Related papers: Exploiting the Distortion-Semantic Interaction in …

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…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-toimage synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach decouples training data generation…

The goal of a classification model is to assign the correct labels to data. In most cases, this data is not fully described by the given set of labels. Often a rich set of meaningful concepts exist in the domain that can much more precisely…

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…

The challenges in recovering underwater images are the presence of diverse degradation factors and the lack of ground truth images. Although synthetic underwater image pairs can be used to overcome the problem of inadequately observing…

Autonomous agents, particularly in the field of robotics, rely on sensory information to perceive and navigate their environment. However, these sensory inputs are often imperfect, leading to distortions in the agent's internal…

Diffusion models have emerged as state-of-the-art generative methods for image synthesis, yet their potential as general-purpose feature encoders remains underexplored. Trained for denoising and generation without labels, they can be…

In recent years, learning-based underwater image enhancement (UIE) techniques have rapidly evolved. However, distribution shifts between high-quality enhanced outputs and natural images can hinder semantic cue extraction for downstream…

Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…

One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action…

Underwater environments pose significant challenges due to the selective absorption and scattering of light by water, which affects image clarity, contrast, and color fidelity. To overcome these, we introduce OceanLens, a method that models…

Context can strongly affect object representations, sometimes leading to undesired biases, particularly when objects appear in out-of-distribution backgrounds at inference. At the same time, many object-centric tasks require to leverage the…

Human activities often occur in specific scene contexts, e.g., playing basketball on a basketball court. Training a model using existing video datasets thus inevitably captures and leverages such bias (instead of using the actual…

In contrast to fully-supervised models, self-supervised representation learning only needs a fraction of data to be labeled and often achieves the same or even higher downstream performance. The goal is to pre-train deep neural networks on…

Motivated by the need to improve model performance in traffic monitoring tasks with limited labeled samples, we propose a straightforward augmentation technique tailored for object detection datasets, specifically designed for stationary…

Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for…

Deep learning models have demonstrated remarkable capabilities in learning complex patterns and concepts from training data. However, recent findings indicate that these models tend to rely heavily on simple and easily discernible features…

In recent years, deep learning has greatly streamlined the process of manipulating photographic face images. Aware of the potential dangers, researchers have developed various tools to spot these counterfeits. Yet, none asks the fundamental…

For a considerable time, deep convolutional neural networks (DCNNs) have reached human benchmark performance in object recognition. On that account, computational neuroscience and the field of machine learning have started to attribute…

Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish…