REVIEW 8 cited by
Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
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
abstract
In this paper I investigate the effect of random seed selection on the accuracy when using popular deep learning architectures for computer vision. I scan a large amount of seeds (up to $10^4$) on CIFAR 10 and I also scan fewer seeds on Imagenet using pre-trained models to investigate large scale datasets. The conclusions are that even if the variance is not very large, it is surprisingly easy to find an outlier that performs much better or much worse than the average.
Forward citations
Cited by 8 Pith papers
-
Pretrain on Small Synthetic Data, Scale Large for Free: Symmetry-Aware Foundation Model for Logic Rule Induction
A canonical decoder that reads literal scores yields exactly equivariant discrete DNF rules under the full rule-induction symmetry group, letting a small-data pretrained inducer transfer to schemas of up to 1024 atoms.
-
GLID: Gated Local Intrinsic Dimension Repairs the Blind Spots of Face-Forgery Detectors
A gated, training-free local-intrinsic-dimension profile from a frozen ViT repairs face-forgery detectors on unseen GAN and diffusion axes, lifting generation-family AUC by +0.084.
-
Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters
In a fully tractable 12K Llama-style model, grokking is a conditional fragile phase transition gated by coverage (tracking modulus more than structure), weight decay, and floating-point reduction order, so evidence mu...
-
Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs
LUViT jointly pretrains a ViT with masked auto-encoding and LoRA adapters in a frozen LLM block, reporting +0.4% ImageNet-1K accuracy and up to +2.2% on ImageNet-A over its own MAE baseline.
-
Towards more transferable adversarial attack in black-box manner
ScorePGD and U-ScorePGD craft transferable black-box adversarial examples by optimizing the log-likelihood of a time-dependent classifier on a single noisy sample, matching or beating DiffPGD at roughly 10x lower cost.
-
Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment
Perceptually initializing a CLIP vision encoder with NIGHTS triplet judgments before YFCC15M contrastive training improves zero-shot accuracy and retrieval over an identical random-start baseline.
-
Algorithmic Tradeoffs, Applied NLP, and the State-of-the-Art Fallacy
On a large corpus of UC admissions essays, correlated topic models plus linear regression matched or beat word embeddings, BERTopic, XGBoost, CNNs, and LSTM-based models, while LLM-generated essays showed strong but h...
-
Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion
A single diffusion-plus-residual-RL policy, trained on four robot morphologies using zero-padded observations and actions, outperforms per-robot PPO baselines in simulation and transfers to real robots.
Discussion (0). Sign in to comment.