WaveNet generates realistic raw audio using an autoregressive neural network with dilated convolutions, achieving state-of-the-art naturalness in speech synthesis for English and Mandarin.
hub
Deep Residual Learning for Image Recognition
65 Pith papers cite this work. Polarity classification is still indexing.
65
Pith papers citing it
abstract
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
hub tools
claims ledger
- abstract Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG ne
co-cited works
representative citing papers
Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.
PSR-NQS makes recurrent neural quantum states scalable for variational Monte Carlo by using parallel scan recurrence, reaching accurate results on 52x52 two-dimensional lattices.
Spectral clipping of leading singular values in gradient matrices stabilizes SGD for non-convex problems with heavy-tailed noise and achieves the optimal convergence rate O(K^{(2-2α)/(3α-2)}).
In generalized contrastive learning with imbalanced classes, optimal representations collapse to class means whose angular geometry is determined by class proportions via convex optimization, and extreme imbalance causes all minority classes to collapse to one vector.
Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
Replica calculations fully solve spherical Boltzmann machine ensembles and identify regimes where ensemble learning outperforms standard training, particularly for nearly finite-dimensional data.
Diffusion models show grokking on modular addition by composing periodic operand representations in simple data regimes or by separating arithmetic computation from visual denoising across timesteps in varied regimes.
Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.
Momentum SGD exhibits two distinct EoSS regimes for batch sharpness, stabilizing at 2(1-β)/η for small batches and 2(1+β)/η for large batches, aligning with linear stability thresholds.
Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
HSTU-based generative recommenders with 1.5 trillion parameters scale as a power law with compute up to GPT-3 scale, outperform baselines by up to 65.8% NDCG, run 5-15x faster than FlashAttention2 on long sequences, and improve online A/B metrics by 12.4%.
UMI enables zero-shot deployment of robot manipulation policies trained solely on portable human demonstrations captured with custom handheld grippers, supporting dynamic bimanual tasks across novel environments and objects.
MobileNets introduce depthwise separable convolutions plus width and resolution multipliers to produce efficient CNNs that trade off latency and accuracy for mobile and embedded vision applications.
MS MARCO is a new large-scale machine reading comprehension dataset built from real Bing search queries, human-generated answers, and web passages, supporting three tasks including answer synthesis and passage ranking.
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.
An algorithm trains n-layer networks with O(sqrt(n)) memory via selective recomputation of activations, at the cost of one extra forward pass.
Chakra introduces a portable, interoperable graph-based execution trace format for distributed ML workloads along with supporting tools to standardize performance benchmarking and software-hardware co-design.
StereoPolicy fuses stereo image pairs via a Stereo Transformer on pretrained 2D encoders to boost robotic manipulation policies, showing gains over monocular, RGB-D, point cloud, and multi-view methods in simulations and real-robot tests.
Event-centric waveform foundation models are learned via self-supervised consistency on latent event structures and interactions, yielding improved performance and label efficiency over sequence-based baselines on physiological tasks.
A mean-pool deep set trained on sets of size at most two produces an encoder that generalizes to arbitrary sizes, decoupling representation learning from posterior modeling and making training cost independent of deployment set size N.
A new dataset of hand-drawn circles from 66 writers and 8 pens yields competition results of 64.8% top-1 accuracy for open-set writer identification and 92.7% for pen classification.
A provable adversarial noise amplification theorem under sufficient conditions enables a custom-trained detector that identifies adversarial examples at inference time using enhanced layer-wise noise signals.
ShapeY is a benchmark dataset and nearest-neighbor protocol that measures shape-based recognition in vision models, revealing that even state-of-the-art networks fail to generalize consistently across 3D viewpoints and non-shape appearance changes.
citing papers explorer
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.