相关论文: Learning What and Where: Disentangling Location an…

While human infants exhibit knowledge about object permanence from two months of age onwards, deep-learning approaches still largely fail to recognize objects' continued existence. We introduce a slot-based autoregressive deep learning…

Current slot-oriented approaches for compositional scene segmentation from images and videos rely on provided background information or slot assignments. We present a segmented location and identity tracking system, Loci-Segmented (Loci-s),…

Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often failing when objects…

Learning object segmentation in image and video datasets without human supervision is a challenging problem. Humans easily identify moving salient objects in videos using the gestalt principle of common fate, which suggests that what moves…

Acquiring count annotations generally requires less human effort than point-level and bounding box annotations. Thus, we propose the novel problem setup of localizing objects in dense scenes under this weaker supervision. We propose LOOC, a…

We present LoTIS, a model for visual navigation that provides robot-agnostic image-space guidance by localizing a reference RGB trajectory in the robot's current view, without requiring camera calibration, poses, or robot-specific training.…

Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning. Recently, techniques for unsupervised learning of object-centric representations have raised growing interest. In…

Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to control and compose the disentangled factors in the synthesis…

Humans learn object orientation progressively, from recognizing which way an object faces, to mentally rotating it, to reasoning about orientations between objects. Current vision-language benchmarks largely conflate orientation with…

When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a…

The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…

Object Permanence allows people to reason about the location of non-visible objects, by understanding that they continue to exist even when not perceived directly. Object Permanence is critical for building a model of the world, since…

We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both…

An important challenge for autonomous agents such as robots is to maintain a spatially and temporally consistent model of the world. It must be maintained through occlusions, previously-unseen views, and long time horizons (e.g., loop…

The ability to recognize objects despite there being differences in appearance, known as Core Object Recognition, forms a critical part of human perception. While it is understood that the brain accomplishes Core Object Recognition through…

Robots need to have a memory of previously observed, but currently occluded objects to work reliably in realistic environments. We investigate the problem of encoding object-oriented memory into a multi-object manipulation reasoning and…

Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use image-level…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

In this paper, we propose a novel trajectory learning method that exploits motion trajectories on topological map using recurrent neural network for temporally consistent geolocalization of object. Inspired by human's ability to both be…