Pith. sign in

REVIEW 4 cited by

Frustratingly Simple Few-Shot Object Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2003.06957 v1 pith:SUJQIJ3O submitted 2020-03-16 cs.CV

Xin Wang , Thomas E. Huang , Trevor Darrell , Joseph E. Gonzalez , Fisher Yu This is my paper · ORCID
classification cs.CV
keywords benchmarksapproachfine-tuningdetectionexamplesexistingfew-shotmeta-learning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the evaluation protocols by sampling multiple groups of training examples to obtain stable comparisons and build new benchmarks based on three datasets: PASCAL VOC, COCO and LVIS. Again, our fine-tuning approach establishes a new state of the art on the revised benchmarks. The code as well as the pretrained models are available at https://github.com/ucbdrive/few-shot-object-detection.

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. Visual Textualization for Image Prompted Object Detection

    cs.CV 2025-06 conditional novelty 7.0 of 10

    Visual textualization projects support images into the text feature space and prompts an unmodified OVLM, achieving strong few-shot and open-set detection results.

  2. Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection

    cs.CV 2026-08 conditional novelty 6.0 of 10

    VLM-synthesized foreground and background images plus feature noise improve few-shot detection accuracy on six cross-domain benchmarks.

  3. Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    CCDM metrics achieve perfect Spearman correlation of 1.0 with YOLOv8 mAP on VisDrone-DET synthetic sets, outperforming prior synthetic-image metrics.

  4. Few-Shot Learning in Video and 3D Object Detection: A Survey

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A survey of few-shot learning for video and 3D object detection that reviews architectures, losses, and training strategies, but contains numerous citation errors and unsupported performance claims.

Pith tools