Pith. sign in

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

arxiv 2111.11429 v1 pith:FOCF5OEC submitted 2021-11-22 cs.CV

classification cs.CV
keywords learningdetectionmethodstrainingbenchmarkingmodelsrecenttransfer
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Twins: Learn to Predict Unified Representations with Focal Loss

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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.

  2. MPT: Motion Prompt Tuning for Micro-Expression Recognition

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    Motion Prompt Tuning with motion magnification and Gaussian tokenization claims state-of-the-art micro-expression recognition on three benchmarks.

  3. ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads

    cs.CV 2025-06 conditional novelty 6.0 of 10

    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.

  4. Towards more transferable adversarial attack in black-box manner

    cs.LG 2025-05 conditional novelty 6.0 of 10

    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.

Pith tools