20 accepted papers
Memory formation is fundamental to intelligence, yet whether deep neural networks preserve identifiable memory traces—analogous to biological memory units—remains an open question. This work introduces a geometric framework to identify such "AI engrams," by formalizing the neuroscientific criteria o…
Recent T2I diffusion models have evolved to control multiple conditions, including structure, appearance, and text prompt. Despite this progress, training-based methods demand heavy computation, whereas training-free methods often 're-imagine' the subject to satisfy given structure, thereby compromi
Recent advancements in controllable text-to-image (T2I) diffusion models, such as Ctrl-X and FreeControl, have demonstrated robust spatial and appearance control without requiring auxiliary module training. However, these models often struggle to accurately preserve spatial structures and fail to ca…
Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions. However, SDS often suffers from blurriness caused by noisy gradients. When SDS meets the image editing, such degradati…
This study emphasizes the significance of exploring distance-based source separation (DSS) in outdoor environments. Unlike existing studies that primarily focus on indoor settings, the proposed model is designed to capture the unique characteristics of outdoor audio sources. It incorporates advanced…
Domain adaptation for object detection typically entails transferring knowledge from one visible domain to another visible domain. However there are limited studies on adapting from the visible to the thermal domain because the domain gap between the visible and thermal domains is much larger than e…
While robust model predictive control (MPC) has been studied extensively in recent decades, addressing unmatched disturbances in underactuated robotic systems is still challenging. In this paper, we propose a method to enhance the robustness of the MPC through the online estimation of disturbances u…
Understanding the interaction between multiple agents is crucial for realistic vehicle trajectory prediction. Existing methods have attempted to infer the interaction from the observed past trajectories of agents using pooling, attention, or graph-based methods, which rely on a deterministic approa…
"We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model’s predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label, dubbed ConMatch. While the latest semi-supervised learning metho…
Establishing dense correspondences across semantically similar images is one of the challenging tasks due to the significant intra-class variations and background clutters. To solve these problems, numerous methods have been proposed, focused on learning feature extractor or cost aggregation indepen…
When a person solves the multi-choice problem, she considers not only what is the answer but also what is not the answer. Knowing what choice is not the answer and utilizing the relationships between choices, she can improve the prediction accuracy. Inspired by this human reasoning process, we propo…
Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised loss was used for training the matching networks, which requires tremendous manually-labeled data, while…
Multispectral pedestrian detection has been actively studied as a promising multi-modality solution to handle illumination and weather changes. Most multi-modality approaches carry the assumption that all inputs are fully-overlapped. However, these kinds of data pairs are not common in practical app
In this study, we propose a self-supervised video denoising method called ""restore-from-restored."" This method fine-tunes a pre-trained network by using a pseudo clean video during the test phase. The pseudo clean video is obtained by applying a noisy video to the baseline network. By adopting a f…
Conventional supervised super-resolution (SR) approaches are trained with massive external SR datasets but fail to exploit desirable properties of the given test image.On the other hand, self-supervised SR approaches utilize the internal information within a test image but suffer from computational…
High-definition (HD) maps are emerging as an essential tool for autonomous driving since they provide high-precision semantic information about the physical environment. To function as a reliable source of map information, HD maps must be constantly updated with changes that occur to the state of th…
Attempts to train a comprehensive artificial intelligence capable of solving multiple tasks have been impeded by a chronic problem called catastrophic forgetting. Although simply replaying all previous data alleviates the problem, it requires large memory and even worse, often infeasible in real wor…
While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations. To avoid costly pairing, we address the task of discovering cro…
We present a highly accurate single image superresolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification [19]. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers.…
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performance without introducing new parameters for additional convolutions. Albeit advanta…