20 papers
LoRA Superposition across Pretrained Models
Keigo Watanabe, Hiroshi Kera, Kazuhiko Kawamoto
Low-rank adaptation (LoRA) is usually tied to the pretrained backbone on which it is learned. We ask whether LoRAs trained independently for the same task on different pretrained b…
What Does Prompt Learning Change? -A Natural-Language Concept Analysis of Vision-Language Models
Ryo Kamiya, Hiroshi Kera, Kazuhiko Kawamoto
Prompt learning adapts vision-language models such as CLIP by optimizing continuous prompt vectors, but the learned prompts are difficult to interpret in natural language. We prese…
Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions
Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto
Zero-shot textual explanations aim to make image classifiers more transparent by probing their internal representations, without relying on task-specific supervision or LVLMs. Howe…
Guided Diffusion Sampling for Precipitation Forecast Interventions
Ayumu Ueyama, Kazuhiko Kawamoto, Hiroshi Kera
Extreme precipitation causes severe societal and economic damage, and weather control has long been discussed as a potential mitigation strategy. However, to the best of our knowle…
Learning Large-Scale Modular Addition with an Auxiliary Modulus
Hanato Kikuchi, Ryosuke Masuya, Kazuhiko Kawamoto +1
Learning parity functions, more general modular addition, is a challenging machine learning task due to its input sensitivity. A recent study substantially scaled modular addition…
Towards Viewpoint-Robust End-to-End Autonomous Driving with 3D Foundation Model Priors
Hiroki Hashimoto, Hiromichi Goto, Hiroyuki Sugai +2
Robust trajectory planning under camera viewpoint changes is important for scalable end-to-end autonomous driving. However, existing models often depend heavily on the camera viewp…
Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning
Taishu Arashima, Hiroshi Kera, Kazuhiko Kawamoto
Human trajectory prediction plays a crucial role in applications such as autonomous navigation and video surveillance. While recent works have explored the integration of human ske…
Zero-Shot Textual Explanations via Translating Decision-Critical Features
Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto
Textual explanations make image classifier decisions transparent by describing the prediction rationale in natural language. Large vision-language models can generate captions but…
Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control
Shingo Ayabe, Hiroshi Kera, Kazuhiko Kawamoto
Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-spa…
Learning Moderately Input-Sensitive Functions: A Case Study in QR Code Decoding
Kazuki Yoda, Kazuhiko Kawamoto, Hiroshi Kera
The hardness of learning a function that attains a target task relates to its input-sensitivity. For example, image classification tasks are input-insensitive as minor corruptions…
Discovering Learning-Friendly Generation Orders for Sequential Computation
Yuta Sato, Kazuhiko Kawamoto, Hiroshi Kera
Sequential computation via autoregressive generation can make difficult tasks learnable, but the generation order of intermediate states strongly affects whether training succeeds.…
Cross-Model Transfer of Task Vectors via Few-Shot Orthogonal Alignment
Kazuhiko Kawamoto, Atsuhiro Endo, Hiroshi Kera
Task arithmetic enables efficient model editing by representing task-specific changes as vectors in parameter space. Task arithmetic typically assumes that the source and target mo…
Undertrained Image Reconstruction for Realistic Degradation in Blind Image Super-Resolution
Ru Ito, Supatta Viriyavisuthisakul, Kazuhiko Kawamoto +1
Most super-resolution (SR) models struggle with real-world low-resolution (LR) images. This issue arises because the degradation characteristics in the synthetic datasets differ fr…
Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations
Shingo Ayabe, Takuto Otomo, Hiroshi Kera +1
Offline reinforcement learning, which learns solely from datasets without environmental interaction, has gained attention. This approach, similar to traditional online deep reinfor…
Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
Takuma Fukuda, Hiroshi Kera, Kazuhiko Kawamoto
We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and…
Explaining Object Detectors via Collective Contribution of Pixels
Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto
Visual explanations for object detectors are crucial for enhancing their reliability. Object detectors identify and localize instances by assessing multiple visual features collect…
Low-Quality Image Detection by Hierarchical VAE
Tomoyasu Nanaumi, Kazuhiko Kawamoto, Hiroshi Kera
To make an employee roster, photo album, or training dataset of generative models, one needs to collect high-quality images while dismissing low-quality ones. This study addresses…
VarteX: Enhancing Weather Forecast through Distributed Variable Representation
Ayumu Ueyama, Kazuhiko Kawamoto, Hiroshi Kera
Weather forecasting is essential for various human activities. Recent data-driven models have outperformed numerical weather prediction by utilizing deep learning in forecasting pe…
Matching Semantically Similar Non-Identical Objects
Yusuke Marumo, Kazuhiko Kawamoto, Satomi Tanaka +2
Not identical but similar objects are ubiquitous in our world, ranging from four-legged animals such as dogs and cats to cars of different models and flowers of various colors. Thi…
Identifying Important Group of Pixels using Interactions
Kosuke Sumiyasu, Kazuhiko Kawamoto, Hiroshi Kera
To better understand the behavior of image classifiers, it is useful to visualize the contribution of individual pixels to the model prediction. In this study, we propose a method,…