Fish Feeding Intensity Assessment (FFIA) is crucial in industrial aquaculture management. Recent multi-modal approaches have shown promise in improving FFIA robustness and efficiency. However, these methods face significant challenges when adapting to new fish species or environments due to catastrophic forgetting and the lack of suitable datasets. To address these limitations, we first introduce AV-CIL-FFIA, a new dataset comprising 81,932 labelled audio-visual clips capturing feeding intensities across six different fish species in real aquaculture environments. Then, we pioneer audio-visual class incremental learning (CIL) for FFIA and demonstrate through benchmarking on AV-CIL-FFIA that it significantly outperforms single-modality methods. Existing CIL methods rely heavily on historical data. Exemplar-based approaches store raw samples, creating storage challenges, while exemplar-free methods avoid data storage but struggle to distinguish subtle feeding intensity variations across different fish species. To overcome these limitations, we introduce HAIL-FFIA, a novel audio-visual class-incremental learning framework that bridges this gap with a prototype-based approach that achieves exemplar-free efficiency while preserving essential knowledge through compact feature representations. Specifically, HAIL-FFIA employs hierarchical representation learning with a dual-path knowledge preservation mechanism that separates general intensity knowledge from fish-specific characteristics. Additionally, it features a dynamic modality balancing system that adaptively adjusts the importance of audio versus visual information based on feeding behaviour stages. Experimental results show that HAIL-FFIA is superior to SOTA methods on AV-CIL-FFIA, achieving higher accuracy with lower storage needs while effectively mitigating catastrophic forgetting in incremental fish species learning.

By dragging a bunch of dead fish around, scientists may have uncovered a hidden power of one of biology's most important substances--mucus. And what they found might even help us understand the very dawn of vertebrate life on land. First, it's important to know that fish are covered in a thin layer of mucus. This slimy coating (it is also called a "slime coat") is known to keep fish healthy by warding off pathogens. Scientists have also found some evidence that mucus can reduce drag, helping fish swim through the water more easily.

In particular, overfishing is one the main issues in sustainable marine development. In alignment with the protection of marine resources and sustainable fishing, this study proposes to advance fish classification techniques that support identifying protected fish species using stateof-the-art machine learning. We use a custom modification of the MobileNet model to design a lightweight classifier called M-MobileNet that is capable of running on limited hardware. As part of the study, we compiled a labeled dataset of 37,462 images of fish found in the waters of the Indonesian archipelago. The proposed model is trained on the dataset to classify images of the captured fish into their species and give recommendations on whether they are consumable or not. Our modified MobileNet model uses only 50% of the top layer parameters with about 42% GTX 860M utility and achieves up to 97% accuracy in fish classification and determining its consumability. Given the limited computing capacity available on many fishing vessels, the proposed model provides a practical solution to on-site fish classification. In addition, synchronized implementation of the proposed model on multiple vessels can supply valuable information about the movement and location of different species of fish. Fish and seafood are among the most highly marketed foods in the world. According to WWF's report [29, 52], over 740 million people (10%) are reliant on catching, measuring, producing, and selling fish and seafood, and the statistics are continuously growing. People in developing maritime countries are largely dependent on fish as their primary livelihood, distributing the largest volume of fish catch and production worldwide and contributing 97% of the world's fishing workforce [27]. This also applies to the overwhelming majority of small-scale fishermen for whom fishing makes up the basis of their earnings as well as an essential part of their daily nourishment.

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.

In both terrestrial and marine ecology, physical tagging is a frequently used method to study population dynamics and behavior. However, such tagging techniques are increasingly being replaced by individual re-identification using image analysis. This paper introduces a contrastive learning-based model for identifying individuals. The model uses the first parts of the Inception v3 network, supported by a projection head, and we use contrastive learning to find similar or dissimilar image pairs from a collection of uniform photographs. We apply this technique for corkwing wrasse, Symphodus melops, an ecologically and commercially important fish species. Photos are taken during repeated catches of the same individuals from a wild population, where the intervals between individual sightings might range from a few days to several years. Our model achieves a one-shot accuracy of 0.35, a 5-shot accuracy of 0.56, and a 100-shot accuracy of 0.88, on our dataset.

"We recorded a beauty score for each species and correlated it with each fish's ecological characteristics – its size, whether it's carnivorous or herbivorous, nocturnal or diurnal, in the middle or at the bottom of the water column, etc.," Mouquet explains. The researchers then noted that the fish that are considered beautiful – those with sharp contrasts of luminosity (black/white) and colour (e.g. In addition, they represent only a small branch of the tree of life. The fish considered "less attractive" are by far the majority, with longer bodies, duller colours and less easily discernable patterns (for example, the bluish-grey fish found in the water column). The oldest of these species have been in existence for 100 million years and span a wider variety of ecological traits.

A new study from the University of Montpellier, France has found that the reef fish humans find 'ugly' are more likely to be endangered than more colourful and aesthetically pleasing species.

Artificial intelligence (AI) is helping prevent overfishing in a bid to protect the world's rapidly dwindling supply of edible marine species. A new project uses AI to improve the identification and measurement of fish species in Africa's Nile Basin. The software can help scientists understand fish population density more quickly than human observers. It's part of a larger effort to harness AI to improve sustainability across a wide range of industries. "The promising thing about AI is that it now allows us to do tasks that would be time-consuming or impossibly complex using traditional methods, with considerably more speed and efficiency," Andrew Dunckelman, head of impact and insights at Google.org, the search giant's charitable arm, told Lifewire in an email interview.

"thwop," "muah" and "boop" are some of the sounds made by Humpback Whales. This story was originally published by the Guardian and is reproduced here as part of the Climate Desk collaboration. From the "boing" of a minke whale to the "drum" of a red piranha, scientists are documenting more sounds in our world's oceans, rivers and lakes every year. Now, a team of experts wants to go a step further and create a reference library of aquatic noise to monitor the health of marine ecosystems. The Global Library of Underwater Biological Sounds (GLUBS) will include every "thwop," "muah" and "boop" of a humpback whale, as well as human-made underwater sounds and records of the geophysical swirl of ice and wind, according to a paper in the journal Frontiers in Ecology and Evolution.

The Ocean Aware project, led by Innovasea and funded through Canada’s Ocean Supercluster, is developing a fish passage observation platform to monitor fish without the use of traditional tags.This will provide an alternative to standard tracking technology, such as acoustic telemetry fish tracking, which are often not appropriate for tracking at-risk fish species protected by legislation.Rather, the observation platform uses a combination of sensors including acoustic devices, visual and active sonar, and optical cameras.This will enable more in-depth scientific research and better support regulatory monitoring of at-risk fish species in fish passages or marine energy sites.Analysis of this data will require a robust and accurate method to automatically detect fish, count fish, and classify them by species in real-time using both sonar and optical cameras.To meet this need, we developed and tested an automated real-time deep learning framework combining state of the art convolutional neural networks and Kalman filters.First, we showed that an adaptation of the widely used YOLO machine learning model can accurately detect and classify eight species of fish from a public high resolution DIDSON imaging sonar dataset captured from the Ocqueoc River in Michigan, USA.Although there has been extensive research in the literature identifying particular fish such as eel vs non-eel and seal vs fish, to our knowledge this is the first successful application of deep learning for classi...