Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time

Sooyoung Jeon; Hongjie Tian; Lemeng Wang; Zheda Mai; Vidhi Bakshi; Jiacheng Hou; Ping Zhang; Arpita Chowdhury

cs.CVMar 20, 2026

Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time

Authors: Sooyoung Jeon, Hongjie Tian, Lemeng Wang, Zheda Mai, Vidhi Bakshi, Jiacheng Hou, Ping Zhang, Arpita Chowdhury,

Organizations: The Ohio State University · Boston University

Abstract

Camera traps are vital for large-scale biodiversity monitoring, yet accurate automated analysis remains challenging due to diverse deployment environments. While the computer vision community has mostly framed this challenge as cross-domain generalization, this perspective overlooks a primary challenge faced by ecological practitioners: maintaining reliable recognition at the fixed site over time, where the dynamic nature of ecosystems introduces profound temporal shifts in both background and animal distributions. To bridge this gap, we present the first unified study of camera-trap species recognition over time. We introduce a realistic benchmark comprising 546 camera traps with a streaming protocol that evaluates models over chronologically ordered intervals. Our end-user-centric study yields four key findings. (1) Biological foundation models (e.g., BioCLIP 2) underperform at numerous sites even in initial intervals, underscoring the necessity of site-specific adaptation. (2) Adaptation is challenging under realistic evaluation: when models are updated using past data and evaluated on future intervals (mirrors real deployment lifecycles), naive adaptation can even degrade below zero-shot performance. (3) We identify two drivers of this difficulty: severe class imbalance and pronounced temporal shift in both species distribution and backgrounds between consecutive intervals. (4) We find that effective integration of model-update and post-processing techniques can largely improve accuracy, though a gap from the upper bounds remains. Finally, we highlight critical open questions, such as predicting when zero-shot models will succeed at a new site and determining whether/when model updates are necessary. Our benchmark and analysis provide actionable deployment guidelines for ecological practitioners while establishing new directions for future research in vision and machine learning.

Figures & tables

Figure 1: (a). Temporal shifts: Even at a fixed site, foreground and background appearances evolve over time due to changing seasons, weather, and animal distribution. (b). Streaming evaluation: Accumulated $\star$ model is fine-tuned with training data up to the current interval and evaluated on the test data of the next interval. For reference, an Oracle $\star$ model is fine-tuned with the union of training data from all time intervals at a site and evaluated on the test data of all intervals. ( $\star$ : our recipe Sec. 4.4 ).

Figure 2: (a). StreamTrap statistics . Top row: histograms of the image, class, and time span; Bottom row: histograms of temporal shift (TCDS, defined in Sec. 4.3 ) and class imbalance metrics (defined in Sec. 3.1 ). (b). Streaming evaluation protocol: models are continually fine-tuned on the labeled data observed so far and evaluated on future unseen data.

Figure 3: (a). Zero-shot accuracy across camera traps. Green :

>90\%

accuracy; orange :

<80\%

. (b). Accuracy difference between oracle naive fine-tuning and zero-shot. Blue : oracle outperforms zero-shot; red : zero-shot is better. (c). Accuracy difference between oracle fine-tuning with our adaptation recipe (Oracle

\star

) and zero-shot.

	C1	C2	C3	C4	C5	C6	C7	C8	C9	C10	C11	C12	C13	C14	C15	C16	C17	C18	C19	C20	Avg
ZS	97.7	92.3	90.9	89.1	86.1	84.3	81.5	81.2	78.3	77.1	75.8	73.8	70.1	69.8	67.1	66.0	62.2	61.5	56.3	55.8	75.8
Accum	73.6	77.1	50.0	71.7	46.7	33.3	56.7	73.0	45.0	25.0	57.0	50.0	68.2	60.8	66.7	11.4	61.7	58.0	33.3	45.7	53.2
$\Delta$	24.1	15.2	40.9	17.4	39.4	51.0	24.8	8.2	33.3	52.1	18.8	23.8	1.9	9.0	0.4	54.6	0.5	3.5	23.0	10.1	–
Accum $\star$	98.7	89.9	89.9	90.8	79.4	79.2	83.4	88.3	81.0	78.7	76.9	70.1	79.4	75.4	86.9	76.6	88.9	71.3	76.7	82.6	82.2
$\Delta$	1.0	2.4	1.0	1.7	6.7	5.1	1.9	7.1	2.7	1.6	1.1	3.7	9.3	5.6	19.8	10.6	26.7	9.8	20.4	26.8	–
Oracle $\star$	98.7	96.4	94.5	96.6	87.8	91.5	91.0	91.0	87.3	82.0	84.3	88.5	91.0	86.6	91.0	83.9	93.8	89.6	89.9	93.4	90.4

Table 1: Accuracy difference (

\Delta

) between zero-shot (ZS) and three fine-tuning methods: naive accumulated fine-tuning (Accum), accumulated fine-tuning with our adaptation recipe (Accum

\star

), fine-tuned on all training data at a site with our recipe (Oracle

\star

). Blue ( red ) denotes improvement (degradation) relative to ZS.

Figure 4: Illustration of temporal shifts. (Top) Images from a camera trap showing shifting context (vegetation, lighting, weather) over time. (Bottom) TCDS comparison of two camera traps (pie chart: class frequency per interval): the left camera exhibits much higher temporal shifts ( TCDS=0.7712 ) than the right one ( TCDS=0.1166 ).

Figure 5: Performance gain (

\Delta_{\text{Accum}\star}

) of calibration, weight interpolation, and model selection over the Accum ⋆ baseline. They are applied on top of Accum ⋆ . More results can be found in Sec. 0.C.3 .

Figure 6: (a). Non-OOD scores (MSP) moderately correlate with zero-shot accuracy. (b). The Adapt-or-Skip problem: should we adapt at this interval or not?.

Stage	$0\%$	$25\%$	$50\%$	$75\%$	$100\%$
Acc.	76.2	73.1	77.8	82.7	84.9

Table 2: Accum

\star

is frozen at a specific interval ( e.g . , 25% means frozen after adaptation with the first 25% intervals) and evaluated on all future intervals. Averaged across 8 camera traps with long deployment durations spanning more than one year.

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

BioCLIP 2 [ 19 ]	CLIP [ 42 ]
84.3	72.3

Appendix

Table 3: Zero-shot baseline selection. Average per-class accuracy (%) across all camera traps in the StreamTrap . BioCLIP 2 is selected as the zero-shot baseline due to its superior performance.

Hyperparameter	Value
Optimizer	AdamW
Max Learning Rate	$2.5\times 10^{-5}$
Min Learning Rate	$4.17\times 10^{-7}$
Weight Decay	$1\times 10^{-4}$
LR Schedule	Cosine Annealing ( $T_{\text{max}}=60$ )
Batch Size	32

Appendix

Table 4: Training configuration for fine-tuning BioCLIP 2.

Loss	FT Method	Accuracy
CE	Full	85.9
BSM [ 43 ]	Full	85.1
CB-Focal [ 12 ]	Full	83.2
CDT [ 61 ]	Full	83.2
CE	LoRA [ 22 ]	86.0
CE	VPT [ 25 ]	76.6

Appendix

Table 5: Ablation of imbalance losses and PEFT fine-tuning (FT) methods. Average per-class accuracy (%) is reported. BSM and LoRA achieve the best performance. Our proposed adaptation recipe (

\star

) is highlighted in blue .

	Closed-Set	Open-Set	Closed-Set + Rare Species
Zero-shot	82.5	37.8	73.1
Accum $\star$	83.7	76.7	73.4
Oracle $\star$	88.3	86.1	66.8

Appendix

Table 6: Average per-class accuracy (%) under relaxed evaluation assumptions. Open-Set expands the vocabulary to all 1,096 classes across StreamTrap . Rare Species adds rare classes (fewer than 10 samples per interval) to the test set.

Figure 7: (a.) Detailed accuracy difference between oracle fine-tuning with our adaptation recipe (Oracle $\star$ ) and zero-shot ( Fig. 3 in the main paper). (b.) Qualitative examples of camera traps with severely degraded visual quality (e.g., blur, exposure artifacts, and sensor noise).

Figure 8: Performance gain (

\Delta{\text{accum}\star}

) of calibration, weight interpolation, and model selection over the accum ⋆ baseline across 50 cameras. They are applied on top of accum ⋆ .

	Accuracy	$\Delta{\text{Oracle}\star}$
Oracle $\star$	87.0	–
Accum $\star$	79.8	7.1
+ Calibration	83.7	3.3
+ Weight Interpolation	83.2	3.8
+ Model Selection	86.1	0.9
+ Best Post-Processing	86.7	0.2

Appendix

Table 7: Extended post-processing results by average per-class accuracy (%).

\Delta{\text{oracle}\star}

denotes remaining gap to Oracle

\star

(87.6 %). Each method is applied on top of accum

\star

. The last row selects the best-performing post-processing method per camera trap.

Panel of Figure 9 — Figure 9: Comparison of adapt-or-not methods on our balanced benchmark. Each interval is labeled as either a Skip case (where not adapting is correct) or an Adapt case (where adapting is correct), with Combined reporting overall accuracy across all intervals. Methods include Random, MSP-based, Feature-based, Always Adapt, Always Skip, and an Oracle upper bound. (a). Balanced accuracy under Skip, Adapt, and Combined evaluation. (b.) Binary decision accuracy of each method.

Figure 10: Detailed camera trap data processing pipeline. Raw camera trap images and metadata are filtered, temporally chunked, and cropped into standardized animal patches, producing per-camera chronological streams for online continual evaluation.

Figure 11: Illustration of burst images from a single sequence. Upon detecting motion, the camera captures multiple frames in rapid succession, producing images that share the same environment, background, and animal appearance.

		Original Dataset			StreamTrap
Dataset	Continent	# Img	# Cls	# Traps	# Img	# Cls	# Traps
Caltech Camera Traps [ 7 ]	N. America	243.1K	22	140	37.6K	13	15
Idaho Camera Traps [ 23 ]	N. America	1535.7K	62	276	43.6K	10	15
NA Camera Trap Img [ 51 ]	N. America	3280.8K	59	551	964.9K	20	52
NZ Trail Cam. Animals [ 38 ]	Oceania	2045.8K	98	2469	543.9K	41	139
Orinoquía Camera Traps [ 58 ]	S. America	112.2K	58	49	20.1K	16	6

Appendix

Table 9: Summary of dataset statistics from the selected original LILA BC sources and StreamTrap after applying the proposed data processing and filtering pipeline. Datasets marked with * indicate datasets grouped under the unified project Snapshot Safari 2024 Expansion [ 40 ] . Image counts are reported in thousands (K) with one-decimal precision.

Dataset	Camera Trap	Index C	Dataset	Camera Trap	Index C
Snapshot APNR	K082	1	Snapshot Serengeti	L06	59
NA Camera Trap Img	lebec_CA-19	2	NZ Trail Cam. Animals	EFH_HCAMH02	60
Snapshot Madikwe	G08	3	NZ Trail Cam. Animals	EFD_DCAMC05	61
NZ Trail Cam. Animals	EFH_HCAMF12	4	NZ Trail Cam. Animals	EFH_HCAMC06	62
Snapshot Serengeti	G13	5	Orinoquía Camera Traps	M04	63
NZ Trail Cam. Animals	PS1_CAM7709	6	NZ Trail Cam. Animals	EFH_HCAMD10	64

Appendix

Table 10: Camera trap index reorganized by the new camera index. Each camera trap is assigned an index

C_{i}

(e.g.,

C_{1}

C_{2}

) used to reference camera traps in figures and tables throughout the paper.

Camera	# Images	# Intervals	# Classes
Snapshot APNR
13U	6,329	23	9
6U	2,081	10	8
BOSP	1,759	6	6
JJ5	4,560	21	9
JJ6	3,223	16	10

Appendix

Table 11: StreamTrap overall camera trap statistics.

Temporal Domain Adaptation

See all 10 papers

Multi-Object Tracking Consistently Improves Wildlife Inference
May 15, 2026Mufhumudzi Muthivhi, Jiahao Huo, Fredrik Gustafsson +1Temporal Consistency Wildlife Monitoring
Academy of Computer Science and Software Engineering University of Johannesburg Johannesburg, South Africa · Department of Electrical Engineering Linköping University Linköping, Sweden
Benchmarking NACTI Species Recognition in Long-Tailed Regimes
Jul 20, 2026Zehua Liu, Tilo BurghardtLong-Tailed Classification OOD Generalization
School of Computer Science, University of Bristol, MVB Woodland Rd, BS8 1UB, Bristol, UK
Can Edge-Deployable Vision-Language Models Identify Species?
Sep 10, 2026William Zhou, Mayukha Siripuram, Xiao Yan +2VLM Evaluation VLM Robustness
Plano West Senior High School

May 15, 2026J/K move · Enter open · S save

Multi-Object Tracking Consistently Improves Wildlife Inference

Mufhumudzi Muthivhi, Jiahao Huo, Fredrik Gustafsson, Terence L. van Zyl

Academy of Computer Science and Software Engineering University of Johannesburg Johannesburg, South Africa · Department of Electrical Engineering Linköping University Linköping, Sweden

Temporal Consistency Wildlife Monitoring

Open paper AskPDF arXiv

Camera traps have become a common tool for wildlife monitoring efforts in ecological research and biodiversity conservation. Wildlife classification models have benefited from the increase in wildlife visual data. These models reach high levels of accuracy on curated, high-quality datasets. However, their performance remains sensitive to real-world environmental constraints. They often produce inconsistent predictions when performing inference on temporally coherent sequences. The predicted label for a single individual shifts rapidly between frames. This study exploits the temporal nature of camera-trap data to augment inferred predictions from a wildlife classification model. Specifically, we adopt several standard Multi-Object Tracking (MOT) models to link detections across consecutive frames. The curated trajectories are used to fuse the softmax class probabilities. The fused probability score produces a single consensus class label estimate that overrides misclassifications caused by noise. The analysis of the experimental results shows that our proposed strategy improves over a standalone classifier over all datasets and for each metric. Specifically, the best-performing MOT models gain a weighted F1-Score of 5.1%, 3.1% and 2.0% over the classifier across three MOT datasets.

Abstract

Temporal Domain Adaptation

Explore similar work

Multi-Object Tracking Consistently Improves Wildlife Inference

Benchmarking NACTI Species Recognition in Long-Tailed Regimes

Can Edge-Deployable Vision-Language Models Identify Species?