment, our study introduces Feature-Selection Gates (FSG) or Hard-Attention Gates (HAG) alongside Gradient Routing (GR) for…
-
25 Jun 2024 1 repository listedWe introduced extensive hardware-aware optimizations for TRIP and implemented the hardware-optimized algorithm on the SENECA neuromorphic processor.
-
14 Feb 2024 1 repository listedTo this end, we propose a novel framework for hierarchical text rating utilizing LLMs, which incorporates Recurrent Alignment with Hard Attention (RAHA).
-
12 Jan 2024 1 repository listedWith the rapid advancements in deep learning technologies, person re-identification (ReID) has witnessed remarkable performance improvements.
-
22 Nov 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 5 pointer-only (licence)To interpret the important text evidence for question answering, we generalize the concept bottleneck model to work with tokens and nonlinear models, which uses hard attention to select a small subset of tokens from the…
-
18 Aug 2023 1 repository listedWith the rapid development of deep learning technology in the past decade, appearance-based gaze estimation has attracted great attention from both computer vision and human-computer interaction research communities.
-
25 Jul 2023 1 repository listedAttention models are typically learned by optimizing one of three standard loss functions that are variously called -- soft attention, hard attention, and latent variable marginal likelihood (LVML) attention.
-
18 Jul 2023 1 repository listedCatastrophic forgetting, the phenomenon in which a neural network loses previously obtained knowledge during the learning of new tasks, poses a significant challenge in continual learning.
-
10 Apr 2023 1 repository listedEarly detection of melanoma is crucial for preventing severe complications and increasing the chances of successful treatment.
-
10 Jan 2023 1 repository listedWe investigate whether a model with these characteristics is capable of achieving similar performance to state-of-the-art model-free RL agents that access the full input observation.
-
19 May 2022 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified (of 12 harvested samples) · 6 pointer-only (licence)In this work, we focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval, or can a simpler text-based model be effectively used to achieve a similar result?"
-
27 Apr 2022 1 repository listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)We study the problem of binding actions to objects in object-factored world models using action-attention mechanisms.
-
1 Apr 2022 1 repository listedMost hard attention models initially observe a complete scene to locate and sense informative glimpses, and predict class-label of a scene based on glimpses.
-
15 Nov 2021 1 repository listedA visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction.
-
26 Oct 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)The selection mechanism is commonly integrated into the model itself by specifying a two-component cascaded system consisting of a rationale generator, which makes a binary selection of the input features (which is the…
-
24 May 2021 1 repository listedDespite their impressive performance in NLP, self-attention networks were recently proved to be limited for processing formal languages with hierarchical structure, such as Dyckₖ, the language consisting of well-nested…
-
29 Apr 2021 1 repository listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)In this work, we propose a transition-based system that combines hard-attention over sentences with a target-side action pointer mechanism to decouple source tokens from node representations and address alignments.
-
31 Mar 2021 1 repository listedWe propose a novel architecture called feedback attention network (FANet) that unifies the previous epoch mask with the feature map of the current training epoch.
-
20 Feb 2021 1 repository listedCan we leverage high-resolution information without the unsustainable quadratic complexity to input scale?
-
3 Jan 2021 1 repository listedMoreover, our temporal semi-soft and hard attention modules, calculating two attention scores for each video snippet, help to focus on the less discriminative frames of an action to capture the full action boundary.
-
7 Oct 2020 1 repository listedWe propose AxFormer, a systematic framework that applies accuracy-driven approximations to create optimized transformer models for a given downstream task.
-
8 Oct 2019 1 repository listed
-
19 Aug 2019 1 repository listed
-
5 Jul 2019 1 repository listed
-
3 Jun 2019 1 repository listed
-
1 Oct 2018 1 repository listed
-
1 Aug 2018 1 repository listed
-
10 Jul 2018 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
1 Jul 2018 1 repository listed
-
31 Jan 2018 1 repository listed
-
4 Nov 2016 1 repository listed
-
8 Jun 2016 1 repository listed
-
Comparison of different Unique hard attention transformer models by the formal languages they can recognize3 Jun 2025 0 repositories listed
-
Characterizing the Expressivity of Transformer Language Models29 May 2025 0 repositories listed
-
Exact Expressive Power of Transformers with Padding25 May 2025 0 repositories listed
-
Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision19 May 2025 0 repositories listed
-
NoPE: The Counting Power of Transformers with No Positional Encodings16 May 2025 0 repositories listed
-
Neuroevolution of Self-Attention Over Proto-Objects30 Apr 2025 0 repositories listed
-
AttentionDrop: A Novel Regularization Method for Transformer Models16 Apr 2025 0 repositories listed
-
Unique Hard Attention: A Tale of Two Sides18 Mar 2025 0 repositories listed
-
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers4 Feb 2025 0 repositories listed
-
Ehrenfeucht-Haussler Rank and Chain of Thought22 Jan 2025 0 repositories listed
-
Simulating Hard Attention Using Soft Attention13 Dec 2024 0 repositories listed
-
Transformers in Uniform TC⁰20 Sep 2024 0 repositories listed
-
Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removal7 Aug 2024 0 repositories listed
-
Transformers as Transducers2 Apr 2024 0 repositories listed
-
GQHAN: A Grover-inspired Quantum Hard Attention Network25 Jan 2024 0 repositories listed
-
Multi-View Unsupervised Image Generation with Cross Attention Guidance7 Dec 2023 0 repositories listed
-
Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters30 Nov 2023 0 repositories listed
-
Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages21 Oct 2023 0 repositories listed
-
Language-Guided Reinforcement Learning for Hard Attention in Few-Shot Learning11 Oct 2023 0 repositories listed
-
Logical Languages Accepted by Transformer Encoders with Hard Attention5 Oct 2023 0 repositories listed
-
Average-Hard Attention Transformers are Constant-Depth Uniform Threshold Circuits6 Aug 2023 0 repositories listed
-
MESAHA-Net: Multi-Encoders based Self-Adaptive Hard Attention Network with Maximum Intensity Projections for Lung Nodule Segmentation in CT Scan4 Apr 2023 0 repositories listed
-
Dual Attention Model with Reinforcement Learning for Classification of Histology Whole-Slide Images19 Feb 2023 0 repositories listed
-
Deep Pneumonia: Attention-Based Contrastive Learning for Class-Imbalanced Pneumonia Lesion Recognition in Chest X-rays23 Jul 2022 0 repositories listed
-
Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity13 Apr 2022 0 repositories listed
-
4 Feb 2022 0 repositories listed
-
You Only Need One Model for Open-domain Question Answering14 Dec 2021 0 repositories listed
-
CLAWS: Contrastive Learning with hard Attention and Weak Supervision1 Dec 2021 0 repositories listed
-
Sharp Attention for Sequence to Sequence Learning29 Sep 2021 0 repositories listed
-
Specialized Transformers: Faster, Smaller and more Accurate NLP Models29 Sep 2021 0 repositories listed
-
Saturated Transformers are Constant-Depth Threshold Circuits30 Jun 2021 0 repositories listed
-
Multimodal Emergent Fake News Detection via Meta Neural Process Networks22 Jun 2021 0 repositories listed
-
Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification28 Apr 2021 0 repositories listed
-
A study of latent monotonic attention variants30 Mar 2021 0 repositories listed
-
Hard Attention Control By Mutual Information Maximization10 Mar 2021 0 repositories listed
-
Achieving Explainability in a Visual Hard Attention Model through Content Prediction1 Jan 2021 0 repositories listed
-
Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks1 Jan 2021 0 repositories listed
-
AMR Parsing with Action-Pointer Transformer24 Nov 2020 0 repositories listed
-
DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors25 Jun 2020 0 repositories listed
-
MultiResolution Attention Extractor for Small Object Detection10 Jun 2020 0 repositories listed
-
3 Apr 2020 0 repositories listed
-
Improved Attention Models for Memory Augmented Neural Network Adaptive Controllers19 Mar 2020 0 repositories listed
-
Upper, Middle and Lower Region Learning for Facial Action Unit Detection10 Feb 2020 0 repositories listed
-
Robust Brain Magnetic Resonance Image Segmentation for Hydrocephalus Patients: Hard and Soft Attention12 Jan 2020 0 repositories listed
-
1 Jan 2020 0 repositories listed
-
Text as Environment: A Deep Reinforcement Learning Text Readability Assessment Model12 Dec 2019 0 repositories listed
-
Effect of choice of probability distribution, randomness, and search methods for alignment modeling in sequence-to-sequence text-to-speech synthesis using hard alignment28 Oct 2019 0 repositories listed
-
Object Guided External Memory Network for Video Object Detection1 Oct 2019 0 repositories listed
-
Look Harder: A Neural Machine Translation Model with Hard Attention1 Jul 2019 0 repositories listed
-
Theoretical Limitations of Self-Attention in Neural Sequence Models16 Jun 2019 0 repositories listed
-
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training13 Jun 2019 0 repositories listed
-
Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams3 Apr 2019 0 repositories listed
-
A Differentiable Self-disambiguated Sense Embedding Model via Scaled Gumbel Softmax27 Sep 2018 0 repositories listed
-
Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts1 Sep 2018 0 repositories listed
-
Hierarchical Multi-scale Attention Networks for Action Recognition25 Aug 2017 0 repositories listed
-
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing13 Jun 2017 0 repositories listed
-
Learning Hard Alignments with Variational Inference16 May 2017 0 repositories listed
-
Word Representation Models for Morphologically Rich Languages in Neural Machine Translation14 Jun 2016 0 repositories listed
-
Hierarchical Memory Networks24 May 2016 0 repositories listed
Syntology lines on 9 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections