dhkim0225 1day_1paper issues

dhkim0225 / 1day_1paper

read 1 paper everyday (only weekday)

53 stars 1 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

RESTART

#134 dhkim0225 opened 1 year ago
2
[103] Understanding Dimensional Collapse in Contrastive Self-supervised Learning (DirectCLR)

#133 dhkim0225 opened 1 year ago
0
[102] TRT-ViT: TensorRT-oriented Vision Transformer

#132 dhkim0225 opened 1 year ago
0
[101] SepViT: Separable Vision Transformer

#131 dhkim0225 opened 1 year ago
0
[100] MobileViT v1, v2, v3

#130 dhkim0225 opened 1 year ago
0
[99] Fisher SAM: Information Geometry and Sharpness Aware Minimisation

#129 dhkim0225 opened 1 year ago
0
[98] ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks

#128 dhkim0225 opened 1 year ago
0
[97] Sharpness-Aware Minimization for Efficiently Improving Generalization (SAM)

#127 dhkim0225 opened 1 year ago
0
[96] Sharp Minima Can Generalize For Deep Nets

#126 dhkim0225 opened 1 year ago
0
[95] CoCa: Contrastive Captioners are Image-Text Foundation Models

#125 dhkim0225 opened 2 years ago
0
[94] Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks

#124 dhkim0225 opened 2 years ago
0
[93] Grounded Language-Image Pre-training (GLIP)

#123 dhkim0225 opened 2 years ago
0
업데이트 뜸해집니다.

#122 dhkim0225 closed 2 years ago
0
[92] Revisiting Multi-Scale Feature Fusion for Semantic Segmentation

#121 dhkim0225 opened 2 years ago
0
[91] Three things everyone should know about Vision Transformers

#120 dhkim0225 opened 2 years ago
0
[90] Exploring Plain Vision Transformer Backbones for Object Detection

#119 dhkim0225 opened 2 years ago
0
[89] Sparse Instance Activation for Real-Time Instance Segmentation (SparseInst)

#118 dhkim0225 opened 2 years ago
0
[88] Training Compute-Optimal Large Language Models (Chinchilla)

#117 dhkim0225 opened 2 years ago
0
[87] PaLM: Scaling Language Modeling with Pathways

#116 dhkim0225 opened 2 years ago
0
[86] Pathways: Asynchronous Distributed Dataflow for ML

#115 dhkim0225 opened 2 years ago
0
[85] When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

#114 dhkim0225 opened 2 years ago
0
[84] A Loss Curvature Perspective on Training Instability in Deep Learning

#113 dhkim0225 opened 2 years ago
0
[83] Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (RepLKNet)

#112 dhkim0225 opened 2 years ago
0
[82] Efficient Language Modeling with Sparse all-MLP (sMLP)

#111 dhkim0225 opened 2 years ago
0
[81] Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting

#110 dhkim0225 opened 2 years ago
0
[80] cosFormer: Rethinking Softmax in Attention

#109 dhkim0225 opened 2 years ago
0
[79] Visualizing the Loss Landscape of Neural Nets

#108 dhkim0225 opened 2 years ago
0
[78] Understanding Failure Modes of Self-Supervised Learning

#107 dhkim0225 opened 2 years ago
0
[77] DeepNet: Scaling Transformers to 1,000 Layers

#106 dhkim0225 opened 2 years ago
0
[76] Visual Attention Network (VAN)

#105 dhkim0225 opened 2 years ago
0
[75] Vision-Language Pre-Training with Triple Contrastive Learning

#104 dhkim0225 opened 2 years ago
0
[74] Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations (EVIT)

#103 dhkim0225 opened 2 years ago
0
[73] Why Do Better Loss Functions Lead to Less Transferable Features?

#102 dhkim0225 opened 2 years ago
0
[72] Similarity of Neural Network Representations Revisited (CKA)

#101 dhkim0225 opened 2 years ago
0
[71] SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

#100 dhkim0225 opened 2 years ago
0
[70] Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision (SEER)

#99 dhkim0225 opened 2 years ago
0
[69] How do vision transformers work? (AlterNet)

#98 dhkim0225 opened 2 years ago
2
[68] Generative multitask learning mitigates target-causing confounding

#97 dhkim0225 opened 2 years ago
0
[67] Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer (TextTranSpotter, TTS)

#96 dhkim0225 opened 2 years ago
0
[67] Predicting the rules behind - Deep Symbolic Regression for Recurrent Sequences

#95 dhkim0225 closed 2 years ago
0
[66] Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

#94 dhkim0225 opened 2 years ago
0
[65] data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

#93 dhkim0225 opened 2 years ago
0
[64] Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet? (RELICv2)

#92 dhkim0225 opened 2 years ago
0
[63] Generalized Category Discovery (GCD)

#91 dhkim0225 opened 2 years ago
0
[62] Detecting Twenty-thousand Classes using Image-level Supervision (Detic)

#90 dhkim0225 opened 2 years ago
0
[61] A ConvNet for the 2020s (ConvNeXts)

#89 dhkim0225 opened 2 years ago
0
[60] Robust Contrastive Learning Using Negative Samples with Diminished Semantics

#88 dhkim0225 opened 2 years ago
0
[59] Stochastic Layers in Vision Transformers

#87 dhkim0225 opened 2 years ago
0
[58] Sound and Visual Representation Learning with Multiple Pretraining Tasks

#86 dhkim0225 opened 2 years ago
0
[57] Vision Transformer with Deformable Attention (DAT)

#85 dhkim0225 opened 2 years ago
0