Pith. sign in

REVIEW 3 cited by

Organizing Background to Explore Latent Classes for Incremental Few-shot Semantic Segmentation

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 2405.19568 v1 pith:FGV2ZGGA submitted 2024-05-29 cs.CV

classification cs.CV
keywords classesnovelembeddingspacebackgroundlearningoinetprototypes
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The goal of incremental Few-shot Semantic Segmentation (iFSS) is to extend pre-trained segmentation models to new classes via few annotated images without access to old training data. During incrementally learning novel classes, the data distribution of old classes will be destroyed, leading to catastrophic forgetting. Meanwhile, the novel classes have only few samples, making models impossible to learn the satisfying representations of novel classes. For the iFSS problem, we propose a network called OINet, i.e., the background embedding space \textbf{O}rganization and prototype \textbf{I}nherit Network. Specifically, when training base classes, OINet uses multiple classification heads for the background and sets multiple sub-class prototypes to reserve embedding space for the latent novel classes. During incrementally learning novel classes, we propose a strategy to select the sub-class prototypes that best match the current learning novel classes and make the novel classes inherit the selected prototypes' embedding space. This operation allows the novel classes to be registered in the embedding space using few samples without affecting the distribution of the base classes. Results on Pascal-VOC and COCO show that OINet achieves a new state of the art.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A 3DGS variant that adds MLP initialization, normal alignment, and region-aware density control reports consistent but modest quality gains over vanilla 3DGS on three standard benchmarks.

  2. Building Lightweight Semantic Segmentation Models for Aerial Images Using Dual Relation Distillation

    eess.IV 2025-06 conditional novelty 4.0 of 10

    A student segmentation network trained with spatial and channel relation distillation from a PSPNet ResNet101 teacher gains about 3 to 5 mIoU points on Vaihingen, Potsdam, and Cityscapes.

  3. A Global-Local Cross-Attention Network for Ultra-high Resolution Remote Sensing Image Semantic Segmentation

    cs.CV 2025-06 reject novelty 3.0 of 10

    GLCANet is a dual-branch global-local attention network that reports top mIoU on DeepGlobe, Vaihingen, and Potsdam, but the method and experiments are internally inconsistent and lack code.

Pith tools