Semin Kim

Jaehoon Yoo, Semin Kim, Doyup Lee et al.

Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the long-term dependency in videos due to the quadratic complexity of self-attention, and inherently suffering from slow inference time and error propagation due to the autoregressive process. In this paper, we propose Memory-efficient Bidirectional Transformer (MeBT) for end-to-end learning of long-term dependency in videos and fast inference. Based on recent advances in bidirectional transformers, our method learns to decode the entire spatio-temporal volume of a video in parallel from partially observed patches. The proposed transformer achieves a linear time complexity in both encoding and decoding, by projecting observable context tokens into a fixed number of latent tokens and conditioning them to decode the masked tokens through the cross-attention. Empowered by linear complexity and bidirectional modeling, our method demonstrates significant improvement over the autoregressive Transformers for generating moderately long videos in both quality and speed. Videos and code are available at https://sites.google.com/view/mebt-cvpr2023 .

Yeonwoo Cha, Semin Kim, Jinhyeon Kwon et al.

Any-to-any generation seeks to translate between arbitrary subsets of modalities, enabling flexible cross-modal synthesis. Despite recent success, existing flow-based approaches are challenged by their inefficiency, as they require large-scale datasets often with restrictive pairing constraints, incur high computational cost from modeling joint distribution, and rely on complex multi-stage training. We propose FlowBind, an efficient framework for any-to-any generation. Our approach is distinguished by its simplicity: it learns a shared latent space capturing cross-modal information, with modality-specific invertible flows bridging this latent to each modality. Both components are optimized jointly under a single flow-matching objective, and at inference the invertible flows act as encoders and decoders for direct translation across modalities. By factorizing interactions through the shared latent, FlowBind naturally leverages arbitrary subsets of modalities for training, and achieves competitive generation quality while substantially reducing data requirements and computational cost. Experiments on text, image, and audio demonstrate that FlowBind attains comparable quality while requiring up to 6x fewer parameters and training 10x faster than prior methods. The project page with code is available at https://yeonwoo378.github.io/official_flowbind.

Donggyun Kim, Seongwoong Cho, Semin Kim et al.

Large language models have evolved data-efficient generalists, benefiting from the universal language interface and large-scale pre-training. However, constructing a data-efficient generalist for dense visual prediction presents a distinct challenge due to the variation in label structures across different tasks. Consequently, generalization to unseen dense prediction tasks in the low-data regime is not straightforward and has received less attention from previous vision generalists. In this study, we explore a universal model that can flexibly adapt to unseen dense label structures with a few examples, enabling it to serve as a data-efficient vision generalist in diverse real-world scenarios. To this end, we base our method on a powerful meta-learning framework and explore several axes to improve its performance and versatility for real-world problems, such as flexible adaptation mechanisms and scalability. We evaluate our model across a spectrum of unseen real-world scenarios where low-shot learning is desirable, including video, 3D, medical, biological, and user-interactive tasks. Equipped with a generic architecture and an effective adaptation mechanism, our model flexibly adapts to all of these tasks with at most 50 labeled images, showcasing a significant advancement over existing data-efficient generalist approaches. Codes are available at https://github.com/GitGyun/chameleon.

Sunyong Seo, Huisu Yoon, Semin Kim et al.

The U-Net architecture and its variants have remained state-of-the-art (SOTA) for retinal vessel segmentation over the past decade. In this study, we introduce a Full Scale Guided Network (FSG-Net), where the feature representation network with modernized convolution blocks extracts full-scale information and the guided convolution block refines that information. Attention-guided filter is introduced to the guided convolution block under the interpretation that the filter behaves like the unsharp mask filter. Passing full-scale information to the attention block allows for the generation of improved attention maps, which are then passed to the attention-guided filter, resulting in performance enhancement of the segmentation network. The structure preceding the guided convolution block can be replaced by any U-Net variant, which enhances the scalability of the proposed approach. For a fair comparison, we re-implemented recent studies available in public repositories to evaluate their scalability and reproducibility. Our experiments also show that the proposed network demonstrates competitive results compared to current SOTA models on various public datasets. Ablation studies demonstrate that the proposed model is competitive with much smaller parameter sizes. Lastly, by applying the proposed model to facial wrinkle segmentation, we confirmed the potential for scalability to similar tasks in other domains. Our code is available on https://github.com/ZombaSY/FSG-Net-pytorch.

Semin Kim, Jaehoon Yoo, Jinwoo Kim et al.

In this work, we investigate a method for simulation-free training of Neural Ordinary Differential Equations (NODEs) for learning deterministic mappings between paired data. Despite the analogy of NODEs as continuous-depth residual networks, their application in typical supervised learning tasks has not been popular, mainly due to the large number of function evaluations required by ODE solvers and numerical instability in gradient estimation. To alleviate this problem, we employ the flow matching framework for simulation-free training of NODEs, which directly regresses the parameterized dynamics function to a predefined target velocity field. Contrary to generative tasks, however, we show that applying flow matching directly between paired data can often lead to an ill-defined flow that breaks the coupling of the data pairs (e.g., due to crossing trajectories). We propose a simple extension that applies flow matching in the embedding space of data pairs, where the embeddings are learned jointly with the dynamic function to ensure the validity of the flow which is also easier to learn. We demonstrate the effectiveness of our method on both regression and classification tasks, where our method outperforms existing NODEs with a significantly lower number of function evaluations. The code is available at https://github.com/seminkim/simulation-free-node.

Semin Kim, Yeonwoo Cha, Jaehoon Yoo et al.

We investigate a general approach for improving user prompts in text-to-image (T2I) diffusion models by finding prompts that maximize a reward function specified at test-time. Although diverse reward models are used for evaluating image generation, existing automated prompt engineering methods typically target specific reward configurations. Consequently, these specialized designs exhibit suboptimal performance when applied to new prompt engineering scenarios involving different reward models. To address this limitation, we introduce RATTPO (Reward-Agnostic Test-Time Prompt Optimization), a flexible test-time optimization method applicable across various reward scenarios without modification. RATTPO iteratively searches for optimized prompts by querying large language models (LLMs) \textit{without} requiring reward-specific task descriptions. Instead, it uses the optimization trajectory and a novel reward-aware feedback signal (termed a "hint") as context. Empirical results demonstrate the versatility of RATTPO, effectively enhancing user prompts across diverse reward setups that assess various generation aspects, such as aesthetics, general human preference, or spatial relationships between objects. RATTPO surpasses other test-time search baselines in search efficiency, running 4.8 times faster than naive reward-agnostic test-time search baseline on average. Furthermore, with sufficient inference budget, it can achieve comparable performance to learning-based baselines that require reward-specific fine-tuning. The code is available at https://github.com/seminkim/RATTPO.

Whie Jung, Semin Kim, Junee Kim et al.

Human intelligence effortlessly interprets visual scenes along a rich spectrum of semantic dimensions. However, existing approaches to language-grounded visual concept learning are limited to a few predefined primitive axes, such as color and shape, and are typically explored in synthetic datasets. In this work, we propose a scalable framework that adaptively identifies image-related concept axes and grounds visual concepts along these axes in real-world scenes. Leveraging a pretrained vision-language model and our universal prompting strategy, our framework identifies a diverse image-related axes without any prior knowledge. Our universal concept encoder adaptively binds visual features to the discovered axes without introducing additional model parameters for each concept. To ground visual concepts along the discovered axes, we optimize a compositional anchoring objective, which ensures that each axis can be independently manipulated without affecting others. We demonstrate the effectiveness of our framework on subsets of ImageNet, CelebA-HQ, and AFHQ, showcasing superior editing capabilities across diverse real-world concepts that are too varied to be manually predefined. Our method also exhibits strong compositional generalization, outperforming existing visual concept learning and text-based editing methods. The code is available at https://github.com/whieya/Language-grounded-VCL.

Yoorhim Cho, Hongyeob Kim, Semin Kim et al.

Visuo-tactile perception aims to understand an object's tactile properties, such as texture, softness, and rigidity. However, the field remains underexplored because collecting tactile data is costly and labor-intensive. We observe that visually distinct objects can exhibit similar surface textures or material properties. For example, a leather sofa and a leather jacket have different appearances but share similar tactile properties. This implies that tactile understanding can be guided by material cues in visual data, even without direct tactile supervision. In this paper, we introduce RA-Touch, a retrieval-augmented framework that improves visuo-tactile perception by leveraging visual data enriched with tactile semantics. We carefully recaption a large-scale visual dataset with tactile-focused descriptions, enabling the model to access tactile semantics typically absent from conventional visual datasets. A key challenge remains in effectively utilizing these tactile-aware external descriptions. RA-Touch addresses this by retrieving visual-textual representations aligned with tactile inputs and integrating them to focus on relevant textural and material properties. By outperforming prior methods on the TVL benchmark, our method demonstrates the potential of retrieval-based visual reuse for tactile understanding. Code is available at https://aim-skku.github.io/RA-Touch

Minchan Kim, Myeonghun Jeong, Byoung Jin Choi et al.

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.

Yeonwoo Cha, Jaehoon Yoo, Semin Kim et al.

Flow-based models learn a target distribution by modeling a marginal velocity field, defined as the average of sample-wise velocities connecting each sample from a simple prior to the target data. When sample-wise velocities conflict at the same intermediate state, however, this averaged velocity can misguide samples toward low-density regions, degrading generation quality. To address this issue, we propose the Flow Divergence Sampler (FDS), a training-free framework that refines intermediate states before each solver step. Our key finding reveals that the severity of this misguidance is quantified by the divergence of the marginal velocity field that is readily computable during inference with a well-optimized model. FDS exploits this signal to steer states toward less ambiguous regions. As a plug-and-play framework compatible with standard solvers and off-the-shelf flow backbones, FDS consistently improves fidelity across various generation tasks including text-to-image synthesis, and inverse problems.

DaeEun Yoon, Semin Kim, SangWook Yoo et al.

In recent years, there has been tremendous progress in object detection performance. However, despite these advances, the detection performance for small objects is significantly inferior to that of large objects. Detecting small objects is one of the most challenging and important problems in computer vision. To improve the detection performance for small objects, we propose an optimal data augmentation method using Fast AutoAugment. Through our proposed method, we can quickly find optimal augmentation policies that can overcome degradation when detecting small objects, and we achieve a 20% performance improvement on the DOTA dataset.

Ju Yeon Kang, Jaehong Park, Semin Kim et al.

Recently, AI-generated image detection has gained increasing attention, as the rapid advancement of image generation technologies has raised serious concerns about their potential misuse. While existing detection methods have achieved promising results, their performance often degrades significantly when facing fake images from unseen, out-of-distribution (OOD) generative models, since they primarily rely on model-specific artifacts and thus overfit to the models used for training. To address this limitation, we propose a novel representation, namely Semantic-Aware Reconstruction Error (SARE), that measures the semantic difference between an image and its caption-guided reconstruction. The key hypothesis behind SARE is that real images, whose captions often fail to fully capture their complex visual content, may undergo noticeable semantic shifts during the caption-guided reconstruction process. In contrast, fake images, which closely align with their captions, show minimal semantic changes. By quantifying these semantic shifts, SARE provides a robust and discriminative feature for detecting fake images across diverse generative models. Additionally, we introduce a fusion module that integrates SARE into the backbone detector via a cross-attention mechanism. Image features attend to semantic representations extracted from SARE, enabling the model to adaptively leverage semantic information. Experimental results demonstrate that the proposed method achieves strong generalization, outperforming existing baselines on benchmarks including GenImage and ForenSynths. We further validate the effectiveness of caption guidance through a detailed analysis of semantic shifts, confirming its ability to enhance detection robustness.

Sunyong Seo, Semin Kim, Jongha Lee

Facial analysis exhibits task-specific feature variations. While Convolutional Neural Networks (CNNs) have enabled the fine-grained representation of spatial information, Vision Transformers (ViTs) have facilitated the representation of semantic information at the patch level. Although the generalization of conventional methodologies has advanced visual interpretability, there remains paucity of research that preserves the unified feature representation on single task learning during the training process. In this work, we introduce ET-Fuser, a novel methodology for learning ensemble token by leveraging attention mechanisms based on task priors derived from pre-trained models for facial analysis. Specifically, we propose a robust prior unification learning method that generates a ensemble token within a self-attention mechanism, which shares the mutual information along the pre-trained encoders. This ensemble token approach offers high efficiency with negligible computational cost. Our results show improvements across a variety of facial analysis, with statistically significant enhancements observed in the feature representations.

Ju Yeon Kang, Ji Won Yoon, Semin Kim et al.

Recently, fake audio detection has gained significant attention, as advancements in speech synthesis and voice conversion have increased the vulnerability of automatic speaker verification (ASV) systems to spoofing attacks. A key challenge in this task is generalizing models to detect unseen, out-of-distribution (OOD) attacks. Although existing approaches have shown promising results, they inherently suffer from overconfidence issues due to the usage of softmax for classification, which can produce unreliable predictions when encountering unpredictable spoofing attempts. To deal with this limitation, we propose a novel framework called fake audio detection with evidential learning (FADEL). By modeling class probabilities with a Dirichlet distribution, FADEL incorporates model uncertainty into its predictions, thereby leading to more robust performance in OOD scenarios. Experimental results on the ASVspoof2019 Logical Access (LA) and ASVspoof2021 LA datasets indicate that the proposed method significantly improves the performance of baseline models. Furthermore, we demonstrate the validity of uncertainty estimation by analyzing a strong correlation between average uncertainty and equal error rate (EER) across different spoofing algorithms.

Semin Kim, Myeonghun Jeong, Hyeonseung Lee et al.

In this paper, we propose MakeSinger, a semi-supervised training method for singing voice synthesis (SVS) via classifier-free diffusion guidance. The challenge in SVS lies in the costly process of gathering aligned sets of text, pitch, and audio data. MakeSinger enables the training of the diffusion-based SVS model from any speech and singing voice data regardless of its labeling, thereby enhancing the quality of generated voices with large amount of unlabeled data. At inference, our novel dual guiding mechanism gives text and pitch guidance on the reverse diffusion step by estimating the score of masked input. Experimental results show that the model trained in a semi-supervised manner outperforms other baselines trained only on the labeled data in terms of pronunciation, pitch accuracy and overall quality. Furthermore, we demonstrate that by adding Text-to-Speech (TTS) data in training, the model can synthesize the singing voices of TTS speakers even without their singing voices.