Minwook Kim

Yecheol Kim, Konyul Park, Minwook Kim et al.

Fusing data from cameras and LiDAR sensors is an essential technique to achieve robust 3D object detection. One key challenge in camera-LiDAR fusion involves mitigating the large domain gap between the two sensors in terms of coordinates and data distribution when fusing their features. In this paper, we propose a novel camera-LiDAR fusion architecture called, 3D Dual-Fusion, which is designed to mitigate the gap between the feature representations of camera and LiDAR data. The proposed method fuses the features of the camera-view and 3D voxel-view domain and models their interactions through deformable attention. We redesign the transformer fusion encoder to aggregate the information from the two domains. Two major changes include 1) dual query-based deformable attention to fuse the dual-domain features interactively and 2) 3D local self-attention to encode the voxel-domain queries prior to dual-query decoding. The results of an experimental evaluation show that the proposed camera-LiDAR fusion architecture achieved competitive performance on the KITTI and nuScenes datasets, with state-of-the-art performances in some 3D object detection benchmarks categories.

Minwook Kim, Juseong Kim, Giltae Song

Recent progress in semi- and self-supervised learning has caused a rift in the long-held belief about the need for an enormous amount of labeled data for machine learning and the irrelevancy of unlabeled data. Although it has been successful in various data, there is no dominant semi- and self-supervised learning method that can be generalized for tabular data (i.e. most of the existing methods require appropriate tabular datasets and architectures). In this paper, we revisit self-training which can be applied to any kind of algorithm including the most widely used architecture, gradient boosting decision tree, and introduce curriculum pseudo-labeling (a state-of-the-art pseudo-labeling technique in image) for a tabular domain. Furthermore, existing pseudo-labeling techniques do not assure the cluster assumption when computing confidence scores of pseudo-labels generated from unlabeled data. To overcome this issue, we propose a novel pseudo-labeling approach that regularizes the confidence scores based on the likelihoods of the pseudo-labels so that more reliable pseudo-labels which lie in high density regions can be obtained. We exhaustively validate the superiority of our approaches using various models and tabular datasets.

Minwook Kim, Juseong Kim, Ki Beom Kim et al.

Tabular data is one of the most widely used data modalities, encompassing numerous datasets with substantial amounts of unlabeled data. Despite this prevalence, there is a notable lack of simple and versatile methods for utilizing unlabeled data in the tabular domain, where both gradient-boosting decision trees and neural networks are employed. In this context, self-training has gained attraction due to its simplicity and versatility, yet it is vulnerable to noisy pseudo-labels caused by erroneous confidence. Several solutions have been proposed to handle this problem, but they often compromise the inherent advantages of self-training, resulting in limited applicability in the tabular domain. To address this issue, we explore a novel direction of reliable confidence in self-training contexts and conclude that self-training can be improved by making that the confidence, which represents the value of the pseudo-label, aligns with the cluster assumption. In this regard, we propose Cluster-Aware Self-Training (CAST) for tabular data, which enhances existing self-training algorithms at a negligible cost while maintaining simplicity and versatility. Concretely, CAST calibrates confidence by regularizing the classifier's confidence based on local density for each class in the labeled training data, resulting in lower confidence for pseudo-labels in low-density regions. Extensive empirical evaluations on up to 21 real-world datasets confirm not only the superior performance of CAST but also its robustness in various setups in self-training contexts.

Junhong Min, Jimin Kim, Cheol-Hui Min et al.

Depth in the real world is rarely singular. Transmissive materials create layered ambiguities that confound conventional perception systems. Existing models remain passive, attempting to estimate static depth maps anchored to the nearest surface, while humans actively shift focus to perceive a desired depth. We introduce DepthFocus, a steerable Vision Transformer that redefines stereo depth estimation as intent-driven control. Conditioned on a scalar depth preference, the model dynamically adapts its computation to focus on the intended depth, enabling selective perception within complex scenes. The training primarily leverages our newly constructed 500k multi-layered synthetic dataset, designed to capture diverse see-through effects. DepthFocus not only achieves state-of-the-art performance on conventional single-depth benchmarks like BOOSTER, a dataset notably rich in transparent and reflective objects, but also quantitatively demonstrates intent-aligned estimation on our newly proposed real and synthetic multi-depth datasets. Moreover, it exhibits strong generalization capabilities on unseen see-through scenes, underscoring its robustness as a significant step toward active and human-like 3D perception.