There are not many large medical image datasets available. For these datasets, too small deep learning models can't learn useful features, so they don't work well due to underfitting, and too big models tend to overfit the limited data. As a result, there is a compromise between the two issues. This paper proposes a training strategy Medi-CAT to overcome the underfitting and overfitting phenomena in medical imaging datasets. Specifically, the proposed training methodology employs large pre-trained vision transformers to overcome underfitting and adversarial and contrastive learning techniques to prevent overfitting. The proposed method is trained and evaluated on four medical image classification datasets from the MedMNIST collection. Our experimental results indicate that the proposed approach improves the accuracy up to 2% on three benchmark datasets compared to well-known approaches, whereas it increases the performance up to 4.1% over the baseline methods.
Due to an alarming trend related to obesity affecting 93.3 million adults in the United States alone, body mass index (BMI) and body weight have drawn significant interest in various health monitoring applications. Consequently, several studies have proposed self-diagnostic facial image-based BMI prediction methods for healthy weight monitoring. These methods have mostly used convolutional neural network (CNN) based regression baselines, such as VGG19, ResNet50, and Efficient-NetB0, for BMI prediction from facial images. However, the high computational requirement of these heavy-weight CNN models limits their deployment to resource-constrained mobile devices, thus deterring weight monitoring using smartphones. This paper aims to develop a lightweight facial patch-based ensemble (PatchBMI-Net) for BMI prediction to facilitate the deployment and weight monitoring using smartphones. Extensive experiments on BMI-annotated facial image datasets suggest that our proposed PatchBMI-Net model can obtain Mean Absolute Error (MAE) in the range [3.58, 6.51] with a size of about 3.3 million parameters. On cross-comparison with heavyweight models, such as ResNet-50 and Xception, trained for BMI prediction from facial images, our proposed PatchBMI-Net obtains equivalent MAE along with the model size reduction of about 5.4x and the average inference time reduction of about 3x when deployed on Apple-14 smartphone. Thus, demonstrating performance efficiency as well as low latency for on-device deployment and weight monitoring using smartphone applications.
Text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models has shown great promise but still suffers from inconsistent 3D geometric structures (Janus problems) and severe artifacts. The aforementioned problems mainly stem from 2D diffusion models lacking 3D awareness during the lifting. In this work, we present GeoDream, a novel method that incorporates explicit generalized 3D priors with 2D diffusion priors to enhance the capability of obtaining unambiguous 3D consistent geometric structures without sacrificing diversity or fidelity. Specifically, we first utilize a multi-view diffusion model to generate posed images and then construct cost volume from the predicted image, which serves as native 3D geometric priors, ensuring spatial consistency in 3D space. Subsequently, we further propose to harness 3D geometric priors to unlock the great potential of 3D awareness in 2D diffusion priors via a disentangled design. Notably, disentangling 2D and 3D priors allows us to refine 3D geometric priors further. We justify that the refined 3D geometric priors aid in the 3D-aware capability of 2D diffusion priors, which in turn provides superior guidance for the refinement of 3D geometric priors. Our numerical and visual comparisons demonstrate that GeoDream generates more 3D consistent textured meshes with high-resolution realistic renderings (i.e., 1024 $\times$ 1024) and adheres more closely to semantic coherence.
Recently, Vision Language Models (VLMs) have gained significant attention, exhibiting notable advancements across various tasks by leveraging extensive image-text paired data. However, prevailing VLMs often treat Visual Question Answering (VQA) as perception tasks, employing black-box models that overlook explicit modeling of relationships between different questions within the same visual scene. Moreover, the existing VQA methods that rely on Knowledge Bases (KBs) might frequently encounter biases from limited data and face challenges in relevant information indexing. Attempt to overcome these limitations, this paper introduces an explainable multi-agent collaboration framework by tapping into knowledge embedded in Large Language Models (LLMs) trained on extensive corpora. Inspired by human cognition, our framework uncovers latent information within the given question by employing three agents, i.e., Seeker, Responder, and Integrator, to perform a top-down reasoning process. The Seeker agent generates relevant issues related to the original question. The Responder agent, based on VLM, handles simple VQA tasks and provides candidate answers. The Integrator agent combines information from the Seeker agent and the Responder agent to produce the final VQA answer. Through the above collaboration mechanism, our framework explicitly constructs a multi-view knowledge base for a specific image scene, reasoning answers in a top-down processing manner. We extensively evaluate our method on diverse VQA datasets and VLMs, demonstrating its broad applicability and interpretability with comprehensive experimental results.
Large multi-modal models (LMMs) hold the potential to usher in a new era of automated visual assistance for people who are blind or low vision (BLV). Yet, these models have not been systematically evaluated on data captured by BLV users. We address this by empirically assessing CLIP, a widely-used LMM likely to underpin many assistive technologies. Testing 25 CLIP variants in a zero-shot classification task, we find that their accuracy is 15 percentage points lower on average for images captured by BLV users than web-crawled images. This disparity stems from CLIP's sensitivities to 1) image content (e.g. not recognizing disability objects as well as other objects); 2) image quality (e.g. not being robust to lighting variation); and 3) text content (e.g. not recognizing objects described by tactile adjectives as well as visual ones). We delve deeper with a textual analysis of three common pre-training datasets: LAION-400M, LAION-2B and DataComp-1B, showing that disability content is rarely mentioned. We then provide three examples that illustrate how the performance disparities extend to three downstream models underpinned by CLIP: OWL-ViT, CLIPSeg and DALL-E2. We find that few-shot learning with as few as 5 images can mitigate CLIP's quality-of-service disparities for BLV users in some scenarios, which we discuss alongside a set of other possible mitigations.
Cross-domain few-shot hyperspectral image classification focuses on learning prior knowledge from a large number of labeled samples from source domain and then transferring the knowledge to the tasks which contain only few labeled samples in target domains. Following the metric-based manner, many current methods first extract the features of the query and support samples, and then directly predict the classes of query samples according to their distance to the support samples or prototypes. The relations between samples have not been fully explored and utilized. Different from current works, this paper proposes to learn sample relations from different views and take them into the model learning process, to improve the cross-domain few-shot hyperspectral image classification. Building on current DCFSL method which adopts a domain discriminator to deal with domain-level distribution difference, the proposed method applys contrastive learning to learn the class-level sample relations to obtain more discriminable sample features. In addition, it adopts a transformer based cross-attention learning module to learn the set-level sample relations and acquire the attentions from query samples to support samples. Our experimental results have demonstrated the contribution of the multi-view relation learning mechanism for few-shot hyperspectral image classification when compared with the state of the art methods.
Cartoon editing, appreciated by both professional illustrators and hobbyists, allows extensive creative freedom and the development of original narratives within the cartoon domain. However, the existing literature on cartoon editing is complex and leans heavily on manual operations, owing to the challenge of automatic identification of individual character instances. Therefore, an automated segmentation of these elements becomes imperative to facilitate a variety of cartoon editing applications such as visual style editing, motion decomposition and transfer, and the computation of stereoscopic depths for an enriched visual experience. Unfortunately, most current segmentation methods are designed for natural photographs, failing to recognize from the intricate aesthetics of cartoon subjects, thus lowering segmentation quality. The major challenge stems from two key shortcomings: the rarity of high-quality cartoon dedicated datasets and the absence of competent models for high-resolution instance extraction on cartoons. To address this, we introduce a high-quality dataset of over 100k paired high-resolution cartoon images and their instance labeling masks. We also present an instance-aware image segmentation model that can generate accurate, high-resolution segmentation masks for characters in cartoon images. We present that the proposed approach enables a range of segmentation-dependent cartoon editing applications like 3D Ken Burns parallax effects, text-guided cartoon style editing, and puppet animation from illustrations and manga.
Marine snow, the floating particles in underwater images, severely degrades the visibility and performance of human and machine vision systems. This paper proposes a novel method to reduce the marine snow interference using deep learning techniques. We first synthesize realistic marine snow samples by training a Generative Adversarial Network (GAN) model and combine them with natural underwater images to create a paired dataset. We then train a U-Net model to perform marine snow removal as an image to image translation task. Our experiments show that the U-Net model can effectively remove both synthetic and natural marine snow with high accuracy, outperforming state-of-the-art methods such as the Median filter and its adaptive variant. We also demonstrate the robustness of our method by testing it on the MSRB dataset, which contains synthetic artifacts that our model has not seen during training. Our method is a practical and efficient solution for enhancing underwater images affected by marine snow.
Multimodal large language models have made significant advancements in recent years, yet they still suffer from a common issue known as the "hallucination problem" where the models generate textual descriptions that contain inaccurate or non-existent content from the image. To address this issue, this paper introduces a novel strategy: Hallucination-Aware Direct Preference Optimization (HA-DPO). Our approach treats the hallucination problem as a unique preference selection issue, where the model is trained to favor the non-hallucinating response when presented with two responses of the same image (one accurate and one hallucinating). This paper also presents an efficient process for constructing hallucination sample pairs to ensure high-quality, style-consistent pairs for stable HA-DPO training. We applied this strategy to two mainstream multimodal models, and the results showed a significant reduction in the hallucination problem and an enhancement in the models' generalization capabilities. With HA-DPO, the MiniGPT-4 model demonstrates significant advancements: POPE accuracy increases from 51.13% to 85.66% (34.5% absolute improvement), and the MME score escalates from 968.58 to 1365.76 (41% relative improvement). The code, models, and datasets will be made publicly available.
In object detection, achieving constant accuracy is challenging due to the variability of object sizes. One possible solution to this problem is to optimize the input resolution, known as a multi-resolution strategy. Previous approaches for optimizing resolution are often based on pre-defined resolutions or a dynamic neural network, but there is a lack of study for run-time resolution optimization for existing architecture. In this paper, we propose an adaptive resolution scaling network called DyRA, which comprises convolutions and transformer encoder blocks, for existing detectors. Our DyRA returns a scale factor from an input image, which enables instance-specific scaling. This network is jointly trained with detectors with specially designed loss functions, namely ParetoScaleLoss and BalanceLoss. The ParetoScaleLoss produces an adaptive scale factor from the image, while the BalanceLoss optimizes the scale factor according to localization power for the dataset. The loss function is designed to minimize accuracy drop about the contrasting objective of small and large objects. Our experiments on COCO, RetinaNet, Faster-RCNN, FCOS, and Mask-RCNN achieved 1.3%, 1.1%, 1.3%, and 0.8% accuracy improvement than a multi-resolution baseline with solely resolution adjustment. The code is available at https://github.com/DaEunFullGrace/DyRA.git.