REVIEW 4 cited by
Benchmarking Detection Transfer Learning with Vision Transformers
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
read the original abstract
Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial when new architectures, such as Vision Transformer (ViT) models, arrive. These difficulties (e.g., architectural incompatibility, slow training, high memory consumption, unknown training formulae, etc.) have prevented recent studies from benchmarking detection transfer learning with standard ViT models. In this paper, we present training techniques that overcome these challenges, enabling the use of standard ViT models as the backbone of Mask R-CNN. These tools facilitate the primary goal of our study: we compare five ViT initializations, including recent state-of-the-art self-supervised learning methods, supervised initialization, and a strong random initialization baseline. Our results show that recent masking-based unsupervised learning methods may, for the first time, provide convincing transfer learning improvements on COCO, increasing box AP up to 4% (absolute) over supervised and prior self-supervised pre-training methods. Moreover, these masking-based initializations scale better, with the improvement growing as model size increases.
Forward citations
Cited by 4 Pith papers
-
Twins: Learn to Predict Unified Representations with Focal Loss
Channel-wise concatenation of SigLIP2 and Flux VAE features into one token, trained with a focal-style flow-matching loss, yields a unified representation with 1.59 gFID on ImageNet 256 and VAE-level reconstruction.
-
MPT: Motion Prompt Tuning for Micro-Expression Recognition
Motion Prompt Tuning with motion magnification and Gaussian tokenization claims state-of-the-art micro-expression recognition on three benchmarks.
-
ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads
ViT-Split freezes a vision foundation model and adds a copied task head plus a multi-scale prior head, matching or beating prior adapters with fewer parameters and up to 4x faster training.
-
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.
Discussion (0). Continue with ORCID to comment.