Related papers: A General Purpose Supervisory Signal for Embodied …
3D Semantic Scene Graph Prediction aims to detect objects and their semantic relationships in 3D scenes, and has emerged as a crucial technology for robotics and AR/VR applications. While previous research has addressed dataset limitations…
Recently image inpainting has witnessed rapid progress due to generative adversarial networks (GAN) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder…
With the increasing computation of training graph neural networks (GNNs) on large-scale graphs, graph condensation (GC) has emerged as a promising solution to synthesize a compact, substitute graph of the large-scale original graph for…
Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph. Existing SGG approaches generally not only…
Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…
Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the datasets of some specific scenes or applications. If we train…
While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges in long-horizon planning. Unlike open-ended text generation, embodied…
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…
Scene graph generation (SGG) aims to capture a wide variety of interactions between pairs of objects, which is essential for full scene understanding. Existing SGG methods trained on the entire set of relations fail to acquire complex…
We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representations to global image representations. This strategy…
In this paper, we tackle the problem of learning visual representations from unlabeled scene-centric data. Existing works have demonstrated the potential of utilizing the underlying complex structure within scene-centric data; still, they…
In recent years, image classification, as a core task in computer vision, relies on high-quality labelled data, which restricts the wide application of deep learning models in practical scenarios. To alleviate the problem of insufficient…
Scene graphs provide valuable information to many downstream tasks. Many scene graph generation (SGG) models solely use the limited annotated relation triples for training, leading to their underperformance on low-shot (few and zero)…
Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a…
We propose a unified Generative Adversarial Network (GAN) for controllable image-to-image translation, i.e., transferring an image from a source to a target domain guided by controllable structures. In addition to conditioning on a…
Despite their recent successes, GAN models for semantic image synthesis still suffer from poor image quality when trained with only adversarial supervision. Historically, additionally employing the VGG-based perceptual loss has helped to…
In the context of visual navigation, the capacity to map a novel environment is necessary for an agent to exploit its observation history in the considered place and efficiently reach known goals. This ability can be associated with spatial…
Scene graphs are semantic abstraction of images that encourage visual understanding and reasoning. However, the performance of Scene Graph Generation (SGG) is unsatisfactory when faced with biased data in real-world scenarios. Conventional…
Training Scene Graph Generation (SGG) models with natural language captions has become increasingly popular due to the abundant, cost-effective, and open-world generalization supervision signals that natural language offers. However, such…
Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data. Contrastive learning for Unpaired image-to-image Translation (CUT) yields state-of-the-art…