Object Discovery
74 papers with code • 0 benchmarks • 2 datasets
Object Discovery is the task of identifying previously unseen objects.
Source: Unsupervised Object Discovery and Segmentation of RGBD-images
Benchmarks
These leaderboards are used to track progress in Object Discovery
Latest papers with no code
Label-Efficient 3D Object Detection For Road-Side Units
We address this challenge by devising a label-efficient object detection method for RSU based on unsupervised object discovery.
Co-Occurring of Object Detection and Identification towards unlabeled object discovery
In co-occurrence matrix analysis, we set base classes based on the maximum occurrences of the labels and build association rules and generate frequent patterns.
LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors
We present a simple self-supervised method to enhance the performance of ViT features for dense downstream tasks.
Attention-Guided Masked Autoencoders For Learning Image Representations
Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks.
Unsupervised Discovery of Object-Centric Neural Fields
Extensive experiments show that uOCF enables unsupervised discovery of visually rich objects from a single real image, allowing applications such as 3D object segmentation and scene manipulation.
HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping
Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images.
Has Anything Changed? 3D Change Detection by 2D Segmentation Masks
Through scene comparison over time, information about objects in the scene and their changes is inferred.
The Background Also Matters: Background-Aware Motion-Guided Objects Discovery
This is a critical limitation given the unsupervised setting, where object segments and noise are not distinguishable.
Towards Unsupervised Object Detection From LiDAR Point Clouds
In this paper, we study the problem of unsupervised object detection from 3D point clouds in self-driving scenes.
Sub-token ViT Embedding via Stochastic Resonance Transformers
We term our method ``Stochastic Resonance Transformer" (SRT), which we show can effectively super-resolve features of pre-trained ViTs, capturing more of the local fine-grained structures that might otherwise be neglected as a result of tokenization.