paper-with-me

홈 › Papers

The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models

2024-04-18 · Cheng Shi, Sibei Yang

Foundation models, pre-trained on a large amount of data have demonstrated impressive zero-shot capabilities in various downstream tasks. However, in object detection and instance segmentation, two fundamental computer vision tasks heavily reliant on extensive human annotations, foundation models such as SAM and DINO struggle to achieve satisfactory performance. In this study, we reveal that the devil is in the object boundary, \textit{i.e.}, these foundation models fail to discern boundaries between individual objects. For the first time, we probe that CLIP, which has never accessed any instance-level annotations, can provide a highly beneficial and strong instance-level boundary prior in the clustering results of its particular intermediate layer. Following this surprising observation, we propose $\textbf{Zip}$ which $\textbf{Z}$ips up CL$\textbf{ip}$ and SAM in a novel classification-first-then-discovery pipeline, enabling annotation-free, complex-scene-capable, open-vocabulary object detection and instance segmentation. Our Zip significantly boosts SAM's mask AP on COCO dataset by 12.5% and establishes state-of-the-art performance in various settings, including training-free, self-training, and label-efficient finetuning. Furthermore, annotation-free Zip even achieves comparable performance to the best-performing open-vocabulary object detecters using base annotations. Code is released at https://github.com/ChengShiest/Zip-Your-CLIP

📄 PDF Abstract BibTeX arXiv:2404.11957

Code (1)

chengshiest/zip-your-clip 공식 구현 pytorch

Tasks

Instance SegmentationObjectobject-detectionObject DetectionOpen-vocabulary object detectionOpen Vocabulary Object DetectionSemantic Segmentation

Methods 이 논문이 사용한 방법론

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…
Residual Connection 설명 없음
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 $x$…
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Cell Instance Segmentation: The Devil Is in the Boundaries

2025-10-10 · Peixian Liang, Yifan Ding, Yizhe Zhang, Jianxu Chen 외 arxiv

State-of-the-art (SOTA) methods for cell instance segmentation are based on deep learning (DL) semantic segmentation approaches, focusing on distinguishing foreground pixels from background pixels. In order to identify c…

Semantic SegmentationInstance Segmentation

Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations

2019-04-16 · CVPR 2019 6 · David Acuna, Amlan Kar, Sanja Fidler

We tackle the problem of semantic boundary prediction, which aims to identify pixels that belong to object(class) boundaries. We notice that relevant datasets consist of a significant level of label noise, reflecting the…

Semantic Segmentation

The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation

2020-11-26 · Myungchul Kim, Sanghyun Woo, Dahun Kim, In So Kweon

Pursuing a more coherent scene understanding towards real-time vision applications, single-stage instance segmentation has recently gained popularity, achieving a simpler and more efficient design than its two-stage coun…

Instance SegmentationScene UnderstandingSegmentationSemantic Segmentation

FreeSOLO: Learning to Segment Objects without Annotations

2022-02-24 · CVPR 2022 1 · Xinlong Wang, Zhiding Yu, Shalini De Mello, Jan Kautz 외

Instance segmentation is a fundamental vision task that aims to recognize and segment each object in an image. However, it requires costly annotations such as bounding boxes and segmentation masks for learning. In this w…

Instance Segmentationobject-detectionObject DetectionSegmentation+2

ASIST: Annotation-free synthetic instance segmentation and tracking for microscope video analysis

2020-11-02 · Quan Liu, Isabella M. Gaeta, Mengyang Zhao, Ruining Deng 외

Instance object segmentation and tracking provide comprehensive quantification of objects across microscope videos. The recent single-stage pixel-embedding based deep learning approach has shown its superior performance …

Generative Adversarial NetworkImage SegmentationInstance SegmentationSegmentation+1