Tint Your Models Task-wise for Improved Multi-task Model Merging

Traditional model merging methods for multi-task learning (MTL) address task conflicts with straightforward strategies such as weight averaging, sign consensus, or minimal test-time adjustments. This presumably counts on the assumption that a merged encoder still retains abundant task knowledge from individual encoders, implying that its shared representation is sufficiently general across tasks. However, our insight is that adding just a single trainable task-specific layer further can bring striking performance gains, as demonstrated by our pilot study. Motivated by this finding, we propose Model Tinting, a new test-time approach that introduces a single task-specific layer for each task as trainable adjustments. Our method jointly trains merging coefficients and task-specific layers, which effectively reduces task conflicts with minimal additional costs. Additionally, we propose a sampling method that utilizes the difference in confidence levels of both merged and individual encoders. Extensive experiments demonstrate our method's effectiveness, which achieves state-of-the-art performance across both computer vision and natural language processing tasks and significantly surpasses prior works. Our code is available at https://github.com/AIM-SKKU/ModelTinting.

A Gated MLP Architecture for Learning Topological Dependencies in Spatio-Temporal Graphs

Graph Neural Networks (GNNs) and Transformer have been increasingly adopted to learn the complex vector representations of spatio-temporal graphs, capturing intricate spatio-temporal dependencies crucial for applications such as traffic datasets. Although many existing methods utilize multi-head attention mechanisms and message-passing neural networks (MPNNs) to capture both spatial and temporal relations, these approaches encode temporal and spatial relations independently, and reflect the graph's topological characteristics in a limited manner. In this work, we introduce the Cycle to Mixer (Cy2Mixer), a novel spatio-temporal GNN based on topological non-trivial invariants of spatio-temporal graphs with gated multi-layer perceptrons (gMLP). The Cy2Mixer is composed of three blocks based on MLPs: A message-passing block for encapsulating spatial information, a cycle message-passing block for enriching topological information through cyclic subgraphs, and a temporal block for capturing temporal properties. We bolster the effectiveness of Cy2Mixer with mathematical evidence emphasizing that our cycle message-passing block is capable of offering differentiated information to the deep learning model compared to the message-passing block. Furthermore, empirical evaluations substantiate the efficacy of the Cy2Mixer, demonstrating state-of-the-art performances across various traffic benchmark datasets.

Diffusion Inertial Poser: Human Motion Reconstruction from Arbitrary Sparse IMU Configurations

Motion capture from a limited number of inertial measurement units (IMUs) has important applications in health, human performance, and virtual reality. Real-world limitations and application-specific goals dictate different IMU configurations (i.e., number of IMUs and chosen attachment body segments), trading off accuracy and practicality. Although recent works were successful in accurately reconstructing whole-body motion from six IMUs, these systems only work with a specific IMU configuration. Here we propose a single diffusion generative model, Diffusion Inertial Poser (DiffIP), which reconstructs human motion in real-time from arbitrary IMU configurations. We show that DiffIP has the benefit of flexibility with respect to the IMU configuration while being as accurate as the state-of-the-art for the commonly used six IMU configuration. Our system enables selecting an optimal configuration for different applications without retraining the model. For example, when only four IMUs are available, DiffIP found that the configuration that minimizes errors in joint kinematics instruments the thighs and forearms. However, global translation reconstruction is better when instrumenting the feet instead of the thighs. Although our approach is agnostic to the underlying model, we built DiffIP based on physiologically realistic musculoskeletal models to enable use in biomedical research and health applications.

FastSurf: Fast Neural RGB-D Surface Reconstruction using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning

We introduce FastSurf, an accelerated neural radiance field (NeRF) framework that incorporates depth information for 3D reconstruction. A dense feature grid and shallow multi-layer perceptron are used for fast and accurate surface optimization of the entire scene. Our per-frame intrinsic refinement scheme corrects the frame-specific errors that cannot be handled by global optimization. Furthermore, FastSurf utilizes a classical real-time 3D surface reconstruction method, the truncated signed distance field (TSDF) Fusion, as prior knowledge to pretrain the feature grid to accelerate the training. The quantitative and qualitative experiments comparing the performances of FastSurf against prior work indicate that our method is capable of quickly and accurately reconstructing a scene with high-frequency details. We also demonstrate the effectiveness of our per-frame intrinsic refinement and TSDF Fusion prior learning techniques via an ablation study.

NoiseTransfer: Image Noise Generation with Contrastive Embeddings

Deep image denoising networks have achieved impressive success with the help of a considerably large number of synthetic train datasets. However, real-world denoising is a still challenging problem due to the dissimilarity between distributions of real and synthetic noisy datasets. Although several real-world noisy datasets have been presented, the number of train datasets (i.e., pairs of clean and real noisy images) is limited, and acquiring more real noise datasets is laborious and expensive. To mitigate this problem, numerous attempts to simulate real noise models using generative models have been studied. Nevertheless, previous works had to train multiple networks to handle multiple different noise distributions. By contrast, we propose a new generative model that can synthesize noisy images with multiple different noise distributions. Specifically, we adopt recent contrastive learning to learn distinguishable latent features of the noise. Moreover, our model can generate new noisy images by transferring the noise characteristics solely from a single reference noisy image. We demonstrate the accuracy and the effectiveness of our noise model for both known and unknown noise removal.

Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcers

We introduce AiD Regen, a novel system that generates 3D wound models combining 2D semantic segmentation with 3D reconstruction so that they can be printed via 3D bio-printers during the surgery to treat diabetic foot ulcers (DFUs). AiD Regen seamlessly binds the full pipeline, which includes RGB-D image capturing, semantic segmentation, boundary-guided point-cloud processing, 3D model reconstruction, and 3D printable G-code generation, into a single system that can be used out of the box. We developed a multi-stage data preprocessing method to handle small and unbalanced DFU image datasets. AiD Regen's human-in-the-loop machine learning interface enables clinicians to not only create 3D regenerative patches with just a few touch interactions but also customize and confirm wound boundaries. As evidenced by our experiments, our model outperforms prior wound segmentation models and our reconstruction algorithm is capable of generating 3D wound models with compelling accuracy. We further conducted a case study on a real DFU patient and demonstrated the effectiveness of AiD Regen in treating DFU wounds.

Cycled Compositional Learning between Images and Text

We present an approach named the Cycled Composition Network that can measure the semantic distance of the composition of image-text embedding. First, the Composition Network transit a reference image to target image in an embedding space using relative caption. Second, the Correction Network calculates a difference between reference and retrieved target images in the embedding space and match it with a relative caption. Our goal is to learn a Composition mapping with the Composition Network. Since this one-way mapping is highly under-constrained, we couple it with an inverse relation learning with the Correction Network and introduce a cycled relation for given Image We participate in Fashion IQ 2020 challenge and have won the first place with the ensemble of our model.

CurlingNet: Compositional Learning between Images and Text for Fashion IQ Data

We present an approach named CurlingNet that can measure the semantic distance of composition of image-text embedding. In order to learn an effective image-text composition for the data in the fashion domain, our model proposes two key components as follows. First, the Delivery makes the transition of a source image in an embedding space. Second, the Sweeping emphasizes query-related components of fashion images in the embedding space. We utilize a channel-wise gating mechanism to make it possible. Our single model outperforms previous state-of-the-art image-text composition models including TIRG and FiLM. We participate in the first fashion-IQ challenge in ICCV 2019, for which ensemble of our model achieves one of the best performances.

Restore from Restored: Video Restoration with Pseudo Clean Video

In this paper, we propose a self-supervised video denoising method called "restore-from-restored" that fine-tunes a baseline network by using a pseudo clean video at the test phase. The pseudo clean video can be obtained by applying an input noisy video to the pre-trained baseline network. By adopting a fully convolutional network (FCN) as the baseline, we can restore videos without accurate optical flow and registration due to its translation-invariant property unlike many conventional video restoration methods. Moreover, the proposed method can take advantage of the existence of many similar patches across consecutive frames (i.e., patch-recurrence), which can boost performance of the baseline network by a large margin. We analyze the restoration performance of the FCN fine-tuned with the proposed self-supervision-based training algorithm, and demonstrate that FCN can utilize recurring patches without the need for registration among adjacent frames. The proposed method can be applied to any FCN-based denoising models. In our experiments, we apply the proposed method to the state-of-the-art denoisers, and our results indicate a considerable improvementin task performance.

Restore from Restored: Single Image Denoising with Pseudo Clean Image

Under certain statistical assumptions of noise (e.g., zero-mean noise), recent self-supervised approaches for denoising have been introduced to learn network parameters without ground-truth clean images, and these methods can restore an image by exploiting information available from the given input (i.e., internal statistics) at test time. However, self-supervised methods are not yet properly combined with conventional supervised denoising methods which train the denoising networks with a large number of external training images. Thus, we propose a new denoising approach that can greatly outperform the state-of-the-art supervised denoising methods by adapting (fine-tuning) their network parameters to the given specific input through self-supervision without changing the fully original network architectures. We demonstrate that the proposed method can be easily employed with state-of-the-art denoising networks without additional parameters, and achieve state-of-the-art performance on numerous denoising benchmark datasets.