Related papers: ACE-G: Improving Generalization of Scene Coordinat…

Visual Place Recognition (VPR) estimates the location of query images by matching them with images in a reference database. Conventional methods generally adopt aggregated CNN features for global retrieval and RANSAC-based geometric…

Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images as positive samples to guide the training of dehazing…

In order for autonomous mobile robots to navigate in human spaces, they must abide by our social norms. Reinforcement learning (RL) has emerged as an effective method to train sequential decision-making policies that are able to respect…

Scene graphs provide a rich, structured representation of a scene by encoding the entities (objects) and their spatial relationships in a graphical format. This representation has proven useful in several tasks, such as question answering,…

Systematic Generalization refers to a learning algorithm's ability to extrapolate learned behavior to unseen situations that are distinct but semantically similar to its training data. As shown in recent work, state-of-the-art deep learning…

A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on reconstructing pre-defined 3D representations, e.g. textured…

Few-shot adaptation of vision-language models remains fundamentally limited by how negative class signals are handled at inference. Existing methods apply uniform negative suppression across all queries, ignoring that the most damaging…

Unaligned Scene Change Detection aims to detect scene changes between image pairs captured at different times without assuming viewpoint alignment. To handle viewpoint variations, current methods rely solely on 2D visual cues to establish…

A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliary tasks to enhance generalization, few adopt image…

A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks…

Scene classification, aiming at classifying a scene image to one of the predefined scene categories by comprehending the entire image, is a longstanding, fundamental and challenging problem in computer vision. The rise of large-scale…

The scalability of Distributed Stochastic Gradient Descent (SGD) is today limited by communication bottlenecks. We propose a novel SGD variant: Communication-efficient SGD with Error Reset, or CSER. The key idea in CSER is first a new…

Scene classification has established itself as a challenging research problem. Compared to images of individual objects, scene images could be much more semantically complex and abstract. Their difference mainly lies in the level of…

Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to. To ensure a good visual coherence and a high class accuracy, it is essential for a scene parser to capture image…

Generally, the performance of a generic detector decreases significantly when it is tested on a specific scene due to the large variation between the source training dataset and the samples from the target scene. To solve this problem, we…

Recent adaptations can boost the low-shot capability of Contrastive Vision-Language Pre-training (CLIP) by effectively facilitating knowledge transfer. However, these adaptation methods are usually operated on the global view of an input…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

Contrastive learning (CL) has become a cornerstone of self-supervised pretraining (SSP) in foundation models, however, extending CL to pixel-wise representation, crucial for medical vision, remains an open problem. Standard CL formulates…

We present a novel approach to reconstructing lightweight, CAD-based representations of scanned 3D environments from commodity RGB-D sensors. Our key idea is to jointly optimize for both CAD model alignments as well as layout estimations of…

Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal systems compared to diffusion-based methods. However, extending AR models to…