27 accepted papers
Latent Factorization-of-Tensors (LFT) models are an effective approach for relation extraction. Existing LFT models assume each mode of the target tensor corresponds to a entity set and the relationships between entity sets are bipartite graphs to explore the relationships among entities within a mo…
Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering and poor adaptability to target classes. While recent methods attempt to improve prompts through diverse class description
Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail to achieve this balance: neural architectural search is computationally expensive, while model retrieval often yields suboptimal static checkpoints. To resolv…
Many modern AI systems are designed to operate under diverse, open-ended, use-cases. To help generalize deployed systems, developers rely on a reactive AI flywheel that observes emerging feedback from user behavior (errors) and patches the model accordingly. However, most flywheels ignore the broade…
This work presents DCFlow, a novel self-supervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous unsupervised approaches that implicitly learn flow estimation solely from appearance similarity, we int…
The alignment of large language models with human preferences is typically achieved via Reinforcement Learning from Human Feedback or Direct Preference Optimization. However, these methods are susceptible to the significant noise prevalent in real-world preference datasets. To address this critical …
Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especially those involving complex spatial compositions, multiple interacting objects, o
Mitigating the negative impact of noisy labels has been a perennial issue in supervised learning. Robust loss functions have emerged as a prevalent solution to this problem. In this work, we introduce the Variation Ratio as a novel property related to the robustness of loss functions, and propose a
Learning with noisy labels is a crucial task for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions, particularly symmetric losses. Nevertheless, symmetric losses usually suffer from the underfitting issue due to the overly stri…
Visual tokenization via auto-encoding empowers state-of-the-art image and video generative models by compressing pixels into a latent space. However, questions remain about how auto-encoder design impacts reconstruction and downstream generative performance. This work explores scaling in auto-encode…
Text-to-video generation enhances content creation but is highly computationally intensive: The computational cost of Diffusion Transformers (DiTs) scales quadratically in the number of pixels. This makes minute-length video generation extremely expensive, limiting most existing models to generatin…
In recent years, the design and transfer of neural network models have been widely studied due to their exceptional performance and capabilities. However, the complex nature of datasets and the vast architecture space pose significant challenges for both manual and automated algorithms in creating h…
Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly symmetric losses. However, they usually suffer from the underfit…
Loop Closure Detection (LCD) is an essential component of Simultaneous Localization and Mapping (SLAM), helping to correct drift errors, facilitate map merging, or both by identifying previously observed scenes. Despite its importance, traditional LCD algorithms based on single sensor such as camera…
Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However one of the major drawbacks of diffusion models is that the image generation process is costly. A large image-to-image network has to be applied many times to ite…
Manually creating 3D environments for AR/VR applications is a complex process requiring expert knowledge in 3D modeling software. Pioneering works facilitate this process by generating room meshes conditioned on textual style descriptions. Yet many of these automatically generated 3D meshes do not a…
Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However the advancement of video-to-video (V2V) synthesis has been hampered by the challenge of maintaining temporal consistency across video frames. This paper proposes a consistent V2V synthesi…
Extrinsic calibration is an essential prerequisite for the applications of camera-LiDAR fusion. Existing methods either suffer from the complex offline setting of man-made targets or tend to produce suboptimal and unrobust results. In this paper, we propose an online two-stage calibration method tha…
Graph-based semi-supervised learning, particularly in the context of extremely sparse labeled data, often suffers from degenerate solutions where label functions tend to be nearly constant across unlabeled data. In this paper, we introduce Variance-enlarged Poisson Learning (VPL), a simple yet power…
We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with a fallback to monocular depth estimation when rectification is unreliable. The output of our depth sensing system is then used in a…
Direct time-of-flight (dToF) sensors are promising for next-generation on-device 3D sensing. However, limited by manufacturing capabilities in a compact module, the dToF data has low spatial resolution (e.g., 20x30 for iPhone dToF), and it requires a super-resolution step before being passed to dow…
We present NeRF-Det, a novel method for indoor 3D detection with posed RGB images as input. Unlike existing indoor 3D detection methods that struggle to model scene geometry, our method makes novel use of NeRF in an end-to-end manner to explicitly estimate 3D geometry, thereby improving 3D detection…
The majority of prior monocular depth estimation methods without groundtruth depth guidance focus on driving scenarios. We show that such methods generalize poorly to unseen complex indoor scenes, where objects are cluttered and arbitrarily arranged in the near field. To obtain more robustness, we p…
Under the conventional diffuse shading model with unknown directional lighting, the set of quadratic surface shapes that are consistent with the spatial derivatives of intensity at a single image point is a two-dimensional algebraic variety embedded in the five-dimensional space of quadratic shapes.…
Robust optimization has been widely used in nowadays data science, especially in adversarial training. However, little research has been done to quantify how robust optimization changes the optimizers and the prediction losses comparing to standard training. In this paper, inspired by the influence…
Stereo occlusion boundaries are one-dimensional structures in the visual field that separate foreground regions of a scene that are visible to both eyes (binocular regions) from background regions of a scene that are visible to only one eye (monocular regions). Stereo occlusion boundaries often coin…
Two types of information exist in a stereo pair: correlation (matching) and decorrelation (half-occlusion). Vision science has shown that both types of information are used in the visual cortex, and that people can perceive depth even when correlation cues are absent or very weak, a capability that…