Kibeom Kim

Hyundo Lee, Inwoo Hwang, Hyunsung Go et al.

Understanding geometric concepts, such as distance and shape, is essential for understanding the real world and also for many vision tasks. To incorporate such information into a visual representation of a scene, we propose learning to represent the scene by sketching, inspired by human behavior. Our method, coined Learning by Sketching (LBS), learns to convert an image into a set of colored strokes that explicitly incorporate the geometric information of the scene in a single inference step without requiring a sketch dataset. A sketch is then generated from the strokes where CLIP-based perceptual loss maintains a semantic similarity between the sketch and the image. We show theoretically that sketching is equivariant with respect to arbitrary affine transformations and thus provably preserves geometric information. Experimental results show that LBS substantially improves the performance of object attribute classification on the unlabeled CLEVR dataset, domain transfer between CLEVR and STL-10 datasets, and for diverse downstream tasks, confirming that LBS provides rich geometric information.

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.

Kibeom Kim, Hyundo Lee, Min Whoo Lee et al.

Tasks that involve interaction with various targets are called multi-target tasks. When applying general reinforcement learning approaches for such tasks, certain targets that are difficult to access or interact with may be neglected throughout the course of training - a predicament we call Under-explored Target Problem (UTP). To address this problem, we propose L-SA (Learning by adaptive Sampling and Active querying) framework that includes adaptive sampling and active querying. In the L-SA framework, adaptive sampling dynamically samples targets with the highest increase of success rates at a high proportion, resulting in curricular learning from easy to hard targets. Active querying prompts the agent to interact more frequently with under-explored targets that need more experience or exploration. Our experimental results on visual navigation tasks show that the L-SA framework improves sample efficiency as well as success rates on various multi-target tasks with UTP. Also, it is experimentally demonstrated that the cyclic relationship between adaptive sampling and active querying effectively improves the sample richness of under-explored targets and alleviates UTP.

Kibeom Kim, Min Whoo Lee, Yoonsung Kim et al.

Learning in a multi-target environment without prior knowledge about the targets requires a large amount of samples and makes generalization difficult. To solve this problem, it is important to be able to discriminate targets through semantic understanding. In this paper, we propose goal-aware cross-entropy (GACE) loss, that can be utilized in a self-supervised way using auto-labeled goal states alongside reinforcement learning. Based on the loss, we then devise goal-discriminative attention networks (GDAN) which utilize the goal-relevant information to focus on the given instruction. We evaluate the proposed methods on visual navigation and robot arm manipulation tasks with multi-target environments and show that GDAN outperforms the state-of-the-art methods in terms of task success ratio, sample efficiency, and generalization. Additionally, qualitative analyses demonstrate that our proposed method can help the agent become aware of and focus on the given instruction clearly, promoting goal-directed behavior.