23 citations · 47 across the 27 of their papers we have counts for
30 papers
PORA: Learning When More Reasoning Pays Off for LLM Agents
Bo Yan, Qi Zhang, Zhen Tan +2
LLM agents perform tasks over multiple steps and revise their actions based on feedback. As the total reasoning budget is often limited and must support future steps, the agent mus…
Feed-Forward Multi-View Feature Coding for 3D Gaussian Splatting
Seungmi Choi, Ji-Hyoun Choi, Suhyun Jo +2
Feed-forward 3D Gaussian Splatting (3DGS) methods enable efficient reconstruction of 3D scenes from sparse multi-view images in a single forward pass, without scene-specific optimi…
LiFT: Loop Flow Transformers
Mohammad Mahdi Derakhshani, Pedro M. P. Curvo, Gertjan J. Burghouts +2
We introduce Loop Flow Transformers (LiFT), a family of looped generative models that scales computation by repeatedly applying a shared Diffusion Transformer (DiT) core, with only…
OASIC: Occlusion-Agnostic and Severity-Informed Classification
Kay Gijzen, Gertjan J. Burghouts, Daniël M. Pelt
Severe occlusions of objects pose a major challenge for computer vision. We show that two root causes are (1) the loss of visible information and (2) the distracting patterns cause…
Neurosymbolic Inference On Foundation Models For Remote Sensing Text-to-image Retrieval With Complex Queries
Emanuele Mezzi, Gertjan Burghouts, Maarten Kruithof
Text-to-image retrieval in remote sensing (RS) has advanced rapidly with the rise of large vision-language models (LVLMs) tailored for aerial and satellite imagery, culminating in…
Occlusion Robustness of CLIP for Military Vehicle Classification
Jan Erik van Woerden, Gertjan Burghouts, Lotte Nijskens +4
Vision-language models (VLMs) like CLIP enable zero-shot classification by aligning images and text in a shared embedding space, offering advantages for defense applications with s…
Textual Inversion for Efficient Adaptation of Open-Vocabulary Object Detectors Without Forgetting
Frank Ruis, Gertjan Burghouts, Hugo Kuijf
Recent progress in large pre-trained vision language models (VLMs) has reached state-of-the-art performance on several object detection benchmarks and boasts strong zero-shot capab…
Self-Supervised Partial Cycle-Consistency for Multi-View Matching
Fedor Taggenbrock, Gertjan Burghouts, Ronald Poppe
Matching objects across partially overlapping camera views is crucial in multi-camera systems and requires a view-invariant feature extraction network. Training such a network with…
Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning
Eric Brouwer, Jan Erik van Woerden, Gertjan Burghouts +2
Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper prese…
Incremental Learning of Affordances using Markov Logic Networks
George Potter, Gertjan Burghouts, Joris Sijs
Affordances enable robots to have a semantic understanding of their surroundings. This allows them to have more acting flexibility when completing a given task. Capturing object af…
Better Language Models Exhibit Higher Visual Alignment
Jona Ruthardt, Gertjan J. Burghouts, Serge Belongie +1
How well do text-only large language models (LLMs) align with the visual world? We present a systematic evaluation of this question by incorporating frozen representations of vario…
Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation
Fieke Hillerstrom, Gertjan Burghouts
Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with pro…
Anticipating Future Object Compositions without Forgetting
Youssef Zahran, Gertjan Burghouts, Yke Bauke Eisma
Despite the significant advancements in computer vision models, their ability to generalize to novel object-attribute compositions remains limited. Existing methods for Composition…
Near, far: Patch-ordering enhances vision foundation models' scene understanding
Valentinos Pariza, Mohammadreza Salehi, Gertjan Burghouts +2
We introduce NeCo: Patch Neighbor Consistency, a novel self-supervised training loss that enforces patch-level nearest neighbor consistency across a student and teacher model. Comp…
Which objects help me to act effectively? Reasoning about physically-grounded affordances
Anne Kemmeren, Gertjan Burghouts, Michael van Bekkum +2
For effective interactions with the open world, robots should understand how interactions with known and novel objects help them towards their goal. A key aspect of this understand…
Lightweight Uncertainty Quantification with Simplex Semantic Segmentation for Terrain Traversability
Judith Dijk, Gertjan Burghouts, Kapil D. Katyal +5
For navigation of robots, image segmentation is an important component to determining a terrain's traversability. For safe and efficient navigation, it is key to assess the uncerta…
Open-World Visual Reasoning by a Neuro-Symbolic Program of Zero-Shot Symbols
Gertjan Burghouts, Fieke Hillerström, Erwin Walraven +5
We consider the problem of finding spatial configurations of multiple objects in images, e.g., a mobile inspection robot is tasked to localize abandoned tools on the floor. We defi…
Affordance Perception by a Knowledge-Guided Vision-Language Model with Efficient Error Correction
Gertjan Burghouts, Marianne Schaaphok, Michael van Bekkum +3
Mobile robot platforms will increasingly be tasked with activities that involve grasping and manipulating objects in open world environments. Affordance understanding provides a ro…
Graph Neural Networks for Learning Equivariant Representations of Neural Networks
Miltiadis Kofinas, Boris Knyazev, Yan Zhang +5
Neural networks that process the parameters of other neural networks find applications in domains as diverse as classifying implicit neural representations, generating neural netwo…
Language-Based Augmentation to Address Shortcut Learning in Object Goal Navigation
Dennis Hoftijzer, Gertjan Burghouts, Luuk Spreeuwers
Deep Reinforcement Learning (DRL) has shown great potential in enabling robots to find certain objects (e.g., `find a fridge') in environments like homes or schools. This task is k…
Diffusing More Objects for Semi-Supervised Domain Adaptation with Less Labeling
Leander van den Heuvel, Gertjan Burghouts, David W. Zhang +2
For object detection, it is possible to view the prediction of bounding boxes as a reverse diffusion process. Using a diffusion model, the random bounding boxes are iteratively ref…
Data Augmentations in Deep Weight Spaces
Aviv Shamsian, David W. Zhang, Aviv Navon +10
Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various field…
Unlocking Slot Attention by Changing Optimal Transport Costs
Yan Zhang, David W. Zhang, Simon Lacoste-Julien +2
Slot attention is a powerful method for object-centric modeling in images and videos. However, its set-equivariance limits its ability to handle videos with a dynamic number of obj…
Self-Guided Diffusion Models
Vincent Tao Hu, David W Zhang, Yuki M. Asano +2
Diffusion models have demonstrated remarkable progress in image generation quality, especially when guidance is used to control the generative process. However, guidance requires a…