Related papers: Learning What and Where: Disentangling Location an…
Existing works of reasoning segmentation often fall short in complex cases, particularly when addressing complicated queries and out-of-domain images. Inspired by the chain-of-thought reasoning, where harder problems require longer thinking…
Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence class). Common to all of these approaches is the assumption that…
We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving the place recognition problem with complex radar data. Our method is based on invariant instance feature learning but is tailored for…
Long-Horizon (LH) tasks in Human-Scene Interaction (HSI) are complex multi-step tasks that require continuous planning, sequential decision-making, and extended execution across domains to achieve the final goal. However, existing methods…
Multimodal intelligence development recently show strong progress in visual understanding and high level reasoning. Though, most reasoning system still reply on textual information as the main medium for inference. This limit their…
The human visual system processes images with varied degrees of resolution, with the fovea, a small portion of the retina, capturing the highest acuity region, which gradually declines toward the field of view's periphery. However, the…
In this paper, we tackle the copy-paste image-to-image composition problem with a focus on object placement learning. Prior methods have leveraged generative models to reduce the reliance for dense supervision. However, this often limits…
Object detection and pose estimation are difficult tasks in robotics and autonomous driving. Existing object detection and pose estimation methods mostly adopt the same-dimensional data for training. For example, 2D object detection usually…
Most tracking-by-detection methods employ a local search window around the predicted object location in the current frame assuming the previous location is accurate, the trajectory is smooth, and the computational capacity permits a search…
Daily images may convey abstract meanings that require us to memorize and infer profound information from them. To encourage such human-like reasoning, in this work, we teach machines to predict where and when it was taken rather than…
Neurosymbolic learning can use symbolic rules to provide supervision for latent concepts from weak labels, but it commonly assumes that the entities referenced by these rules are already specified. Object-centric models decompose images…
There have recently been large advances both in pre-training visual representations for robotic control and segmenting unknown category objects in general images. To leverage these for improved robot learning, we propose $\textbf{POCR}$, a…
Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene…
Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in precise control of image compositions. In this paper, we…
Global localization is a critical problem in autonomous navigation, enabling precise positioning without reliance on GPS. Modern global localization techniques often depend on dense LiDAR maps, which, while precise, require extensive…
Localization for autonomous robots in prior maps is crucial for their functionality. This paper offers a solution to this problem for indoor environments called InstaLoc, which operates on an individual lidar scan to localize it within a…
While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object…
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…
Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…
We propose a new representation of visual data that disentangles object position from appearance. Our method, termed Deep Latent Particles (DLP), decomposes the visual input into low-dimensional latent ``particles'', where each particle is…