paper-with-me

홈 › Papers

Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers

2022-10-24 · Zhiwei Lin, Zengyu Yang, Yongtao Wang

Unsupervised object discovery (UOD) has recently shown encouraging progress with the adoption of pre-trained Transformer features. However, current methods based on Transformers mainly focus on designing the localization head (e.g., seed selection-expansion and normalized cut) and overlook the importance of improving Transformer features. In this work, we handle UOD task from the perspective of feature enhancement and propose FOReground guidance and MUlti-LAyer feature fusion for unsupervised object discovery, dubbed FORMULA. Firstly, we present a foreground guidance strategy with an off-the-shelf UOD detector to highlight the foreground regions on the feature maps and then refine object locations in an iterative fashion. Moreover, to solve the scale variation issues in object detection, we design a multi-layer feature fusion module that aggregates features responding to objects at different scales. The experiments on VOC07, VOC12, and COCO 20k show that the proposed FORMULA achieves new state-of-the-art results on unsupervised object discovery. The code will be released at https://github.com/VDIGPKU/FORMULA.

📄 PDF Abstract BibTeX arXiv:2210.13053

Code (1)

vdigpku/formula 공식 구현 pytorch

Tasks

Objectobject-detectionObject DetectionObject Discovery

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer

2026-05-24 · Kyoungkook Kang, Gyujin Sim, Sunghyun Cho arxiv

As generative models expand the possibilities of visual content creation, layered image synthesis has emerged as a promising direction for controllable and creative editing. However, existing methods struggle to fully re…

MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human Erasing

2025-08-05 · Jinghan Yu, Junhao Xiao, Zhiyuan Ma, Yue Ma 외 arxiv

Recent years have witnessed the success of diffusion models in image customization tasks. However, existing mask-guided human erasing methods still struggle in complex scenarios such as human-human occlusion, human-objec…

A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation

2018-07-06 · Yang Hu, Andrea Soltoggio, Russell Lock, Steve Carter

In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactive image segmentation. The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that p…

Image SegmentationSegmentationSemantic SegmentationVocal Bursts Valence Prediction

LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model

2024-03-18 · Runhui Huang, Kaixin Cai, Jianhua Han, Xiaodan Liang 외

Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. …

Image GenerationStyle Transfer

Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning

2026-04-10 · Yang Deng, David Mould, Paul L. Rosin, Yu-Kun Lai arxiv

Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized byproduct. This imbalance compromises global…