Large language models (LLMs) have demonstrated a powerful ability to answer various queries as a general-purpose assistant. The continuous multi-modal large language models (MLLM) empower LLMs with the ability to perceive visual signals. The launch of GPT-4 (Generative Pre-trained Transformers) has generated significant interest in the research communities. GPT-4V(ison) has demonstrated significant power in both academia and industry fields, as a focal point in a new artificial intelligence generation. Though significant success was achieved by GPT-4V, exploring MLLMs in domain-specific analysis (e.g., marine analysis) that required domain-specific knowledge and expertise has gained less attention. In this study, we carry out the preliminary and comprehensive case study of utilizing GPT-4V for marine analysis. This report conducts a systematic evaluation of existing GPT-4V, assessing the performance of GPT-4V on marine research and also setting a new standard for future developments in MLLMs. The experimental results of GPT-4V show that the responses generated by GPT-4V are still far away from satisfying the domain-specific requirements of the marine professions. All images and prompts used in this study will be available at https://github.com/hkust-vgd/Marine_GPT-4V_Eval
Large language models (LLMs), such as ChatGPT/GPT-4, have proven to be powerful tools in promoting the user experience as an AI assistant. The continuous works are proposing multi-modal large language models (MLLM), empowering LLMs with the ability to sense multiple modality inputs through constructing a joint semantic space (e.g. visual-text space). Though significant success was achieved in LLMs and MLLMs, exploring LLMs and MLLMs in domain-specific applications that required domain-specific knowledge and expertise has been less conducted, especially for \textbf{marine domain}. Different from general-purpose MLLMs, the marine-specific MLLM is required to yield much more \textbf{sensitive}, \textbf{informative}, and \textbf{scientific} responses. In this work, we demonstrate that the existing MLLMs optimized on huge amounts of readily available general-purpose training data show a minimal ability to understand domain-specific intents and then generate informative and satisfactory responses. To address these issues, we propose \textbf{MarineGPT}, the first vision-language model specially designed for the marine domain, unlocking the secrets of the ocean to the public. We present our \textbf{Marine-5M} dataset with more than 5 million marine image-text pairs to inject domain-specific marine knowledge into our model and achieve better marine vision and language alignment. Our MarineGPT not only pushes the boundaries of marine understanding to the general public but also offers a standard protocol for adapting a general-purpose assistant to downstream domain-specific experts. We pave the way for a wide range of marine applications while setting valuable data and pre-trained models for future research in both academic and industrial communities.
The huge domain gap between sketches and photos and the highly abstract sketch representations pose challenges for sketch-based image retrieval (\underline{SBIR}). The zero-shot sketch-based image retrieval (\underline{ZS-SBIR}) is more generic and practical but poses an even greater challenge because of the additional knowledge gap between the seen and unseen categories. To simultaneously mitigate both gaps, we propose an \textbf{A}pproaching-and-\textbf{C}entralizing \textbf{Net}work (termed ``\textbf{ACNet}'') to jointly optimize sketch-to-photo synthesis and the image retrieval. The retrieval module guides the synthesis module to generate large amounts of diverse photo-like images which gradually approach the photo domain, and thus better serve the retrieval module than ever to learn domain-agnostic representations and category-agnostic common knowledge for generalizing to unseen categories. These diverse images generated with retrieval guidance can effectively alleviate the overfitting problem troubling concrete category-specific training samples with high gradients. We also discover the use of proxy-based NormSoftmax loss is effective in the zero-shot setting because its centralizing effect can stabilize our joint training and promote the generalization ability to unseen categories. Our approach is simple yet effective, which achieves state-of-the-art performance on two widely used ZS-SBIR datasets and surpasses previous methods by a large margin.
We aim to improve the performance of Multiple Object Tracking and Segmentation (MOTS) by refinement. However, it remains challenging for refining MOTS results, which could be attributed to that appearance features are not adapted to target videos and it is also difficult to find proper thresholds to discriminate them. To tackle this issue, we propose a self-supervised refining MOTS (i.e., ReMOTS) framework. ReMOTS mainly takes four steps to refine MOTS results from the data association perspective. (1) Training the appearance encoder using predicted masks. (2) Associating observations across adjacent frames to form short-term tracklets. (3) Training the appearance encoder using short-term tracklets as reliable pseudo labels. (4) Merging short-term tracklets to long-term tracklets utilizing adopted appearance features and thresholds that are automatically obtained from statistical information. Using ReMOTS, we reached the $1^{st}$ place on CVPR 2020 MOTS Challenge 1, with an sMOTSA score of $69.9$.
The aim of this work is learning to reshape the object in an input image to an arbitrary new shape, by just simply providing a single reference image with an object instance in the desired shape. We propose a new Generative Adversarial Network (GAN) architecture for such an object reshaping problem, named ReshapeGAN. The network can be tailored for handling all kinds of problem settings, including both within-domain (or single-dataset) reshaping and cross-domain (typically across mutiple datasets) reshaping, with paired or unpaired training data. The appearance of the input object is preserved in all cases, and thus it is still identifiable after reshaping, which has never been achieved as far as we are aware. We present the tailored models of the proposed ReshapeGAN for all the problem settings, and have them tested on 8 kinds of reshaping tasks with 13 different datasets, demonstrating the ability of ReshapeGAN on generating convincing and superior results for object reshaping. To the best of our knowledge, we are the first to be able to make one GAN framework work on all such object reshaping tasks, especially the cross-domain tasks on handling multiple diverse datasets. We present here both ablation studies on our proposed ReshapeGAN models and comparisons with the state-of-the-art models when they are made comparable, using all kinds of applicable metrics that we are aware of.
It is well known that humans can learn and recognize objects effectively from several limited image samples. However, learning from just a few images is still a tremendous challenge for existing main-stream deep neural networks. Inspired by analogical reasoning in the human mind, a feasible strategy is to translate the abundant images of a rich source domain to enrich the relevant yet different target domain with insufficient image data. To achieve this goal, we propose a novel, effective multi-adversarial framework (MA) based on part-global learning, which accomplishes one-shot cross-domain image-to-image translation. In specific, we first devise a part-global adversarial training scheme to provide an efficient way for feature extraction and prevent discriminators being over-fitted. Then, a multi-adversarial mechanism is employed to enhance the image-to-image translation ability to unearth the high-level semantic representation. Moreover, a balanced adversarial loss function is presented, which aims to balance the training data and stabilize the training process. Extensive experiments demonstrate that the proposed approach can obtain impressive results on various datasets between two extremely imbalanced image domains and outperform state-of-the-art methods on one-shot image-to-image translation.
Current approaches have made great progress on image-to-image translation tasks benefiting from the success of image synthesis methods especially generative adversarial networks (GANs). However, existing methods are limited to handling translation tasks between two species while keeping the content matching on the semantic level. A more challenging task would be the translation among more than two species. To explore this new area, we propose a simple yet effective structure of a multi-branch discriminator for enhancing an arbitrary generative adversarial architecture (GAN), named GAN-MBD. It takes advantage of the boosting strategy to break a common discriminator into several smaller ones with fewer parameters, which can enhance the generation and synthesis abilities of GANs efficiently and effectively. Comprehensive experiments show that the proposed multi-branch discriminator can dramatically improve the performance of popular GANs on cross-species image-to-image translation tasks while reducing the number of parameters for computation. The code and some datasets are attached as supplementary materials for reference.
Image-to-image translation has been made much progress with embracing Generative Adversarial Networks (GANs). However, it's still very challenging for translation tasks that require high quality, especially at high-resolution and photorealism. In this paper, we present Discriminative Region Proposal Adversarial Networks (DRPAN) for high-quality image-to-image translation. We decompose the procedure of image-to-image translation task into three iterated steps, first is to generate an image with global structure but some local artifacts (via GAN), second is using our DRPnet to propose the most fake region from the generated image, and third is to implement "image inpainting" on the most fake region for more realistic result through a reviser, so that the system (DRPAN) can be gradually optimized to synthesize images with more attention on the most artifact local part. Experiments on a variety of image-to-image translation tasks and datasets validate that our method outperforms state-of-the-arts for producing high-quality translation results in terms of both human perceptual studies and automatic quantitative measures.
Recently, image-to-image translation has been made much progress owing to the success of conditional Generative Adversarial Networks (cGANs). And some unpaired methods based on cycle consistency loss such as DualGAN, CycleGAN and DiscoGAN are really popular. However, it's still very challenging for translation tasks with the requirement of high-level visual information conversion, such as photo-to-caricature translation that requires satire, exaggeration, lifelikeness and artistry. We present an approach for learning to translate faces in the wild from the source photo domain to the target caricature domain with different styles, which can also be used for other high-level image-to-image translation tasks. In order to capture global structure with local statistics while translation, we design a dual pathway model with one coarse discriminator and one fine discriminator. For generator, we provide one extra perceptual loss in association with adversarial loss and cycle consistency loss to achieve representation learning for two different domains. Also the style can be learned by the auxiliary noise input. Experiments on photo-to-caricature translation of faces in the wild show considerable performance gain of our proposed method over state-of-the-art translation methods as well as its potential real applications.
Semantic layouts based Image synthesizing, which has benefited from the success of Generative Adversarial Network (GAN), has drawn much attention in these days. How to enhance the synthesis image equality while keeping the stochasticity of the GAN is still a challenge. We propose a novel denoising framework to handle this problem. The overlapped objects generation is another challenging task when synthesizing images from a semantic layout to a realistic RGB photo. To overcome this deficiency, we include a one-hot semantic label map to force the generator paying more attention on the overlapped objects generation. Furthermore, we improve the loss function of the discriminator by considering perturb loss and cascade layer loss to guide the generation process. We applied our methods on the Cityscapes, Facades and NYU datasets and demonstrate the image generation ability of our model.