REVIEW 10 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Identity Mappings in Deep Residual Networks
read the original abstract
Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. A series of ablation experiments support the importance of these identity mappings. This motivates us to propose a new residual unit, which makes training easier and improves generalization. We report improved results using a 1001-layer ResNet on CIFAR-10 (4.62% error) and CIFAR-100, and a 200-layer ResNet on ImageNet. Code is available at: https://github.com/KaimingHe/resnet-1k-layers
Forward citations
Cited by 10 Pith papers
-
Density estimation using Real NVP
Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.
-
Generating Long Sequences with Sparse Transformers
Sparse Transformers factorize attention to handle sequences tens of thousands long, achieving new SOTA density modeling on Enwik8, CIFAR-10, and ImageNet-64.
-
Wide Residual Networks
Wide residual networks achieve higher accuracy and faster training than very deep thin residual networks by increasing width and decreasing depth, setting new state-of-the-art results on CIFAR, SVHN, and ImageNet.
-
Training Deep Nets with Sublinear Memory Cost
An algorithm trains n-layer networks with O(sqrt(n)) memory via selective recomputation of activations, at the cost of one extra forward pass.
-
CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry
CascadeFormer tapers Transformer width with depth based on gradient fan-in asymmetry to match uniform baselines in perplexity while cutting latency 8.6%.
-
SGDR: Stochastic Gradient Descent with Warm Restarts
SGDR uses periodic warm restarts of the learning rate in SGD to reach new state-of-the-art error rates of 3.14% on CIFAR-10 and 16.21% on CIFAR-100.
-
SORA: Free Second-Order Attacks in Fast Adversarial Training
SORA is an adaptive step-size adversarial training algorithm that formalizes epsilon overfitting, introduces the PertAlign metric to predict catastrophic overfitting, and dynamically adjusts perturbations to achieve s...
-
mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters
Manifold-constrained multi-stream mixing plus per-stream adapters improves SSM language model validation loss from 6.3507 to 6.1353 and perplexity from 572.91 to 461.88 on WikiText-2.
-
ActiNet: An Open-Source Tool for Activity Intensity Classification of Wrist-Worn Accelerometry Using Self-Supervised Deep Learning
ActiNet, consisting of a self-supervised 18-layer ResNet-V2 model followed by HMM smoothing, achieves mean macro F1 of 0.82 and Cohen's kappa of 0.86 on wrist accelerometer data from 151 participants, outperforming a ...
-
Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems
Experiments show that shifted-ReLU layers can replace batch-normalization in single-bit-weight wide residual networks on CIFAR-10/100 and ImageNet without consistent accuracy penalty.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.