English
Related papers

Related papers: Are Object-Centric Representations Better At Compo…

200 papers

Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model's detection capability to new object classes requires large amounts of annotated training data,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Vikhyat Agarwal , Jiayi Cora Guo , Declan Hoban , Sissi Zhang , Nicholas Moran , Peter Cho , Srilakshmi Pattabiraman , Shantanu Joshi

Most approaches to cross-modal retrieval (CMR) focus either on object-centric datasets, meaning that each document depicts or describes a single object, or on scene-centric datasets, meaning that each image depicts or describes a complex…

Information Retrieval · Computer Science 2023-10-12 Mariya Hendriksen , Svitlana Vakulenko , Ernst Kuiper , Maarten de Rijke

Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling compositional generalization, various unsupervised learning…

Machine Learning · Computer Science 2022-10-07 Zhenlin Xu , Marc Niethammer , Colin Raffel

Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable…

Machine Learning · Computer Science 2023-06-16 Jinyang Yuan , Tonglin Chen , Bin Li , Xiangyang Xue

A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to…

Computer Vision and Pattern Recognition · Computer Science 2018-09-05 Youssef Tamaazousti , Hervé Le Borgne , Céline Hudelot , Mohamed El Amine Seddik , Mohamed Tamaazousti

World models aim to capture the dynamics of the environment, enabling agents to predict and plan for future states. In most scenarios of interest, the dynamics are highly centered on interactions among objects within the environment. This…

Machine Learning · Computer Science 2025-07-08 Zizhao Wang , Kaixin Wang , Li Zhao , Peter Stone , Jiang Bian

Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information…

Computer Vision and Pattern Recognition · Computer Science 2022-12-21 Monika Wysoczańska , Tom Monnier , Tomasz Trzciński , David Picard

Object-centric architectures can learn to extract distinct object representations from visual scenes, enabling downstream applications on the object level. Similarly to autoencoder-based image models, object-centric approaches have been…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Bastian Jäckl , Yannick Metz , Udo Schlegel , Daniel A. Keim , Maximilian T. Fischer

Large Vision-Language Models (LVLMs) excel at captioning, visual question answering, and robotics by combining vision and language, yet they often miss obvious objects or hallucinate nonexistent ones in atypical scenes. We examine these…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Zhaoyang Li , Zhan Ling , Yuchen Zhou , Litian Gong , Erdem Bıyık , Hao Su

Among the most impressive recent applications of neural decoding is the visual representation decoding, where the category of an object that a subject either sees or imagines is inferred by observing his/her brain activity. Even though…

Neural and Evolutionary Computing · Computer Science 2018-11-06 Angeliki Papadimitriou , Nikolaos Passalis , Anastasios Tefas

DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual contexts. But this pipeline requires rendering token embeddings…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Ivan Yee Lee , Cheng Yang , Taylor Berg-Kirkpatrick

Object-Centric Learning (OCL) aggregates image or video feature maps into object-level feature vectors, termed \textit{slots}. It's self-supervision of reconstructing the input from slots struggles with complex object textures, thus Vision…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Rongzhen Zhao , Vivienne Wang , Juho Kannala , Joni Pajarinen

Humans can discern scene-independent features of objects across various environments, allowing them to swiftly identify objects amidst changing factors such as lighting, perspective, size, and position and imagine the complete images of the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Tonglin Chen , Yinxuan Huang , Zhimeng Shen , Jinghao Huang , Bin Li , Xiangyang Xue

As a core problem in computer vision, the performance of object detection has improved drastically in the past few years. Despite their impressive performance, object detectors suffer from a lack of interpretability. Visualization…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Ang Cao , Justin Johnson

Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as…

Robotics · Computer Science 2017-09-27 Coline Devin , Pieter Abbeel , Trevor Darrell , Sergey Levine

Visual scenes are extremely diverse, not only because there are infinite possible combinations of objects and backgrounds but also because the observations of the same scene may vary greatly with the change of viewpoints. When observing a…

Computer Vision and Pattern Recognition · Computer Science 2024-01-05 Jinyang Yuan , Tonglin Chen , Zhimeng Shen , Bin Li , Xiangyang Xue

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Damien Teney , Peng Wang , Jiewei Cao , Lingqiao Liu , Chunhua Shen , Anton van den Hengel

Compositional representations are thought to enable humans to generalize across combinatorially vast state spaces. Models with learnable object slots, which encode information about objects in separate latent codes, have shown promise for…

Machine Learning · Computer Science 2024-10-08 Tankred Saanum , Luca M. Schulze Buschoff , Peter Dayan , Eric Schulz

It is known that representations from self-supervised pre-training can perform on par, and often better, on various downstream tasks than representations from fully-supervised pre-training. This has been shown in a host of settings such as…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 David Torpey , Richard Klein

Discovering object-centric representations from images can significantly enhance the robustness, sample efficiency and generalizability of vision models. Works on images with multi-part objects typically follow an implicit object…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Alex Foo , Wynne Hsu , Mong Li Lee
‹ Prev 1 3 4 5 6 7 10 Next ›