PatchNet: Unsupervised Object Discovery based on Patch Embedding
We demonstrate that frequently appearing objects can be discovered by training randomly sampled patches from a small number of images (100 to 200) by self-supervision. Key to this approach is the pattern space, a latent space of patterns that represents all possible sub-images of the given image data. The distance structure in the pattern space captures the co-occurrence of patterns due to the frequent objects. The pattern space embedding is learned by minimizing the contrastive loss between randomly generated adjacent patches. To prevent the embedding from learning the background, we modulate the contrastive loss by color-based object saliency and background dissimilarity. The learned distance structure serves as object memory, and the frequent objects are simply discovered by clustering the pattern vectors from the random patches sampled for inference. Our image representation based on image patches naturally handles the position and scale invariance property that is crucial to multi-object discovery. The method has been proven surprisingly effective, and successfully applied to finding multiple human faces and bodies from natural images.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringMulti-object discoveryObjectObject DiscoverySimilar Papers 제목 키워드 기반
PatchNet -- Short-range Template Matching for Efficient Video Processing
Object recognition is a fundamental problem in many video processing tasks, accurately locating seen objects at low computation cost paves the way for on-device video recognition. We propose PatchNet, an efficient convol…
Objectobject-detectionObject DetectionObject Recognition+5Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification
While discriminative local features have been shown effective in solving the person re-identification problem, they are limited to be trained on fully pairwise labelled data which is expensive to obtain. In this work, we…
Person Re-IdentificationUnsupervised Person Re-IdentificationPatchNet: A Tool for Deep Patch Classification
This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure tha…
ClassificationDeep LearningGeneral ClassificationMedicalPatchNet: A Patch-Based Self-Explainable AI Architecture for Chest X-ray Classification
Deep neural networks excel in radiological image classification but frequently suffer from poor interpretability, limiting clinical acceptance. We present MedicalPatchNet, an inherently self-explainable architecture for …
Image ClassificationFlightPatchNet: Multi-Scale Patch Network with Differential Coding for Flight Trajectory Prediction
Accurate multi-step flight trajectory prediction plays an important role in Air Traffic Control, which can ensure the safety of air transportation. Two main issues limit the flight trajectory prediction performance of ex…
PredictionTrajectory Prediction