Hard Attention

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.

Most implemented papers archive 2025-07-28

30 shown of 41 papers with code (100 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Recurrent Models of Visual Attention
  24 Jun 2014 20 repositories listed Syntology ran 7 of 24 samples · 17 unverified · 1 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.
• Dual Attention Networks for Few-Shot Fine-Grained Recognition
  28 Jun 2022 3 repositories listed
  Specifically, 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.
• Deep Attention Recurrent Q-Network
  5 Dec 2015 3 repositories listed
  A 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.
• Learning Texture Transformer Network for Image Super-Resolution
  7 Jun 2020 2 repositories listed Syntology ran 3 of 7 samples · 4 unverified
  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.
• Saccader: Improving Accuracy of Hard Attention Models for Vision
  20 Aug 2019 2 repositories listed
  Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret.
• Exact Hard Monotonic Attention for Character-Level Transduction
  15 May 2019 2 repositories listed
  Our models achieve state-of-the-art performance on morphological inflection.
• Hard Non-Monotonic Attention for Character-Level Transduction
  29 Aug 2018 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  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.
• Overcoming catastrophic forgetting with hard attention to the task
  4 Jan 2018 2 repositories listed
  In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning.
• Center-guided Classifier for Semantic Segmentation of Remote Sensing Images
  21 Mar 2025 1 repository listed
  i.
• Hard-Attention Gates with Gradient Routing for Endoscopic Image Computing
  5 Jul 2024 1 repository listed
  To 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…
• TRIP: Trainable Region-of-Interest Prediction for Hardware-Efficient Neuromorphic Processing on Event-based Vision
  25 Jun 2024 1 repository listed
  We introduced extensive hardware-aware optimizations for TRIP and implemented the hardware-optimized algorithm on the SENECA neuromorphic processor.
• Recurrent Alignment with Hard Attention for Hierarchical Text Rating
  14 Feb 2024 1 repository listed
  To this end, we propose a novel framework for hierarchical text rating utilizing LLMs, which incorporates Recurrent Alignment with Hard Attention (RAHA).
• Mutual Distillation Learning For Person Re-Identification
  12 Jan 2024 1 repository listed
  With the rapid advancements in deep learning technologies, person re-identification (ReID) has witnessed remarkable performance improvements.
• Vamos: Versatile Action Models for Video Understanding
  22 Nov 2023 1 repository listed Syntology ran 7 of 8 samples · 1 unverified
  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…
• Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimation
  18 Aug 2023 1 repository listed
  With 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.
• On the Learning Dynamics of Attention Networks
  25 Jul 2023 1 repository listed
  Attention 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.
• HAT-CL: A Hard-Attention-to-the-Task PyTorch Library for Continual Learning
  18 Jul 2023 1 repository listed
  Catastrophic 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.
• Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosis
  10 Apr 2023 1 repository listed
  Early detection of melanoma is crucial for preventing severe complications and increasing the chances of successful treatment.
• Learning to Perceive in Deep Model-Free Reinforcement Learning
  10 Jan 2023 1 repository listed
  We 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.
• Table Retrieval May Not Necessitate Table-specific Model Design
  19 May 2022 1 repository listed Syntology ran 7 of 12 samples · 5 unverified
  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?"
• Binding Actions to Objects in World Models
  27 Apr 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We study the problem of binding actions to objects in object-factored world models using action-attention mechanisms.
• Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes
  1 Apr 2022 1 repository listed
  Most hard attention models initially observe a complete scene to locate and sense informative glimpses, and predict class-label of a scene based on glimpses.
• A Probabilistic Hard Attention Model For Sequentially Observed Scenes
  15 Nov 2021 1 repository listed
  A visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction.
• Understanding Interlocking Dynamics of Cooperative Rationalization
  26 Oct 2021 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  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…
• Self-Attention Networks Can Process Bounded Hierarchical Languages
  24 May 2021 1 repository listed
  Despite 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…
• AMR Parsing with Action-Pointer Transformer
  29 Apr 2021 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  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.
• FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation
  31 Mar 2021 1 repository listed
  We propose a novel architecture called feedback attention network (FANet) that unifies the previous epoch mask with the feature map of the current training epoch.
• Hard-Attention for Scalable Image Classification
  20 Feb 2021 1 repository listed
  Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale?
• A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization
  3 Jan 2021 1 repository listed
  Moreover, 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.
• AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models
  7 Oct 2020 1 repository listed
  We propose AxFormer, a systematic framework that applies accuracy-driven approximations to create optimized transformer models for a given downstream task.

Syntology lines on 8 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. Read from the graph 2026-09-24.