paper-with-me

Papers Object Discovery

“Object Discovery” 태그가 달린 논문 210편 · 필터 해제

When Does Pruning Benefit Vision Representations?

2025-07-02 · Enrico Cassano, Riccardo Renzulli, Andrea Bragagnolo, Marco Grangetto

Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper investigates how pruning influences vision mod…

Object DiscoveryRepresentation Learning

FORLA:Federated Object-centric Representation Learning with Slot Attention

2025-06-03 · Guiqiu Liao, Matjaz Jogan, Eric Eaton, Daniel A. Hashimoto

Learning efficient visual representations across heterogeneous unlabeled datasets remains a central challenge in federated learning. Effective federated representations require features that are jointly informative acros…

DecoderFederated LearningObject DiscoveryRepresentation Learning

Binding threshold units with artificial oscillatory neurons

2025-05-06 · Vladimir Fanaskov, Ivan Oseledets

Artificial Kuramoto oscillatory neurons were recently introduced as an alternative to threshold units. Empirical evidence suggests that oscillatory units outperform threshold units in several tasks including unsupervised…

FormObject Discovery

Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning

2025-05-04 · Can Küçüksözen, Yücel Yemez

We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery ta…

ClusteringDecoderInductive BiasObject+3

Are We Done with Object-Centric Learning?

2025-04-09 · Alexander Rubinstein, Ameya Prabhu, Matthias Bethge, Seong Joon Oh

Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD…

ObjectObject Discovery

CTRL-O: Language-Controllable Object-Centric Visual Representation Learning

2025-03-27 · CVPR 2025 1 · Aniket Didolkar, Andrii Zadaianchuk, Rabiul Awal, Maximilian Seitzer 외

Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models …

Image GenerationObjectObject DiscoveryQuestion Answering+4

xMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motion

2025-03-19 · Saad Lahlali, Sandra Kara, Hejer Ammar, Florian Chabot 외

Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing interest, it remains under-explored in 3D d…

Multi-object discoveryObjectObject DiscoveryObject Localization

OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection

2025-03-09 · Adrian Chow, Evelien Riddell, Yimu Wang, Sean Sedwards 외

Open-vocabulary 3D object detection for autonomous driving aims to detect novel objects beyond the predefined training label sets in point cloud scenes. Existing approaches achieve this by connecting traditional 3D objec…

3D Object DetectionAutonomous Drivingcross-modal alignmentObject+3

Vector-Quantized Vision Foundation Models for Object-Centric Learning

2025-02-27 · Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen

Decomposing visual scenes into objects, as humans do, facilitates modeling object relations and dynamics. Object-Centric Learning (OCL) achieves this by aggregating image or video feature maps into object-level feature v…

ObjectObject Discovery

Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation

2025-01-27 · Adil Kaan Akan, Yucel Yemez

We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our method preserves the generative power of pret…

Image GenerationObject Discovery

Slot-BERT: Self-supervised Object Discovery in Surgical Video

2025-01-21 · Guiqiu Liao, Matjaz Jogan, Marcel Hussing, Kenta Nakahashi 외

Object-centric slot attention is a powerful framework for unsupervised learning of structured and explainable representations that can support reasoning about objects and actions, including in surgical videos. While conv…

DisentanglementDomain AdaptationObjectObject Discovery

FrontierNet: Learning Visual Cues to Explore

2025-01-08 · Boyang Sun, Hanzhi Chen, Stefan Leutenegger, Cesar Cadena 외

Exploration of unknown environments is crucial for autonomous robots; it allows them to actively reason and decide on what new data to acquire for different tasks, such as mapping, object discovery, and environmental ass…

Object Discovery

Leveraging Registers in Vision Transformers for Robust Adaptation

2025-01-08 · Srikar Yellapragada, Kowshik Thopalli, Vivek Narayanaswamy, Wesam Sakla 외

Vision Transformers (ViTs) have shown success across a variety of tasks due to their ability to capture global image representations. Recent studies have identified the existence of high-norm tokens in ViTs, which can in…

Anomaly DetectionObject Discovery

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning

2025-01-01 · CVPR 2025 1 · Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth

Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles…

Conditional Image GenerationImage GenerationObjectObject Discovery

Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D Motion

2025-01-01 · CVPR 2025 1 · Saad Lahlali, Sandra Kara, Hejer Ammar, Florian Chabot 외

Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing interest, it remains under-explored in …

Multi-object discoveryObjectObject DiscoveryObject Localization

Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning

2025-01-01 · CVPR 2025 1 · Can Kucuksozen, Yucel Yemez

We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discover…

ClusteringDecoderInductive BiasObject+3

Temporally Consistent Object-Centric Learning by Contrasting Slots

2024-12-18 · CVPR 2025 1 · Anna Manasyan, Maximilian Seitzer, Filip Radovic, Georg Martius 외

Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these repre…

Inductive BiasObjectObject Discovery

Efficient Object-centric Representation Learning with Pre-trained Geometric Prior

2024-12-16 · Phúc H. Le Khac, Graham Healy, Alan F. Smeaton

This paper addresses key challenges in object-centric representation learning of video. While existing approaches struggle with complex scenes, we propose a novel weakly-supervised framework that emphasises geometric und…

Computational EfficiencyDecoderObjectObject Discovery+1

Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory

2024-11-25 · Zaira Manigrasso, Matteo Dunnhofer, Antonino Furnari, Moritz Nottebaum 외

Episodic memory retrieval aims to enable wearable devices with the ability to recollect from past video observations objects or events that have been observed (e.g., "where did I last see my smartphone?"). Despite the cl…

Objectobject-detectionObject DetectionObject Discovery

PickScan: Object discovery and reconstruction from handheld interactions

2024-11-17 · Vincent van der Brugge, Marc Pollefeys, Joshua B. Tenenbaum, Ayush Tewari 외

Reconstructing compositional 3D representations of scenes, where each object is represented with its own 3D model, is a highly desirable capability in robotics and augmented reality. However, most existing methods rely h…

ObjectObject Discovery
1–20 / 210 다음 →