Object Discovery

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 96 papers with code (210 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Object-Centric Learning with Slot Attention
  26 Jun 2020 8 repositories listed Syntology ran 14 of 21 samples · 7 unverified · 7 pointer-only (licence)
  Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features.
• Vision Transformers Need Registers
  28 Sep 2023 6 repositories listed Syntology ran 4 of 20 samples · 16 unverified · 2 pointer-only (licence)
  Transformers have recently emerged as a powerful tool for learning visual representations.
• Learning Open-World Object Proposals without Learning to Classify
  15 Aug 2021 6 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.
• MONet: Unsupervised Scene Decomposition and Representation
  22 Jan 2019 5 repositories listed Syntology ran 1 of 7 samples · 6 unverified
  The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.
• Learn To Pay Attention
  6 Apr 2018 4 repositories listed
  We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification.
• GuessWhat?! Visual object discovery through multi-modal dialogue
  23 Nov 2016 4 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
• Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset
  24 Sep 2023 3 repositories listed
  Using our dataset and annotations, we release benchmarks for 3D object detection and 3D semantic segmentation using established metrics.
• CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers
  12 Mar 2024 2 repositories listed Syntology ran 6 of 9 samples · 3 unverified
  In this paper, we introduce VoteCut, an innovative method for unsupervised object discovery that leverages feature representations from multiple self-supervised models.
• Object Discovery from Motion-Guided Tokens
  27 Mar 2023 2 repositories listed Syntology ran 18 of 29 samples · 11 unverified · 29 pointer-only (licence)
  Object discovery -- separating objects from the background without manual labels -- is a fundamental open challenge in computer vision.
• Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
  9 Feb 2023 2 repositories listed
  Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning.
• Unsupervised Domain Adaptation for Nighttime Aerial Tracking
  20 Mar 2022 2 repositories listed Syntology ran 4 of 11 samples · 7 unverified
  Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications.
• What Matters For Meta-Learning Vision Regression Tasks?
  9 Mar 2022 2 repositories listed
  To this end, we (i) exhaustively evaluate common meta-learning techniques on these tasks, and (ii) quantitatively analyze the effect of various deep learning techniques commonly used in recent meta-learning algorithms…
• Unsupervised Image Decomposition with Phase-Correlation Networks
  7 Oct 2021 2 repositories listed
  The ability to decompose scenes into their object components is a desired property for autonomous agents, allowing them to reason and act in their surroundings.
• Localizing Objects with Self-Supervised Transformers and no Labels
  29 Sep 2021 2 repositories listed
  We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points.
• GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
  30 Jul 2019 2 repositories listed
  Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning.
• COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
  22 May 2019 2 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms.
• Efficient Dialog Policy Learning via Positive Memory Retention
  2 Oct 2018 2 repositories listed
  This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning.
• When Does Pruning Benefit Vision Representations?
  2 Jul 2025 1 repository listed
  Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood.
• Binding threshold units with artificial oscillatory neurons
  6 May 2025 1 repository listed
  For threshold units, this leads to Hopfield associative memory model, and for oscillatory units it yields a specific form of generalized Kuramoto model.
• Are We Done with Object-Centric Learning?
  9 Apr 2025 1 repository listed Syntology ran 0 of 8 samples · 8 unverified
  However, with recent sample-efficient segmentation models, we can separate objects in the pixel space and encode them independently.
• Vector-Quantized Vision Foundation Models for Object-Centric Learning
  27 Feb 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  Decomposing visual scenes into objects, as humans do, facilitates modeling object relations and dynamics.
• FrontierNet: Learning Visual Cues to Explore
  8 Jan 2025 1 repository listed
  This work aims at leveraging 2D visual cues for efficient autonomous exploration, addressing the limitations of extracting goal poses from a 3D map.
• PickScan: Object discovery and reconstruction from handheld interactions
  17 Nov 2024 1 repository listed
  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.
• Grouped Discrete Representation for Object-Centric Learning
  4 Nov 2024 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  Visualizations show that our GDR captures better object separability.
• Artificial Kuramoto Oscillatory Neurons
  17 Oct 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  It has long been known in both neuroscience and AI that ``binding'' between neurons leads to a form of competitive learning where representations are compressed in order to represent more abstract concepts in deeper…
• PEEKABOO: Hiding parts of an image for unsupervised object localization
  24 Jul 2024 1 repository listed
  Localizing objects in an unsupervised manner poses significant challenges due to the absence of key visual information such as the appearance, type and number of objects, as well as the lack of labeled object classes…
• Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation
  3 Jul 2024 1 repository listed
  Considering the adopted bidirectional alignment will also weaken the anchor image activation if appropriate constraints are missing, we propose a self-supervised regularization module to maintain the reliable activation…
• DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
  21 Jun 2024 1 repository listed Syntology ran 5 of 7 samples · 2 unverified
  We demonstrate the effectiveness of DiPEx through extensive class-agnostic OD and OOD-OD experiments on MS-COCO and LVIS, surpassing other prompting methods by up to 20.
• Adaptive Slot Attention: Object Discovery with Dynamic Slot Number
  13 Jun 2024 1 repository listed
  Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to each instance's complexity, offering the potential for further exploration in slot attention…
• Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection
  2 Jun 2024 1 repository listed Syntology ran 7 of 11 samples · 4 unverified
  3D-NOD is further extended with an Enrichment strategy that significantly enriches the novel object distribution in the training scenes, and then enhances the model's ability to localize more novel objects.

Syntology lines on 15 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.