Sara Beery

Justin Kay, Peter Kulits, Suzanne Stathatos et al. · mit

We present the Caltech Fish Counting Dataset (CFC), a large-scale dataset for detecting, tracking, and counting fish in sonar videos. We identify sonar videos as a rich source of data for advancing low signal-to-noise computer vision applications and tackling domain generalization in multiple-object tracking (MOT) and counting. In comparison to existing MOT and counting datasets, which are largely restricted to videos of people and vehicles in cities, CFC is sourced from a natural-world domain where targets are not easily resolvable and appearance features cannot be easily leveraged for target re-identification. With over half a million annotations in over 1,500 videos sourced from seven different sonar cameras, CFC allows researchers to train MOT and counting algorithms and evaluate generalization performance at unseen test locations. We perform extensive baseline experiments and identify key challenges and opportunities for advancing the state of the art in generalization in MOT and counting.

Rupa Kurinchi-Vendhan, Sara Beery

Active learning is now standard practice in labeling ecological data, enabling ecologists to quickly process large volumes of field data to understand and monitor natural environments. Current practices evaluate active learning inductively, estimating predictive performance on a held-out test set. We argue that this evaluation is misaligned with most ecological tasks, where the goal is to transductively label an entire pool of data as efficiently as possible. We demonstrate that ignoring the human-in-the-loop underestimates the importance of continuing to label, particularly for classes in the long tail which may be of disproportionate ecological importance (rare species, uncommon behaviors, etc.). Our analysis shows that, for this long tail, the transductive objective shifts importance from prediction to discovery: the true challenge becomes finding "needles in the haystack," examples of rare classes that are embedded within dense regions of abundant classes in the latent geometry, which we quantify with a novel metric of sampling difficulty. Finally, to translate these insights to practical ecological workflows, we propose a conservative hybrid stopping criterion inspired by ecological rarefaction curves, and show that combining predictive performance with discovery criteria reduces premature stopping on long-tailed pools, improving rare-class recovery when discovery, not classification, is the limiting factor.

Jun Chen, Ming Hu, Darren J. Coker et al. · mit

Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function. Automatic recognition of animals and their behaviors is critical for capitalizing on the large unlabeled datasets generated by modern video devices and for accelerating monitoring efforts at scale. However, the development of automated recognition systems is currently hindered by a lack of appropriately labeled datasets. Existing video datasets 1) do not classify animals according to established biological taxonomies; 2) are too small to facilitate large-scale behavioral studies and are often limited to a single species; and 3) do not feature temporally localized annotations and therefore do not facilitate localization of targeted behaviors within longer video sequences. Thus, we propose MammalNet, a new large-scale animal behavior dataset with taxonomy-guided annotations of mammals and their common behaviors. MammalNet contains over 18K videos totaling 539 hours, which is ~10 times larger than the largest existing animal behavior dataset. It covers 17 orders, 69 families, and 173 mammal categories for animal categorization and captures 12 high-level animal behaviors that received focus in previous animal behavior studies. We establish three benchmarks on MammalNet: standard animal and behavior recognition, compositional low-shot animal and behavior recognition, and behavior detection. Our dataset and code have been made available at: https://mammal-net.github.io.

Nihal V. Nayak, Paula Rodriguez-Diaz, Neha Hulkund et al. · harvard, microsoft-research

Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task. Despite growing interest, the literature on targeted instruction selection remains fragmented and opaque: methods vary widely in selection budgets, often omit zero-shot baselines, and frequently entangle the contributions of key components. As a result, practitioners lack actionable guidance on selecting instructions for their target tasks. In this work, we aim to bring clarity to this landscape by disentangling and systematically analyzing the two core ingredients: data representation and selection algorithms. Our framework enables controlled comparisons across models, tasks, and budgets. We find that only gradient-based data representations choose subsets whose similarity to the query consistently predicts performance across datasets and models. While no single method dominates, gradient-based representations paired with a greedy round-robin selection algorithm tend to perform best on average at low budgets, but these benefits diminish at larger budgets. Finally, we unify several existing selection algorithms as forms of approximate distance minimization between the selected subset and the query set, and support this view with new generalization bounds. More broadly, our findings provide critical insights and a foundation for more principled data selection in LLM fine-tuning. The code is available at https://github.com/dcml-lab/targeted-instruction-selection.

Lily Xu, Esther Rolf, Sara Beery et al. · mit

In this white paper, we synthesize key points made during presentations and discussions from the AI-Assisted Decision Making for Conservation workshop, hosted by the Center for Research on Computation and Society at Harvard University on October 20-21, 2022. We identify key open research questions in resource allocation, planning, and interventions for biodiversity conservation, highlighting conservation challenges that not only require AI solutions, but also require novel methodological advances. In addition to providing a summary of the workshop talks and discussions, we hope this document serves as a call-to-action to orient the expansion of algorithmic decision-making approaches to prioritize real-world conservation challenges, through collaborative efforts of ecologists, conservation decision-makers, and AI researchers.

Denis Kuznedelev, Soroush Tabesh, Kimia Noorbakhsh et al. · mit

Recent vision architectures and self-supervised training methods enable vision models that are extremely accurate and general, but come with massive parameter and computational costs. In practical settings, such as camera traps, users have limited resources, and may fine-tune a pretrained model on (often limited) data from a small set of specific categories of interest. These users may wish to make use of modern, highly-accurate models, but are often computationally constrained. To address this, we ask: can we quickly compress large generalist models into accurate and efficient specialists? For this, we propose a simple and versatile technique called Few-Shot Task-Aware Compression (TACO). Given a large vision model that is pretrained to be accurate on a broad task, such as classification over ImageNet-22K, TACO produces a smaller model that is accurate on specialized tasks, such as classification across vehicle types or animal species. Crucially, TACO works in few-shot fashion, i.e. only a few task-specific samples are used, and the procedure has low computational overheads. We validate TACO on highly-accurate ResNet, ViT/DeiT, and ConvNeXt models, originally trained on ImageNet, LAION, or iNaturalist, which we specialize and compress to a diverse set of "downstream" subtasks. TACO can reduce the number of non-zero parameters in existing models by up to 20x relative to the original models, leading to inference speedups of up to 3$\times$, while remaining accuracy-competitive with the uncompressed models on the specialized tasks.

Jae Joong Lee, Bosheng Li, Sara Beery et al. · mit

We introduce Tree D-fusion, featuring the first collection of 600,000 environmentally aware, 3D simulation-ready tree models generated through Diffusion priors. Each reconstructed 3D tree model corresponds to an image from Google's Auto Arborist Dataset, comprising street view images and associated genus labels of trees across North America. Our method distills the scores of two tree-adapted diffusion models by utilizing text prompts to specify a tree genus, thus facilitating shape reconstruction. This process involves reconstructing a 3D tree envelope filled with point markers, which are subsequently utilized to estimate the tree's branching structure using the space colonization algorithm conditioned on a specified genus.

Elijah Cole, Suzanne Stathatos, Björn Lütjens et al. · mit

Computer vision can accelerate ecology research by automating the analysis of raw imagery from sensors like camera traps, drones, and satellites. However, computer vision is an emerging discipline that is rarely taught to ecologists. This work discusses our experience teaching a diverse group of ecologists to prototype and evaluate computer vision systems in the context of an intensive hands-on summer workshop. We explain the workshop structure, discuss common challenges, and propose best practices. This document is intended for computer scientists who teach computer vision across disciplines, but it may also be useful to ecologists or other domain experts who are learning to use computer vision themselves.

Tom Raynes, Otto Brookes, Timm Haucke et al.

The estimation of abundance and density in unmarked populations of great apes relies on statistical frameworks that require animal-to-camera distance measurements. In practice, acquiring these distances depends on labour-intensive manual interpretation of animal observations across large camera trap video corpora. This study introduces and evaluates an only sparsely explored alternative: the integration of computer vision-based monocular depth estimation (MDE) pipelines directly into ecological camera trap workflows for great ape conservation. Using a real-world dataset of 220 camera trap videos documenting a wild chimpanzee population, we combine two MDE models, Dense Prediction Transformers and Depth Anything, with multiple distance sampling strategies. These components are used to generate detection distance estimates, from which population density and abundance are inferred. Comparative analysis against manually derived ground-truth distances shows that calibrated DPT consistently outperforms Depth Anything. This advantage is observed in both distance estimation accuracy and downstream density and abundance inference. Nevertheless, both models exhibit systematic biases. We show that, given complex forest environments, they tend to overestimate detection distances and consequently underestimate density and abundance relative to conventional manual approaches. We further find that failures in animal detection across distance ranges are a primary factor limiting estimation accuracy. Overall, this work provides a case study that shows MDE-driven camera trap distance sampling is a viable and practical alternative to manual distance estimation. The proposed approach yields population estimates within 22% of those obtained using traditional methods.

Mridul Khurana, Amin Karimi Monsefi, Justin Lee et al.

Accurately generating images across the Tree of Life is difficult: there are over 10M distinct species on Earth, many of which differ only by subtle visual traits. Despite the remarkable progress in text-to-image synthesis, existing models often fail to capture the fine-grained visual cues that define species identity, even when their outputs appear photo-realistic. To this end, we propose TaxaAdapter, a simple and lightweight approach that incorporates Vision Taxonomy Models (VTMs) such as BioCLIP to guide fine-grained species generation. Our method injects VTM embeddings into a frozen text-to-image diffusion model, improving species-level fidelity while preserving flexible text control over attributes such as pose, style, and background. Extensive experiments demonstrate that TaxaAdapter consistently improves morphology fidelity and species-identity accuracy over strong baselines, with a cleaner architecture and training recipe. To better evaluate these improvements, we also introduce a multimodal Large Language Model-based metric that summarizes trait-level descriptions from generated and real images, providing a more interpretable measure of morphological consistency. Beyond this, we observe that TaxaAdapter exhibits strong generalization capabilities, enabling species synthesis in challenging regimes such as few-shot species with only a handful of training images and even species unseen during training. Overall, our results highlight that VTMs are a key ingredient for scalable, fine-grained species generation.

Rupa Kurinchi-Vendhan, Pratyusha Sharma, Antonio Torralba et al. · deepmind

Scientific and environmental imagery often suffer from complex mixtures of noise related to the sensor and the environment. Existing restoration methods typically remove one degradation at a time, leading to cascading artifacts, overcorrection, or loss of meaningful signal. In scientific applications, restoration must be able to simultaneously handle compound degradations while allowing experts to selectively remove subsets of distortions without erasing important features. To address these challenges, we present PRISM (Precision Restoration with Interpretable Separation of Mixtures). PRISM is a prompted conditional diffusion framework which combines compound-aware supervision over mixed degradations with a weighted contrastive disentanglement objective that aligns primitives and their mixtures in the latent space. This compositional geometry enables high-fidelity joint removal of overlapping distortions while also allowing flexible, targeted fixes through natural language prompts. Across microscopy, wildlife monitoring, remote sensing, and urban weather datasets, PRISM outperforms state-of-the-art baselines on complex compound degradations, including zero-shot mixtures not seen during training. Importantly, we show that selective restoration significantly improves downstream scientific accuracy in several domains over standard "black-box" restoration. These results establish PRISM as a generalizable and controllable framework for high-fidelity restoration in domains where scientific utility is a priority.

Joshua Vendrow, Edward Vendrow, Sara Beery et al.

When deploying large language models (LLMs), it is important to ensure that these models are not only capable, but also reliable. Many benchmarks have been created to track LLMs' growing capabilities, however there has been no similar focus on measuring their reliability. To understand the potential ramifications of this gap, we investigate how well current benchmarks quantify model reliability. We find that pervasive label errors can compromise these evaluations, obscuring lingering model failures and hiding unreliable behavior. Motivated by this gap in the evaluation of reliability, we then propose the concept of so-called platinum benchmarks, i.e., benchmarks carefully curated to minimize label errors and ambiguity. As a first attempt at constructing such benchmarks, we revise examples from fifteen existing popular benchmarks. We evaluate a wide range of models on these platinum benchmarks and find that, indeed, frontier LLMs still exhibit failures on simple tasks such as elementary-level math word problems. Analyzing these failures further reveals previously unidentified patterns of problems on which frontier models consistently struggle. We provide code at https://github.com/MadryLab/platinum-benchmarks

Andres Hernandez, Zhongqi Miao, Luisa Vargas et al.

The alarming decline in global biodiversity, driven by various factors, underscores the urgent need for large-scale wildlife monitoring. In response, scientists have turned to automated deep learning methods for data processing in wildlife monitoring. However, applying these advanced methods in real-world scenarios is challenging due to their complexity and the need for specialized knowledge, primarily because of technical challenges and interdisciplinary barriers. To address these challenges, we introduce Pytorch-Wildlife, an open-source deep learning platform built on PyTorch. It is designed for creating, modifying, and sharing powerful AI models. This platform emphasizes usability and accessibility, making it accessible to individuals with limited or no technical background. It also offers a modular codebase to simplify feature expansion and further development. Pytorch-Wildlife offers an intuitive, user-friendly interface, accessible through local installation or Hugging Face, for animal detection and classification in images and videos. As two real-world applications, Pytorch-Wildlife has been utilized to train animal classification models for species recognition in the Amazon Rainforest and for invasive opossum recognition in the Galapagos Islands. The Opossum model achieves 98% accuracy, and the Amazon model has 92% recognition accuracy for 36 animals in 90% of the data. As Pytorch-Wildlife evolves, we aim to integrate more conservation tasks, addressing various environmental challenges. Pytorch-Wildlife is available at https://github.com/microsoft/CameraTraps.

Justin Kay, Timm Haucke, Suzanne Stathatos et al. · mit

Object detectors often perform poorly on data that differs from their training set. Domain adaptive object detection (DAOD) methods have recently demonstrated strong results on addressing this challenge. Unfortunately, we identify systemic benchmarking pitfalls that call past results into question and hamper further progress: (a) Overestimation of performance due to underpowered baselines, (b) Inconsistent implementation practices preventing transparent comparisons of methods, and (c) Lack of generality due to outdated backbones and lack of diversity in benchmarks. We address these problems by introducing: (1) A unified benchmarking and implementation framework, Align and Distill (ALDI), enabling comparison of DAOD methods and supporting future development, (2) A fair and modern training and evaluation protocol for DAOD that addresses benchmarking pitfalls, (3) A new DAOD benchmark dataset, CFC-DAOD, enabling evaluation on diverse real-world data, and (4) A new method, ALDI++, that achieves state-of-the-art results by a large margin. ALDI++ outperforms the previous state-of-the-art by +3.5 AP50 on Cityscapes to Foggy Cityscapes, +5.7 AP50 on Sim10k to Cityscapes (where ours is the only method to outperform a fair baseline), and +0.6 AP50 on CFC Kenai to Channel. ALDI and ALDI++ are architecture-agnostic, setting a new state-of-the-art for YOLO and DETR-based DAOD as well without additional hyperparameter tuning. Our framework, dataset, and state-of-the-art method offer a critical reset for DAOD and provide a strong foundation for future research. Code and data are available: https://github.com/justinkay/aldi and https://github.com/visipedia/caltech-fish-counting.

Julia Chae, Nicholas Kolkin, Jui-Hsien Wang et al.

Humans have remarkable selective sensitivity to identities -- easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to match this capability, and progress toward identity-focused tasks such as personalized image generation is slowed by a lack of identity-focused evaluation metrics. To help facilitate progress, we propose ID-Sim, a feed-forward metric designed to faithfully reflect human selective sensitivity. To build ID-Sim, we curate a high-quality training set of images spanning diverse real-world domains, augmented with generative synthetic data that provides controlled, fine-grained identity and contextual variations. We evaluate our metric on a new unified evaluation benchmark for assessing consistency with human annotations across identity-focused recognition, retrieval, and generative tasks.

Connor Kilrain, David Carlyn, Julia Chae et al.

The rise of personalized generative models raises a central question: how should we evaluate identity preservation? Given a reference image (e.g., one's pet), we expect the generated image to retain precise details attached to the subject's identity. However, current generative evaluation metrics emphasize the overall semantic similarity between the reference and the output, and overlook these fine-grained discriminative details. We introduce Finer-Personalization Rank, an evaluation protocol tailored to identity preservation. Instead of pairwise similarity, Finer-Personalization Rank adopts a ranking view: it treats each generated image as a query against an identity-labeled gallery consisting of visually similar real images. Retrieval metrics (e.g., mean average precision) measure performance, where higher scores indicate that identity-specific details (e.g., a distinctive head spot) are preserved. We assess identity at multiple granularities -- from fine-grained categories (e.g., bird species, car models) to individual instances (e.g., re-identification). Across CUB, Stanford Cars, and animal Re-ID benchmarks, Finer-Personalization Rank more faithfully reflects identity retention than semantic-only metrics and reveals substantial identity drift in several popular personalization methods. These results position the gallery-based protocol as a principled and practical evaluation for personalized generation.

Justin Kay, Grant Van Horn, Subhransu Maji et al. · mit

The widespread availability of off-the-shelf machine learning models poses a challenge: which model, of the many available candidates, should be chosen for a given data analysis task? This question of model selection is traditionally answered by collecting and annotating a validation dataset -- a costly and time-intensive process. We propose a method for active model selection, using predictions from candidate models to prioritize the labeling of test data points that efficiently differentiate the best candidate. Our method, CODA, performs consensus-driven active model selection by modeling relationships between classifiers, categories, and data points within a probabilistic framework. The framework uses the consensus and disagreement between models in the candidate pool to guide the label acquisition process, and Bayesian inference to update beliefs about which model is best as more information is collected. We validate our approach by curating a collection of 26 benchmark tasks capturing a range of model selection scenarios. CODA outperforms existing methods for active model selection significantly, reducing the annotation effort required to discover the best model by upwards of 70% compared to the previous state-of-the-art. Code and data are available at https://github.com/justinkay/coda.

Lauren Shrack, Timm Haucke, Antoine Salaün et al. · meta-ai

The differences between images belonging to fine-grained categories are often subtle and highly localized, and existing explainability techniques for deep learning models are often too diffuse to provide useful and interpretable explanations. We propose a new explainability method (PAIR-X) that leverages both intermediate model activations and backpropagated relevance scores to generate fine-grained, highly-localized pairwise visual explanations. We use animal and building re-identification (re-ID) as a primary case study of our method, and we demonstrate qualitatively improved results over a diverse set of explainability baselines on 35 public re-ID datasets. In interviews, animal re-ID experts found PAIR-X to be a meaningful improvement over existing baselines for deep model explainability, and suggested that its visualizations would be directly applicable to their work. We also propose a novel quantitative evaluation metric for our method, and demonstrate that PAIR-X visualizations appear more plausible for correct image matches than incorrect ones even when the model similarity score for the pairs is the same. By improving interpretability, PAIR-X enables humans to better distinguish correct and incorrect matches. Our code is available at: https://github.com/pairx-explains/pairx

Edward Vendrow, Julia Chae, Rupa Kurinchi-Vendhan et al.

Large community science platforms such as iNaturalist contain hundreds of millions of biodiversity images that often capture ecological context on behaviors, interactions, phenology, and habitat. Yet most ecological workflows rely on metadata filtering or manual inspection, leaving this secondary information inaccessible at scale. We introduce INQUIRE-Search, an open-source system that enables scientists to rapidly and interactively search within an ecological image database for specific concepts using natural language, verify and export relevant observations, and utilize this discovered data for novel scientific analysis. Compared to traditional methods, INQUIRE-Search takes a fraction of the time, opening up new possibilities for scientific questions that can be explored. Through five case studies, we show the diversity of scientific applications that a tool like INQUIRE-Search can support, from seasonal variation in behavior across species to forest regrowth after wildfires. These examples demonstrate a new paradigm for interactive, efficient, and scalable scientific discovery that can begin to unlock previously inaccessible scientific value in large-scale biodiversity datasets. Finally, we emphasize using such AI-enabled discovery tools for science call for experts to reframe the priorities of the scientific process and develop novel methods for experiment design, data collection, survey effort, and uncertainty analysis.

Shiori Sagawa, Pang Wei Koh, Tony Lee et al.

Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data and can often be obtained from distributions beyond the source distribution as well. However, existing distribution shift benchmarks with unlabeled data do not reflect the breadth of scenarios that arise in real-world applications. In this work, we present the WILDS 2.0 update, which extends 8 of the 10 datasets in the WILDS benchmark of distribution shifts to include curated unlabeled data that would be realistically obtainable in deployment. These datasets span a wide range of applications (from histology to wildlife conservation), tasks (classification, regression, and detection), and modalities (photos, satellite images, microscope slides, text, molecular graphs). The update maintains consistency with the original WILDS benchmark by using identical labeled training, validation, and test sets, as well as the evaluation metrics. On these datasets, we systematically benchmark state-of-the-art methods that leverage unlabeled data, including domain-invariant, self-training, and self-supervised methods, and show that their success on WILDS is limited. To facilitate method development and evaluation, we provide an open-source package that automates data loading and contains all of the model architectures and methods used in this paper. Code and leaderboards are available at https://wilds.stanford.edu.

Pang Wei Koh, Shiori Sagawa, Henrik Marklund et al.

Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity in the real-world deployments, these distribution shifts are under-represented in the datasets widely used in the ML community today. To address this gap, we present WILDS, a curated benchmark of 10 datasets reflecting a diverse range of distribution shifts that naturally arise in real-world applications, such as shifts across hospitals for tumor identification; across camera traps for wildlife monitoring; and across time and location in satellite imaging and poverty mapping. On each dataset, we show that standard training yields substantially lower out-of-distribution than in-distribution performance. This gap remains even with models trained by existing methods for tackling distribution shifts, underscoring the need for new methods for training models that are more robust to the types of distribution shifts that arise in practice. To facilitate method development, we provide an open-source package that automates dataset loading, contains default model architectures and hyperparameters, and standardizes evaluations. Code and leaderboards are available at https://wilds.stanford.edu.

David Rolnick, Alan Aspuru-Guzik, Sara Beery et al. · mit

As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly important. Such work offers the potential for significant impact not merely in domains of application but also in machine learning itself. In this paper, we describe the paradigm of application-driven research in machine learning, contrasting it with the more standard paradigm of methods-driven research. We illustrate the benefits of application-driven machine learning and how this approach can productively synergize with methods-driven work. Despite these benefits, we find that reviewing, hiring, and teaching practices in machine learning often hold back application-driven innovation. We outline how these processes may be improved.

Edward Vendrow, Omiros Pantazis, Alexander Shepard et al. · mit

We introduce INQUIRE, a text-to-image retrieval benchmark designed to challenge multimodal vision-language models on expert-level queries. INQUIRE includes iNaturalist 2024 (iNat24), a new dataset of five million natural world images, along with 250 expert-level retrieval queries. These queries are paired with all relevant images comprehensively labeled within iNat24, comprising 33,000 total matches. Queries span categories such as species identification, context, behavior, and appearance, emphasizing tasks that require nuanced image understanding and domain expertise. Our benchmark evaluates two core retrieval tasks: (1) INQUIRE-Fullrank, a full dataset ranking task, and (2) INQUIRE-Rerank, a reranking task for refining top-100 retrievals. Detailed evaluation of a range of recent multimodal models demonstrates that INQUIRE poses a significant challenge, with the best models failing to achieve an mAP@50 above 50%. In addition, we show that reranking with more powerful multimodal models can enhance retrieval performance, yet there remains a significant margin for improvement. By focusing on scientifically-motivated ecological challenges, INQUIRE aims to bridge the gap between AI capabilities and the needs of real-world scientific inquiry, encouraging the development of retrieval systems that can assist with accelerating ecological and biodiversity research. Our dataset and code are available at https://inquire-benchmark.github.io

Vaibhav Balloli, Sara Beery, Elizabeth Bondi-Kelly

Image retrieval plays a pivotal role in applications from wildlife conservation to healthcare, for finding individual animals or relevant images to aid diagnosis. Although deep learning techniques for image retrieval have advanced significantly, their imperfect real-world performance often necessitates including human expertise. Human-in-the-loop approaches typically rely on humans completing the task independently and then combining their opinions with an AI model in various ways, as these models offer very little interpretability or \textit{correctability}. To allow humans to intervene in the AI model instead, thereby saving human time and effort, we adapt the Concept Bottleneck Model (CBM) and propose \texttt{CHAIR}. \texttt{CHAIR} (a) enables humans to correct intermediate concepts, which helps \textit{improve} embeddings generated, and (b) allows for flexible levels of intervention that accommodate varying levels of human expertise for better retrieval. To show the efficacy of \texttt{CHAIR}, we demonstrate that our method performs better than similar models on image retrieval metrics without any external intervention. Furthermore, we also showcase how human intervention helps further improve retrieval performance, thereby achieving human-AI complementarity.

Lukas Picek, Timm Haucke, Lukáš Adam et al.

Recognizing individual animals over time is central to many ecological and conservation questions, including estimating abundance, survival, movement, and social structure. Recent advances in automated identification from images and even acoustic data suggest that this process could be greatly accelerated, yet their promise has not translated well into ecological practice. We argue that the main barrier is not the performance of the automated methods themselves, but a mismatch between how those methods are typically developed and evaluated, and how ecological data is actually collected, processed, reviewed, and used. Future progress, therefore, will depend less on algorithmic gains alone than on recognizing that the usefulness of automated identification is grounded in ecological context: it depends on what question is being asked, what data are available, and what kinds of mistakes matter. Only by centering these questions can we move toward automated identification of individuals that is not only accurate but also ecologically useful, transparent, and trustworthy.

Shobhita Sundaram, Julia Chae, Yonglong Tian et al.

Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data to general-purpose representation learning, while advances in T2I diffusion models have enabled the generation of personalized images from just a few real examples. Here, we explore a potential connection between these ideas, and formalize the challenge of using personalized synthetic data to learn personalized representations, which encode knowledge about an object of interest and may be flexibly applied to any downstream task relating to the target object. We introduce an evaluation suite for this challenge, including reformulations of two existing datasets and a novel dataset explicitly constructed for this purpose, and propose a contrastive learning approach that makes creative use of image generators. We show that our method improves personalized representation learning for diverse downstream tasks, from recognition to segmentation, and analyze characteristics of image generation approaches that are key to this gain.

Avirath Sundaresan, Jason R. Parham, Jonathan Crall et al.

In both 2016 and 2018, a census of the highly-endangered Grevy's zebra population was enabled by the Great Grevy's Rally (GGR), a citizen science event that produces population estimates via expert and algorithmic curation of volunteer-captured images. A complementary, scalable, and long-term Grevy's population monitoring approach involves deploying camera trap networks. However, in both scenarios, a substantial majority of zebra images are not usable for individual identification due to poor in-the-wild imaging conditions; camera trap images in particular present high rates of occlusion and high spatio-temporal similarity within image bursts. Our proposed filtering pipeline incorporates animal detection, species identification, viewpoint estimation, quality evaluation, and temporal subsampling to obtain individual crops suitable for re-ID, which are subsequently curated by the LCA decision management algorithm. Our method processed images taken during GGR-16 and GGR-18 in Meru County, Kenya, into 4,142 highly-comparable annotations, requiring only 120 contrastive human decisions to produce a population estimate within 4.6% of the ground-truth count. Our method also efficiently processed 8.9M unlabeled camera trap images from 70 cameras at the Mpala Research Centre in Laikipia County, Kenya over two years into 685 encounters of 173 individuals, requiring only 331 contrastive human decisions.

Neha Hulkund, Alaa Maalouf, Levi Cai et al.

In many real-world machine learning (ML) applications (e.g. detecting broken bones in x-ray images, detecting species in camera traps), in practice models need to perform well on specific deployments (e.g. a specific hospital, a specific national park) rather than the domain broadly. However, deployments often have imbalanced, unique data distributions. Discrepancy between the training distribution and the deployment distribution can lead to suboptimal performance, highlighting the need to select deployment-specialized subsets from the available training data. We formalize dataset subset selection for specialization (DS3): given a training set drawn from a general distribution and a (potentially unlabeled) query set drawn from the desired deployment-specific distribution, the goal is to select a subset of the training data that optimizes deployment performance. We introduce DataS^3; the first dataset and benchmark designed specifically for the DS3 problem. DataS^3 encompasses diverse real-world application domains, each with a set of distinct deployments to specialize in. We conduct a comprehensive study evaluating algorithms from various families--including coresets, data filtering, and data curation--on DataS^3, and find that general-distribution methods consistently fail on deployment-specific tasks. Additionally, we demonstrate the existence of manually curated (deployment-specific) expert subsets that outperform training on all available data with accuracy gains up to 51.3 percent. Our benchmark highlights the critical role of tailored dataset curation in enhancing performance and training efficiency on deployment-specific distributions, which we posit will only become more important as global, public datasets become available across domains and ML models are deployed in the real world.

Yuyan Chen, Nico Lang, B. Christian Schmidt et al. · mit

Global biodiversity is declining at an unprecedented rate, yet little information is known about most species and how their populations are changing. Indeed, some 90% of Earth's species are estimated to be completely unknown. Machine learning has recently emerged as a promising tool to facilitate long-term, large-scale biodiversity monitoring, including algorithms for fine-grained classification of species from images. However, such algorithms typically are not designed to detect examples from categories unseen during training -- the problem of open-set recognition (OSR) -- limiting their applicability for highly diverse, poorly studied taxa such as insects. To address this gap, we introduce Open-Insect, a large-scale, fine-grained dataset to evaluate unknown species detection across different geographic regions with varying difficulty. We benchmark 38 OSR algorithms across three categories: post-hoc, training-time regularization, and training with auxiliary data, finding that simple post-hoc approaches remain a strong baseline. We also demonstrate how to leverage auxiliary data to improve species discovery in regions with limited data. Our results provide insights to guide the development of computer vision methods for biodiversity monitoring and species discovery.

Olawale Salaudeen, Haoran Zhang, Kumail Alhamoud et al.

Benchmarks for out-of-distribution (OOD) generalization frequently show a strong positive correlation between in-distribution (ID) and OOD accuracy across models, termed "accuracy-on-the-line." This pattern is often taken to imply that spurious correlations - correlations that improve ID but reduce OOD performance - are rare in practice. We find that this positive correlation is often an artifact of aggregating heterogeneous OOD examples. Using a simple gradient-based method, OODSelect, we identify semantically coherent OOD subsets where accuracy on the line does not hold. Across widely used distribution shift benchmarks, the OODSelect uncovers subsets, sometimes over half of the standard OOD set, where higher ID accuracy predicts lower OOD accuracy. Our findings indicate that aggregate metrics can obscure important failure modes of OOD robustness. We release code and the identified subsets to facilitate further research.

Yahia Battach, Abdulwahab Felemban, Faizan Farooq Khan et al.

Coral reefs are rapidly declining due to anthropogenic pressures such as climate change, underscoring the urgent need for scalable, automated monitoring. We introduce ReefNet, a large public coral reef image dataset with point-label annotations mapped to the World Register of Marine Species (WoRMS). ReefNet aggregates imagery from 76 curated CoralNet sources and an additional site from Al Wajh in the Red Sea, totaling approximately 925000 genus-level hard coral annotations with expert-verified labels. Unlike prior datasets, which are often limited by size, geography, or coarse labels and are not ML-ready, ReefNet offers fine-grained, taxonomically mapped labels at a global scale to WoRMS. We propose two evaluation settings: (i) a within-source benchmark that partitions each source's images for localized evaluation, and (ii) a cross-source benchmark that withholds entire sources to test domain generalization. We analyze both supervised and zero-shot classification performance on ReefNet and find that while supervised within-source performance is promising, supervised performance drops sharply across domains, and performance is low across the board for zero-shot models, especially for rare and visually similar genera. This provides a challenging benchmark intended to catalyze advances in domain generalization and fine-grained coral classification. We will release our dataset, benchmarking code, and pretrained models to advance robust, domain-adaptive, global coral reef monitoring and conservation.

Kai Van Brunt, Justin Kay, Timm Haucke et al. · mit

Accurate estimates of salmon escapement - the number of fish migrating upstream to spawn - are key data for conservation and fishery management. Existing methods for salmon counting using high-resolution imaging sonar hardware are non-invasive and compatible with computer vision processing. Prior work in this area has utilized object detection and tracking based methods for automated salmon counting. However, these techniques remain inaccessible to many sonar deployment sites due to limited compute and connectivity in the field. We propose an alternative lightweight computer vision method for fish counting based on analyzing echograms - temporal representations that compress several hundred frames of imaging sonar video into a single image. We predict upstream and downstream counts within 200-frame time windows directly from echograms using a ResNet-18 model, and propose a set of domain-specific image augmentations and a weakly-supervised training protocol to further improve results. We achieve a count error of 23% on representative data from the Kenai River in Alaska, demonstrating the feasibility of our approach.

Seulki Park, Youren Zhang, Stella X. Yu et al.

Hierarchical classification predicts labels across multiple levels of a taxonomy, e.g., from coarse-level 'Bird' to mid-level 'Hummingbird' to fine-level 'Green hermit', allowing flexible recognition under varying visual conditions. It is commonly framed as multiple single-level tasks, but each level may rely on different visual cues: Distinguishing 'Bird' from 'Plant' relies on global features like feathers or leaves, while separating 'Anna's hummingbird' from 'Green hermit' requires local details such as head coloration. Prior methods improve accuracy using external semantic supervision, but such statistical learning criteria fail to ensure consistent visual grounding at test time, resulting in incorrect hierarchical classification. We propose, for the first time, to enforce internal visual consistency by aligning fine-to-coarse predictions through intra-image segmentation. Our method outperforms zero-shot CLIP and state-of-the-art baselines on hierarchical classification benchmarks, achieving both higher accuracy and more consistent predictions. It also improves internal image segmentation without requiring pixel-level annotations.

Devis Tuia, Benjamin Kellenberger, Sara Beery et al.

Data acquisition in animal ecology is rapidly accelerating due to inexpensive and accessible sensors such as smartphones, drones, satellites, audio recorders and bio-logging devices. These new technologies and the data they generate hold great potential for large-scale environmental monitoring and understanding, but are limited by current data processing approaches which are inefficient in how they ingest, digest, and distill data into relevant information. We argue that machine learning, and especially deep learning approaches, can meet this analytic challenge to enhance our understanding, monitoring capacity, and conservation of wildlife species. Incorporating machine learning into ecological workflows could improve inputs for population and behavior models and eventually lead to integrated hybrid modeling tools, with ecological models acting as constraints for machine learning models and the latter providing data-supported insights. In essence, by combining new machine learning approaches with ecological domain knowledge, animal ecologists can capitalize on the abundance of data generated by modern sensor technologies in order to reliably estimate population abundances, study animal behavior and mitigate human/wildlife conflicts. To succeed, this approach will require close collaboration and cross-disciplinary education between the computer science and animal ecology communities in order to ensure the quality of machine learning approaches and train a new generation of data scientists in ecology and conservation.

Tuhin Das, Robert-Jan Bruintjes, Attila Lengyel et al.

To alleviate lower classification performance on rare classes in imbalanced datasets, a possible solution is to augment the underrepresented classes with synthetic samples. Domain adaptation can be incorporated in a classifier to decrease the domain discrepancy between real and synthetic samples. While domain adaptation is generally applied on completely synthetic source domains and real target domains, we explore how domain adaptation can be applied when only a single rare class is augmented with simulated samples. As a testbed, we use a camera trap animal dataset with a rare deer class, which is augmented with synthetic deer samples. We adapt existing domain adaptation methods to two new methods for the single rare class setting: DeerDANN, based on the Domain-Adversarial Neural Network (DANN), and DeerCORAL, based on deep correlation alignment (Deep CORAL) architectures. Experiments show that DeerDANN has the highest improvement in deer classification accuracy of 24.0% versus 22.4% improvement of DeerCORAL when compared to the baseline. Further, both methods require fewer than 10k synthetic samples, as used by the baseline, to achieve these higher accuracies. DeerCORAL requires the least number of synthetic samples (2k deer), followed by DeerDANN (8k deer).

Sara Beery, Elijah Cole, Joseph Parker et al.

Conservation science depends on an accurate understanding of what's happening in a given ecosystem. How many species live there? What is the makeup of the population? How is that changing over time? Species Distribution Modeling (SDM) seeks to predict the spatial (and sometimes temporal) patterns of species occurrence, i.e. where a species is likely to be found. The last few years have seen a surge of interest in applying powerful machine learning tools to challenging problems in ecology. Despite its considerable importance, SDM has received relatively little attention from the computer science community. Our goal in this work is to provide computer scientists with the necessary background to read the SDM literature and develop ecologically useful ML-based SDM algorithms. In particular, we introduce key SDM concepts and terminology, review standard models, discuss data availability, and highlight technical challenges and pitfalls.

Peter Kulits, Jake Wall, Anka Bedetti et al.

African elephants are vital to their ecosystems, but their populations are threatened by a rise in human-elephant conflict and poaching. Monitoring population dynamics is essential in conservation efforts; however, tracking elephants is a difficult task, usually relying on the invasive and sometimes dangerous placement of GPS collars. Although there have been many recent successes in the use of computer vision techniques for automated identification of other species, identification of elephants is extremely difficult and typically requires expertise as well as familiarity with elephants in the population. We have built and deployed a web-based platform and database for human-in-the-loop re-identification of elephants combining manual attribute labeling and state-of-the-art computer vision algorithms, known as ElephantBook. Our system is currently in use at the Mara Elephant Project, helping monitor the protected and at-risk population of elephants in the Greater Maasai Mara ecosystem. ElephantBook makes elephant re-identification usable by non-experts and scalable for use by multiple conservation NGOs.

Edoardo Lanzini, Sara Beery

The natural world is long-tailed: rare classes are observed orders of magnitudes less frequently than common ones, leading to highly-imbalanced data where rare classes can have only handfuls of examples. Learning from few examples is a known challenge for deep learning based classification algorithms, and is the focus of the field of low-shot learning. One potential approach to increase the training data for these rare classes is to augment the limited real data with synthetic samples. This has been shown to help, but the domain shift between real and synthetic hinders the approaches' efficacy when tested on real data. We explore the use of image-to-image translation methods to close the domain gap between synthetic and real imagery for animal species classification in data collected from camera traps: motion-activated static cameras used to monitor wildlife. We use low-level feature alignment between source and target domains to make synthetic data for a rare species generated using a graphics engine more "realistic". Compared against a system augmented with unaligned synthetic data, our experiments show a considerable decrease in classification error rates on a rare species.

Sara Beery, Elizabeth Bondi

To protect the location of camera trap data containing sensitive, high-target species, many ecologists randomly obfuscate the latitude and longitude of the camera when publishing their data. For example, they may publish a random location within a 1km radius of the true camera location for each camera in their network. In this paper, we investigate the robustness of geo-obfuscation for maintaining camera trap location privacy, and show via a case study that a few simple, intuitive heuristics and publicly available satellite rasters can be used to reduce the area likely to contain the camera by 87% (assuming random obfuscation within 1km), demonstrating that geo-obfuscation may be less effective than previously believed.

Sara Beery, Arushi Agarwal, Elijah Cole et al.

Camera traps enable the automatic collection of large quantities of image data. Ecologists use camera traps to monitor animal populations all over the world. In order to estimate the abundance of a species from camera trap data, ecologists need to know not just which species were seen, but also how many individuals of each species were seen. Object detection techniques can be used to find the number of individuals in each image. However, since camera traps collect images in motion-triggered bursts, simply adding up the number of detections over all frames is likely to lead to an incorrect estimate. Overcoming these obstacles may require incorporating spatio-temporal reasoning or individual re-identification in addition to traditional species detection and classification. We have prepared a challenge where the training data and test data are from different cameras spread across the globe. The set of species seen in each camera overlap, but are not identical. The challenge is to classify species and count individual animals across sequences in the test cameras.

Grant Van Horn, Elijah Cole, Sara Beery et al.

Recent progress in self-supervised learning has resulted in models that are capable of extracting rich representations from image collections without requiring any explicit label supervision. However, to date the vast majority of these approaches have restricted themselves to training on standard benchmark datasets such as ImageNet. We argue that fine-grained visual categorization problems, such as plant and animal species classification, provide an informative testbed for self-supervised learning. In order to facilitate progress in this area we present two new natural world visual classification datasets, iNat2021 and NeWT. The former consists of 2.7M images from 10k different species uploaded by users of the citizen science application iNaturalist. We designed the latter, NeWT, in collaboration with domain experts with the aim of benchmarking the performance of representation learning algorithms on a suite of challenging natural world binary classification tasks that go beyond standard species classification. These two new datasets allow us to explore questions related to large-scale representation and transfer learning in the context of fine-grained categories. We provide a comprehensive analysis of feature extractors trained with and without supervision on ImageNet and iNat2021, shedding light on the strengths and weaknesses of different learned features across a diverse set of tasks. We find that features produced by standard supervised methods still outperform those produced by self-supervised approaches such as SimCLR. However, improved self-supervised learning methods are constantly being released and the iNat2021 and NeWT datasets are a valuable resource for tracking their progress.

Sara Beery, Elijah Cole, Arvi Gjoka

Camera traps enable the automatic collection of large quantities of image data. Biologists all over the world use camera traps to monitor animal populations. We have recently been making strides towards automatic species classification in camera trap images. However, as we try to expand the geographic scope of these models we are faced with an interesting question: how do we train models that perform well on new (unseen during training) camera trap locations? Can we leverage data from other modalities, such as citizen science data and remote sensing data? In order to tackle this problem, we have prepared a challenge where the training data and test data are from different cameras spread across the globe. For each camera, we provide a series of remote sensing imagery that is tied to the location of the camera. We also provide citizen science imagery from the set of species seen in our data. The challenge is to correctly classify species in the test camera traps.

Sara Beery, Guanhang Wu, Vivek Rathod et al.

In static monitoring cameras, useful contextual information can stretch far beyond the few seconds typical video understanding models might see: subjects may exhibit similar behavior over multiple days, and background objects remain static. Due to power and storage constraints, sampling frequencies are low, often no faster than one frame per second, and sometimes are irregular due to the use of a motion trigger. In order to perform well in this setting, models must be robust to irregular sampling rates. In this paper we propose a method that leverages temporal context from the unlabeled frames of a novel camera to improve performance at that camera. Specifically, we propose an attention-based approach that allows our model, Context R-CNN, to index into a long term memory bank constructed on a per-camera basis and aggregate contextual features from other frames to boost object detection performance on the current frame. We apply Context R-CNN to two settings: (1) species detection using camera traps, and (2) vehicle detection in traffic cameras, showing in both settings that Context R-CNN leads to performance gains over strong baselines. Moreover, we show that increasing the contextual time horizon leads to improved results. When applied to camera trap data from the Snapshot Serengeti dataset, Context R-CNN with context from up to a month of images outperforms a single-frame baseline by 17.9% mAP, and outperforms S3D (a 3d convolution based baseline) by 11.2% mAP.

Mohammad Sadegh Norouzzadeh, Dan Morris, Sara Beery et al.

Biodiversity conservation depends on accurate, up-to-date information about wildlife population distributions. Motion-activated cameras, also known as camera traps, are a critical tool for population surveys, as they are cheap and non-intrusive. However, extracting useful information from camera trap images is a cumbersome process: a typical camera trap survey may produce millions of images that require slow, expensive manual review. Consequently, critical information is often lost due to resource limitations, and critical conservation questions may be answered too slowly to support decision-making. Computer vision is poised to dramatically increase efficiency in image-based biodiversity surveys, and recent studies have harnessed deep learning techniques for automatic information extraction from camera trap images. However, the accuracy of results depends on the amount, quality, and diversity of the data available to train models, and the literature has focused on projects with millions of relevant, labeled training images. Many camera trap projects do not have a large set of labeled images and hence cannot benefit from existing machine learning techniques. Furthermore, even projects that do have labeled data from similar ecosystems have struggled to adopt deep learning methods because image classification models overfit to specific image backgrounds (i.e., camera locations). In this paper, we focus not on automating the labeling of camera trap images, but on accelerating this process. We combine the power of machine intelligence and human intelligence to build a scalable, fast, and accurate active learning system to minimize the manual work required to identify and count animals in camera trap images. Our proposed scheme can match the state of the art accuracy on a 3.2 million image dataset with as few as 14,100 manual labels, which means decreasing manual labeling effort by over 99.5%.

Sara Beery, Dan Morris, Siyu Yang

Biologists all over the world use camera traps to monitor biodiversity and wildlife population density. The computer vision community has been making strides towards automating the species classification challenge in camera traps, but it has proven difficult to to apply models trained in one region to images collected in different geographic areas. In some cases, accuracy falls off catastrophically in new region, due to both changes in background and the presence of previously-unseen species. We propose a pipeline that takes advantage of a pre-trained general animal detector and a smaller set of labeled images to train a classification model that can efficiently achieve accurate results in a new region.

Sara Beery, Dan Morris, Pietro Perona

Camera Traps (or Wild Cams) enable the automatic collection of large quantities of image data. Biologists all over the world use camera traps to monitor biodiversity and population density of animal species. The computer vision community has been making strides towards automating the species classification challenge in camera traps, but as we try to expand the scope of these models from specific regions where we have collected training data to different areas we are faced with an interesting problem: how do you classify a species in a new region that you may not have seen in previous training data? In order to tackle this problem, we have prepared a dataset and challenge where the training data and test data are from different regions, namely The American Southwest and the American Northwest. We use the Caltech Camera Traps dataset, collected from the American Southwest, as training data. We add a new dataset from the American Northwest, curated from data provided by the Idaho Department of Fish and Game (IDFG), as our test dataset. The test data has some class overlap with the training data, some species are found in both datasets, but there are both species seen during training that are not seen during test and vice versa. To help fill the gaps in the training species, we allow competitors to utilize transfer learning from two alternate domains: human-curated images from iNaturalist and synthetic images from Microsoft's TrapCam-AirSim simulation environment.

Sara Beery, Grant van Horn, Oisin Mac Aodha et al.

Camera traps are a valuable tool for studying biodiversity, but research using this data is limited by the speed of human annotation. With the vast amounts of data now available it is imperative that we develop automatic solutions for annotating camera trap data in order to allow this research to scale. A promising approach is based on deep networks trained on human-annotated images. We provide a challenge dataset to explore whether such solutions generalize to novel locations, since systems that are trained once and may be deployed to operate automatically in new locations would be most useful.

Sara Beery, Yang Liu, Dan Morris et al.

The ability to detect and classify rare occurrences in images has important applications - for example, counting rare and endangered species when studying biodiversity, or detecting infrequent traffic scenarios that pose a danger to self-driving cars. Few-shot learning is an open problem: current computer vision systems struggle to categorize objects they have seen only rarely during training, and collecting a sufficient number of training examples of rare events is often challenging and expensive, and sometimes outright impossible. We explore in depth an approach to this problem: complementing the few available training images with ad-hoc simulated data. Our testbed is animal species classification, which has a real-world long-tailed distribution. We analyze the effect of different axes of variation in simulation, such as pose, lighting, model, and simulation method, and we prescribe best practices for efficiently incorporating simulated data for real-world performance gain. Our experiments reveal that synthetic data can considerably reduce error rates for classes that are rare, that as the amount of simulated data is increased, accuracy on the target class improves, and that high variation of simulated data provides maximum performance gain.

Sara Beery, Grant van Horn, Pietro Perona

It is desirable for detection and classification algorithms to generalize to unfamiliar environments, but suitable benchmarks for quantitatively studying this phenomenon are not yet available. We present a dataset designed to measure recognition generalization to novel environments. The images in our dataset are harvested from twenty camera traps deployed to monitor animal populations. Camera traps are fixed at one location, hence the background changes little across images; capture is triggered automatically, hence there is no human bias. The challenge is learning recognition in a handful of locations, and generalizing animal detection and classification to new locations where no training data is available. In our experiments state-of-the-art algorithms show excellent performance when tested at the same location where they were trained. However, we find that generalization to new locations is poor, especially for classification systems.