{"total":21,"rows":[{"id":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14,"area":null},{"id":"2308.04073","title":"Learning Specialized Activation Functions for Physics-informed Neural Networks","created":"2023-08-08","cited_by_count":14,"area":null},{"id":"2407.07564","title":"Trainable Highly-expressive Activation Functions","created":"2024-07-10","cited_by_count":6,"area":null},{"id":"2108.12313","title":"TE-YOLOF: Tiny and efficient YOLOF for blood cell detection","created":"2021-08-27","cited_by_count":5,"area":null},{"id":"2109.04386","title":"ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions","created":"2021-09-09","cited_by_count":5,"area":null},{"id":"2309.00216","title":"Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation","created":"2023-09-01","cited_by_count":4,"area":null},{"id":"2203.11700","title":"Exploring Linear Feature Disentanglement For Neural Networks","created":"2022-03-22","cited_by_count":3,"area":null},{"id":"2207.06413","title":"MorphoActivation: Generalizing ReLU activation function by mathematical morphology","created":"2022-07-13","cited_by_count":3,"area":null},{"id":"2109.00903","title":"Effect of the output activation function on the probabilities and errors in medical image segmentation","created":"2021-09-02","cited_by_count":1,"area":null},{"id":"2109.07878","title":"A Medical Pre-Diagnosis System for Histopathological Image of Breast Cancer","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2109.13210","title":"SAU: Smooth activation function using convolution with approximate identities","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2305.10964","title":"Learning Activation Functions for Sparse Neural Networks","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2310.02776","title":"Dynamic Shuffle: An Efficient Channel Mixture Method","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2504.08217","title":"DrivAer Transformer: A high-precision and fast prediction method for vehicle aerodynamic drag coefficient based on the DrivAerNet++ dataset","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2111.14349","title":"First Power Linear Unit with Sign","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2407.00131","title":"RepAct: The Re-parameterizable Adaptive Activation Function","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2407.01012","title":"Swish-T : Enhancing Swish Activation with Tanh Bias for Improved Neural Network Performance","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2408.03599","title":"Activations Through Extensions: A Framework To Boost Performance Of Neural Networks","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2502.06119","title":"An Appearance Defect Detection Method for Cigarettes Based on C-CenterNet","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2603.26096","title":"AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2607.10593","title":"AutoNorm: Understanding Adaptive Normalization in Transformers through Differentiable Gating","created":"2026-07-12","cited_by_count":0,"area":null}],"next_cursor":null}