Papers › ProgressiveSpinalNet architecture for FC layers

ProgressiveSpinalNet architecture for FC layers

21 Mar 2021arXiv:2103.11373archive 2025-07-28

Praveen Chopra

In deeplearning models the FC (fully connected) layer has biggest important role for classification of the input based on the learned features from previous layers. The FC layers has highest numbers of parameters and fine-tuning these large numbers of parameters, consumes most of the computational resources, so in this paper it is aimed to reduce these large numbers of parameters significantly with improved performance. The motivation is inspired from SpinalNet and other biological architecture. The proposed architecture has a gradient highway between input to output layers and this solves the problem of diminishing gradient in deep networks. In this all the layers receives the input from previous layers as well as the CNN layer output and this way all layers contribute in decision making with last layer. This approach has improved classification performance over the SpinalNet architecture and has SOTA performance on many datasets such as Caltech101, KMNIST, QMNIST and EMNIST. The source code is available at https://github.com/praveenchopra/ProgressiveSpinalNet.

PaperPDFCode

Code

praveenchopra/ProgressiveSpinalNet officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decision MakingFine-Grained Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification Bird-225 Pre trained wide-resnet-101 Accuracy 99.55 #2 of 5 Archive leaderboard report
Fine-Grained Image Classification Caltech-101 Pre trained wide-resnet-101 Accuracy 97.76 #18 of 18 Archive leaderboard report
Fine-Grained Image Classification EMNIST-Digits VGG-5 Accuracy 99.82 #1 of 1 Archive leaderboard report
Fine-Grained Image Classification EMNIST-Letters VGG-5 Accuracy 95.86 #1 of 1 Archive leaderboard report
Fine-Grained Image Classification Fruits-360 Pre trained wide-resnet-101 Accuracy 99.97 #3 of 3 Archive leaderboard report
Fine-Grained Image Classification Kuzushiji-MNIST VGG-5 Accuracy 98.98 #1 of 1 Archive leaderboard report
Fine-Grained Image Classification MNIST Vanilla FC layer only Accuracy 98.19 #1 of 1 Archive leaderboard report
Fine-Grained Image Classification QMNIST VGG-5 Accuracy 99.6867 #1 of 1 Archive leaderboard report
Fine-Grained Image Classification STL-10 Pre trained wide-resnet-101 Accuracy 98.18 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionDense ConnectionsDropoutMax PoolingReLUSGDSoftmax

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