No article text was recorded for this version.
diminishing returns of model depth
Version 1 of 1383 papers431 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis
- Blog: Properties and Potential Applications of Random Functional-Linked Types of Neural Networks
- Blog: Convolutional Neural Networks at Constrained Time Cost
- Blog: Revisiting 3D ResNets for Video Recognition
- Blog: SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation
- Blog: What Affects the Effective Depth of Large Language Models?
- Blog: Very Deep Convolutional Networks for Large-Scale Image Recognition
- Blog: Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention
- Blog: Lighter Stacked Hourglass Human Pose Estimation
- Blog: Automatic Image Annotation Model Using LSTM Approach
- Blog: GRU based Convolutional Neural Network with Initialized Filters for Text Classification
- Blog: PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation
- Blog: Revisiting Vision Transformer from the View of Path Ensemble
- Blog: Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Blog: Exploiting Depth and Highway Connections in Convolutional Recurrent Deep Neural Networks for Speech Recognition
- Blog: Fose: Fusion of One-Step Diffusion and End-to-End Network for Pansharpening
- Blog: The Depth-to-Width Interplay in Self-Attention
- Blog: Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model
- Blog: When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data
- Blog: Exploring Transformers for Large-Scale Speech Recognition
- Blog: Deep photonic reservoir computing recurrent network
- Blog: Highway-LSTM and Recurrent Highway Networks for Speech Recognition
- Blog: Application of a Two-Dimensional Regression Network Algorithm Model Based on Local Constraints in Human Motion Recognition
- Blog: MomentsNet: a simple learning-free method for binary image recognition
- Blog: The 4th Dimension for Scaling Model Size
- Blog: Shortcut Sequence Tagging
- Blog: Sparsely Connected Convolutional Networks
- Blog: Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data
- Blog: Low-Light Object Tracking: A Benchmark
- Blog: Image Super-Resolution Using Deep Convolutional Networks.
- Blog: An Empirical Exploration of Skip Connections for Sequential Tagging
- Blog: Attention-Based Extraction of Structured Information from Street View Imagery
- Blog: Very Deep Convolutional Networks for Natural Language Processing
- Blog: Nonlinear Approximation via Compositions
- Blog: The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018
- Blog: Using Deep Belief Nets for Chinese Named Entity Categorization
- Blog: Attention Based Feature Fusion For Multi-Agent Collaborative Perception
- Blog: Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modelling
- Blog: What can we learn from misclassified ImageNet images?
- Blog: GeoMamba: Towards Multi-granular POI Recommendation with Geographical State Space Model
- Blog: Richness of Deep Echo State Network Dynamics
- Blog: Resolving the Doubts: On the Construction and Use of ResNets for Side-Channel Analysis
- Blog: JLBert: Japanese Light BERT for Cross-Domain Short Text Classification
- Blog: Learned Optimizers for Analytic Continuation
- Blog: BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation
- Blog: Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution
- Blog: ListConRanker: A Contrastive Text Reranker with Listwise Encoding
- Blog: Convolutional-Recurrent Neural Networks for Speech Enhancement
- Blog: Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints
- Blog: Densely Connected Networks for Conversational Speech Recognition
- Blog: Interpreting Twitter User Geolocation
- Blog: CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal
- Blog: EASRec: Elastic Architecture Search for Efficient Long-term Sequential Recommender Systems
- Blog: A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality Perception
- Blog: Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice
- Blog: DCANet: Learning Connected Attentions for Convolutional Neural Networks
- Blog: SJTU-AISPEECH System for VoxCeleb Speaker Recognition Challenge 2022
- Blog: Overfitting in Histopathology Model Training: The Need for Customized Architectures
- Blog: The NiuTrans System for the WMT21 Efficiency Task
- Blog: Non-Iterative Phase Retrieval With Cascaded Neural Networks
Showing 60 of 383 papers.
History & citation
Current · Permanent link
- The Depth Saturation Problem in Neural Architectures merged into this direction (89% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_diminishing_returns_of_model_depth_41460e99,
title = {diminishing returns of model depth},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/diminishing-returns-of-model-depth/rdr_41460e99a07d4f39b15126e06ad1dda4},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_diminishing_returns_of_model_depth_41460e99_v1,
title = {diminishing returns of model depth},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/diminishing-returns-of-model-depth/rdr_41460e99a07d4f39b15126e06ad1dda4/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}