MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba

An ecosystem of Transformer-based models has been established by building large models with extensive data. Parameter-efficient fine-tuning (PEFT) is a crucial technology for deploying these models to downstream tasks with minimal cost while achieving effective performance. Recently, Mamba, a State Space Model (SSM)-based model, has attracted attention as a potential alternative to Transformers. While many large-scale Mamba-based models have been proposed, efficiently adapting pre-trained Mamba-based models to downstream tasks remains unexplored. In this paper, we conduct an exploratory analysis of PEFT methods for Mamba. We investigate the effectiveness of existing PEFT methods for Transformers when applied to Mamba. We also modify these methods to better align with the Mamba architecture. Additionally, we propose new Mamba-specific PEFT methods that leverage the distinctive structure of Mamba. Our experiments indicate that PEFT performs more effectively for Mamba than Transformers. Lastly, we demonstrate how to effectively combine multiple PEFT methods and provide a framework that outperforms previous works. To ensure reproducibility, we will release the code after publication.

Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter

Compression of large and performant vision foundation models (VFMs) into arbitrary bit-wise operations (BitOPs) allows their deployment on various hardware. We propose to fine-tune a VFM to a mixed-precision quantized supernet. The supernet-based neural architecture search (NAS) can be adopted for this purpose, which trains a supernet, and then subnets within arbitrary hardware budgets can be extracted. However, existing methods face difficulties in optimizing the mixed-precision search space and incurring large memory costs during training. To tackle these challenges, first, we study the effective search space design for fine-tuning a VFM by comparing different operators (such as resolution, feature size, width, depth, and bit-widths) in terms of performance and BitOPs reduction. Second, we propose memory-efficient supernet training using a low-rank adapter (LoRA) and a progressive training strategy. The proposed method is evaluated for the recently proposed VFM, Segment Anything Model, fine-tuned on segmentation tasks. The searched model yields about a 95% reduction in BitOPs without incurring performance degradation.

PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality

Full DNN-based image signal processors (ISPs) have been actively studied and have achieved superior image quality compared to conventional ISPs. In contrast to this trend, we propose a lightweight ISP that consists of simple conventional ISP functions but achieves high image quality by increasing expressiveness. Specifically, instead of tuning the parameters of the ISP, we propose to control them dynamically for each environment and even locally. As a result, state-of-the-art accuracy is achieved on various datasets, including other tasks like tone mapping and image enhancement, even though ours is lighter than DNN-based ISPs. Additionally, our method can process different image sensors with a single ISP through dynamic control, whereas conventional methods require training for each sensor.

Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection

Unprocessed sensor outputs (RAW images) potentially improve both low-level and high-level computer vision algorithms, but the lack of large-scale RAW image datasets is a barrier to research. Thus, reversed Image Signal Processing (ISP) which converts existing RGB images into RAW images has been studied. However, most existing methods require camera-specific metadata or paired RGB and RAW images to model the conversion, and they are not always available. In addition, there are issues in handling diverse ISPs and recovering global illumination. To tackle these limitations, we propose a self-supervised reversed ISP method that does not require metadata and paired images. The proposed method converts a RGB image into a RAW-like image taken in the same environment with the same sensor as a reference RAW image by dynamically selecting parameters of the reversed ISP pipeline based on the reference RAW image. The parameter selection is trained via pseudo paired data created from unpaired RGB and RAW images. We show that the proposed method is able to learn various reversed ISPs with comparable accuracy to other state-of-the-art supervised methods and convert unknown RGB images from COCO and Flickr1M to target RAW-like images more accurately in terms of pixel distribution. We also demonstrate that our generated RAW images improve performance on real RAW image object detection task.

Efficient Joint Detection and Multiple Object Tracking with Spatially Aware Transformer

We propose a light-weight and highly efficient Joint Detection and Tracking pipeline for the task of Multi-Object Tracking using a fully-transformer architecture. It is a modified version of TransTrack, which overcomes the computational bottleneck associated with its design, and at the same time, achieves state-of-the-art MOTA score of 73.20%. The model design is driven by a transformer based backbone instead of CNN, which is highly scalable with the input resolution. We also propose a drop-in replacement for Feed Forward Network of transformer encoder layer, by using Butterfly Transform Operation to perform channel fusion and depth-wise convolution to learn spatial context within the feature maps, otherwise missing within the attention maps of the transformer. As a result of our modifications, we reduce the overall model size of TransTrack by 58.73% and the complexity by 78.72%. Therefore, we expect our design to provide novel perspectives for architecture optimization in future research related to multi-object tracking.

DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition

Image signal processor (ISP) plays an important role not only for human perceptual quality but also for computer vision. In most cases, experts resort to manual tuning of many parameters in the ISPs for perceptual quality. It failed in sub-optimal, especially for computer vision. Aiming to improve ISPs, two approaches have been actively proposed; tuning the parameters with machine learning, or constructing an ISP with DNN. The former is lightweight but lacks expressive powers. The latter has expressive powers but it was too heavy to calculate on edge devices. To this end, we propose DynamicISP, which consists of traditional simple ISP functions but their parameters are controlled dynamically per image according to what the downstream image recognition model felt to the previous frame. Our proposed method successfully controlled parameters of multiple ISP functions and got state-of-the-art accuracy with a small computational cost.

Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments

Image recognition models that can work in challenging environments (e.g., extremely dark, blurry, or high dynamic range conditions) must be useful. However, creating a training dataset for such environments is expensive and hard due to the difficulties of data collection and annotation. It is desirable if we could get a robust model without the need of hard-to-obtain dataset. One simple approach is to apply data augmentation such as color jitter and blur to standard RGB (sRGB) images in simple scenes. Unfortunately, this approach struggles to yield realistic images in terms of pixel intensity and noise distribution due to not considering the non-linearity of Image Signal Processor (ISP) and noise characteristics of an image sensor. Instead, we propose a noise-accounted RAW image augmentation method. In essence, color jitter and blur augmentation are applied to a RAW image before applying non-linear ISP, yielding realistic intensity. Furthermore, we introduce a noise amount alignment method that calibrates the domain gap in noise property caused by the augmentation. We show that our proposed noise-accounted RAW augmentation method doubles the image recognition accuracy in challenging environments only with simple training data.

MBAPose: Mask and Bounding-Box Aware Pose Estimation of Surgical Instruments with Photorealistic Domain Randomization

Surgical robots are controlled using a priori models based on robots' geometric parameters, which are calibrated before the surgical procedure. One of the challenges in using robots in real surgical settings is that parameters change over time, consequently deteriorating control accuracy. In this context, our group has been investigating online calibration strategies without added sensors. In one step toward that goal, we have developed an algorithm to estimate the pose of the instruments' shafts in endoscopic images. In this study, we build upon that earlier work and propose a new framework to more precisely estimate the pose of a rigid surgical instrument. Our strategy is based on a novel pose estimation model called MBAPose and the use of synthetic training data. Our experiments demonstrated an improvement of 21 % for translation error and 26 % for orientation error on synthetic test data with respect to our previous work. Results with real test data provide a baseline for further research.

FOSS: Multi-Person Age Estimation with Focusing on Objects and Still Seeing Surroundings

Age estimation from images can be used in many practical scenes. Most of the previous works targeted on the estimation from images in which only one face exists. Also, most of the open datasets for age estimation contain images like that. However, in some situations, age estimation in the wild and for multi-person is needed. Usually, such situations were solved by two separate models; one is a face detector model which crops facial regions and the other is an age estimation model which estimates from cropped images. In this work, we propose a method that can detect and estimate the age of multi-person with a single model which estimates age with focusing on faces and still seeing surroundings. Also, we propose a training method which enables the model to estimate multi-person well despite trained with images in which only one face is photographed. In the experiments, we evaluated our proposed method compared with the traditional approach using two separate models. As the result, the accuracy could be enhanced with our proposed method. We also adapted our proposed model to commonly used single person photographed age estimation datasets and it is proved that our method is also effective to those images and outperforms the state of the art accuracy.

Single-Shot Pose Estimation of Surgical Robot Instruments' Shafts from Monocular Endoscopic Images

Surgical robots are used to perform minimally invasive surgery and alleviate much of the burden imposed on surgeons. Our group has developed a surgical robot to aid in the removal of tumors at the base of the skull via access through the nostrils. To avoid injuring the patients, a collision-avoidance algorithm that depends on having an accurate model for the poses of the instruments' shafts is used. Given that the model's parameters can change over time owing to interactions between instruments and other disturbances, the online estimation of the poses of the instrument's shaft is essential. In this work, we propose a new method to estimate the pose of the surgical instruments' shafts using a monocular endoscope. Our method is based on the use of an automatically annotated training dataset and an improved pose-estimation deep-learning architecture. In preliminary experiments, we show that our method can surpass state of the art vision-based marker-less pose estimation techniques (providing an error decrease of 55% in position estimation, 64% in pitch, and 69% in yaw) by using artificial images.